Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+gguf/base-v7-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/base-v7-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/comparison.png filter=lfs diff=lfs merge=lfs -text
+workflows/pony-v7-simple.png filter=lfs diff=lfs merge=lfs -text
+workflows/pony-v7-simple-gguf.png filter=lfs diff=lfs merge=lfs -text
+workflows/pony-v7-noise-selection.png filter=lfs diff=lfs merge=lfs -text
+workflows/pony-v7-lora.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,131 @@
+---
+license: other
+license_name: pony-license
+license_link: LICENSE
+---
+
+# Pony V7
+
+![Pony V7](V7.webp)
+
+Pony V7 is a versatile character generation model based on AuraFlow architecture. It supports a wide range of styles and species types (humanoid, anthro, feral, and more) and handles character interactions through natural language prompts.
+
+## Fictional
+
+First, let me introduce [Fictional](https://fictional.ai) - our multimodal platform where AI Characters come alive through text, images, voice, and (soon) video. Powered by PonyV7, V6, Chroma, Seedream 4, and other advanced models, Fictional lets you discover, create, and interact with characters who live their own lives and share their own stories.
+
+Fictional is also what enables the development of models like V7, so if you're excited about the future of multimodal AI characters, please download Fictional on iOS or Android and help shape our future!
+
+- **iOS**: https://apps.apple.com/us/app/fictional/id6739802573
+- **Android**: https://play.google.com/store/apps/details?id=ai.fictional.app
+
+### Get in touch with us
+
+Please join [our Discord Server](https://discord.gg/pYsdjMfu3q) if you have questions about Fictional and Pony models.
+
+## Important model information
+
+Please check [this article](https://civitai.com/articles/19986) to learn more about why it took so long for us to ship V7 and upcoming model releases.
+
+## Important HuggingFace links
+
+- **[GGUF Models](gguf/README.md)** - Quantized models for lower VRAM usage (Q8_0 recommended for best quality/size balance)
+- **[Safetensor Model](safetensor/README.md)** - Single-file safetensors format for easier loading
+- **[LoRA Training](lora/README.md)** - Information and tools for training LoRAs with SimpleTuner
+- **[Workflows](workflows/README.md)** - ComfyUI workflow examples for standard and GGUF inference
+- **[ComfyUI Nodes](comfy_nodes/README.md)** - Custom PonyNoise node for GPU/CPU noise selection
+
+
+## Model prompting
+
+This model supports a wide array of styles and aesthetics but provides an opinionated default prompt template:
+
+```
+special tags, factual description of image, stylistic description of image, additional content tags
+```
+
+### Special Tags
+
+`score_X`, `style_cluster_x`, `source_X` - warning: V7 prompting may be inconsistent, please see the article as we are working on V7.1 to address this.
+
+### Factual description of image
+
+Description of what is portrayed in the image without any stylistic indicators. Two recommendations:
+
+1. Start with a single phrase describing what you want in the image before going into details
+
+2. When referring to characters use pattern: `<species> <gender> <name> from <source>`
+
+For example "Anthro bunny female Lola Bunny from Space Jam".
+
+This model is capable of recognizing many popular and obscure characters and series.
+
+### Stylistic description of image
+
+Any information about image medium, shot type, lighting, etc. (More info TBD with captioning Colab)
+
+### Tags
+
+V7 is trained on a combination of natural language prompts and tags and is capable of understanding both, so describing the intended result using normal language works in most cases, although you can add some tags after the main prompt to boost them.
+
+### Captioning Colab
+
+To get a better understanding of V7 prompting, we are releasing a [captioning Colab](https://colab.research.google.com/drive/19PG-0ltob8EynxUZSwOdjMFmqyJ7ZOCB) with all the models used for V7 captioning.
+
+## Supported inference settings
+
+V7 supports resolutions in the range of 768px to 1536px. It is recommended to go for higher resolutions and at least 30 steps during inference.
+
+## Highlights compared to V6
+
+- Much stronger understanding of prompts, especially when it comes to spatial information and multiple characters
+- Much stronger background support - both generation of backgrounds and using background with character
+- Much stronger realism support out of the box
+- Ability to generate very dark and very light images
+- Resolution up to 1536x1536 pixels
+- Expanded character recognition (some V6 characters may get less recognized, but generally we extended the knowledge by a lot)
+
+## Special thanks
+
+- Iceman for helping to procure necessary training resources
+- [Simo Ryu](https://x.com/cloneofsimo) and the rest of FAL.ai team for creating AuraFlow and emotional support
+- [Runpod for providing captioning compute](https://runpod.io/?utm_source=purplesmartai)
+- [Piclumen](https://www.piclumen.com/) for being our partners
+- [City96](https://github.com/city96) for help with GGUF support
+- [diffusers](https://huggingface.co/docs/diffusers/en/index) team for supporting AuraFlow integration work
+- PSAI Server Subscribers for supporting the project costs
+- PSAI Server Moderators for being vigilant and managing the community
+- Many supporters that decided to remain anonymous but their help has been critical for getting V7 done
+
+## Technical details
+
+The model has been trained on ~10M images aesthetically ranked and selected from a superset of over 30M images with roughly 1:1 ratio between anime/cartoon/furry/pony datasets and 1:1 ratio between safe/questionable/explicit ratings. 100% of all images have been tagged and captioned with high quality detailed captions.
+
+All images have been used in training with both captions and tags. Artists' names have been removed and source data has been filtered based on our Opt-in/Opt-out program. Any inappropriate explicit content has been filtered out.
+
+## Limitations
+
+- This model does not support text generation and has degraded text generation capabilities compared to base AuraFlow
+- Special tags (including quality tags) have much weaker performance compared to V6, meaning score_9 would not necessarily yield better results on some prompts. We are working on a V7.1 follow-up to improve this
+- Small details and especially faces may degrade significantly depending on art style, this is a combination of outdated VAE and insufficient training which we are trying to improve in V7.1
+
+## LoRA training
+
+We recommend using SimpleTuner for LoRA training following [this guide](https://github.com/bghira/SimpleTuner/blob/main/documentation/quickstart/AURAFLOW.md). 
+
+For information on converting SimpleTuner LoRAs to diffusers/ComfyUI compatible format, see the [LoRA folder](lora/). A [LoRA workflow example](workflows/pony-v7-lora.png) is also available.
+
+
+## Commercial API
+
+We provide [commercial API](https://fal.ai/models/fal-ai/pony-v7) via our exclusive partner FAL.ai
+
+## License
+
+This model is licensed under a Pony License
+
+In short, you can use this model and its outputs commercially unless you provide an inference service or application, have a company with over 1M revenue or use in professional video production. This limitations do not apply if you use first party commercial APIs.
+
+If you want to use this model commercially, please reach us at [email protected].
+
+Explicit permission for commercial inference has been granted to CivitAi and Hugging Face.

comfy_nodes/ComfyUI_PonyNoise.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d38d47ae4509d87a55ed21aec01c33fd537013b0a68f70c2fbc26cf7640fc7
+size 1165

comfy_nodes/README.md

@@ -0,0 +1,26 @@
+# ComfyUI PonyNoise Node
+
+## Download
+
+📦 [ComfyUI_PonyNoise.zip](ComfyUI_PonyNoise.zip)
+
+## Overview
+
+ComfyUI uses CPU noise by default to ensure consistency across different platforms, while `diffusers` use GPU noise by default. However, GPU noise generation may vary between different GPU models, although it typically remains consistent across the latest NVIDIA cards.
+
+This custom node provides the flexibility to switch between GPU and CPU noise generation modes, enabling you to match `diffusers` output on the same machine when needed.
+
+## Usage
+
+To get started with the PonyNoise node, please refer to the [noise selection workflow](../workflows/pony-v7-noise-selection.png) which demonstrates proper configuration and integration with your generation pipeline.
+
+## Installation
+
+1. Download the [ComfyUI_PonyNoise.zip](ComfyUI_PonyNoise.zip) file
+2. Extract the contents to your ComfyUI custom nodes directory
+3. Restart ComfyUI
+4. Load the workflow
+
+## Acknowledgments
+
+Special thanks to [Silver](https://github.com/silveroxides) for adapting the [ComfyUI Noise nodes](https://github.com/BlenderNeko/ComfyUI_Noise) and helping with workflows.

gguf/README.md

@@ -0,0 +1,22 @@
+# Pony V7 GGUFs
+
+Install the ComfyUI [GGUF nodes by City96](https://github.com/city96/ComfyUI-GGUF) before using these workflows.
+
+We recommend Q8_0 for the best balance between quality and file size.
+
+| VARIANT | MAX VRAM |
+|---------|------|
+| F16 | ~16GB |
+| [Q8_0](base-v7-Q8_0.gguf) | ~10GB |
+| Q6_K | ~8GB |
+| Q5_K_M | ~7GB |
+| [Q4_0](base-v7-Q4_0.gguf) | ~6.5GB |
+| Q4_K_M | ~6.5GB |
+| Q3_K_L | ~6GB |
+| Q3_K_S | ~6GB |
+| Q2_K | ~5GB |
+
+Download ComfyUI workflow for GGUF [here](../workflows/poly-v7-gguf.png).
+
+![GGUF comparison](comparison.png)
+

gguf/base-v7-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091f36054915e573f64ca44d05eca27c67a1d758ea12b456d9cae47e6298cf68
+size 3949749536

gguf/base-v7-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50bb230f0a198a7e20dea9f19a21d0a9fb3b49e7833c39c2f5334adb4cfcb912
+size 7347135776

lora/README.md

@@ -0,0 +1,24 @@
+# Pony V7 LoRA Training
+
+## Training Guide
+
+We recommend using SimpleTuner for LoRA training following [this guide](https://github.com/bghira/SimpleTuner/blob/main/documentation/quickstart/AURAFLOW.md).
+
+## ComfyUI LoRA Workflow
+
+A [LoRA workflow example](../workflows/pony-v7-lora.png) is available showing how to load and use LoRAs with Pony V7. Simply drag and drop the workflow image into your ComfyUI canvas to load it.
+
+## LoRA Conversion Script
+
+### [convert_simpletuner_lora.py](convert_simpletuner_lora.py)
+
+A utility script to convert SimpleTuner LoRA weights to diffusers-compatible format for AuraFlow models.
+
+**Usage:**
+```bash
+python convert_simpletuner_lora.py <input_lora.safetensors> <output_lora.safetensors>
+```
+
+
+This script ensures your LoRAs trained with SimpleTuner can be loaded directly with diffusers' `load_lora_weights()` method or inside of ComfyUI's LoRA nodes.
+

lora/convert_simpletuner_lora.py

@@ -0,0 +1,483 @@
+#!/usr/bin/env python3
+"""
+Convert SimpleTuner LoRA weights to diffusers-compatible format for AuraFlow.
+
+This script converts LoRA weights saved by SimpleTuner into a format that can be
+directly loaded by diffusers' load_lora_weights() method.
+
+Usage:
+    python convert_simpletuner_lora.py <input_lora.safetensors> <output_lora.safetensors>
+
+Example:
+    python convert_simpletuner_lora.py input_lora.safetensors diffusers_compatible_lora.safetensors
+"""
+
+import argparse
+import sys
+from pathlib import Path
+from typing import Dict
+
+import safetensors.torch
+import torch
+
+
+def detect_lora_format(state_dict: Dict[str, torch.Tensor]) -> str:
+    """
+    Detect the format of the LoRA state dict.
+    
+    Returns:
+        "peft" if already in PEFT/diffusers format
+        "mixed" if mixed format (some lora_A/B, some lora.down/up)
+        "simpletuner_transformer" if in SimpleTuner format with transformer prefix
+        "simpletuner_auraflow" if in SimpleTuner AuraFlow format
+        "kohya" if in Kohya format
+        "unknown" otherwise
+    """
+    keys = list(state_dict.keys())
+    
+    # Check the actual weight naming convention (lora_A/lora_B vs lora_down/lora_up)
+    has_lora_a_b = any((".lora_A." in k or ".lora_B." in k) for k in keys)
+    has_lora_down_up = any((".lora_down." in k or ".lora_up." in k) for k in keys)
+    has_lora_dot_down_up = any((".lora.down." in k or ".lora.up." in k) for k in keys)
+    
+    # Check prefixes
+    has_transformer_prefix = any(k.startswith("transformer.") for k in keys)
+    has_lora_transformer_prefix = any(k.startswith("lora_transformer_") for k in keys)
+    has_lora_unet_prefix = any(k.startswith("lora_unet_") for k in keys)
+    
+    # Mixed format: has both lora_A/B AND lora.down/up (SimpleTuner hybrid)
+    if has_transformer_prefix and has_lora_a_b and (has_lora_down_up or has_lora_dot_down_up):
+        return "mixed"
+    
+    # Pure PEFT format: transformer.* with ONLY lora_A/lora_B
+    if has_transformer_prefix and has_lora_a_b and not has_lora_down_up and not has_lora_dot_down_up:
+        return "peft"
+    
+    # SimpleTuner with transformer prefix but old naming: transformer.* with lora_down/lora_up
+    if has_transformer_prefix and (has_lora_down_up or has_lora_dot_down_up):
+        return "simpletuner_transformer"
+    
+    # SimpleTuner AuraFlow format: lora_transformer_* with lora_down/lora_up
+    if has_lora_transformer_prefix and has_lora_down_up:
+        return "simpletuner_auraflow"
+    
+    # Traditional Kohya format: lora_unet_* with lora_down/lora_up
+    if has_lora_unet_prefix and has_lora_down_up:
+        return "kohya"
+    
+    return "unknown"
+
+
+def convert_mixed_lora_to_diffusers(state_dict: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
+    """
+    Convert mixed LoRA format to pure PEFT format.
+    
+    SimpleTuner sometimes saves a hybrid format where some layers use lora_A/lora_B
+    and others use .lora.down./.lora.up. This converts all to lora_A/lora_B.
+    """
+    new_state_dict = {}
+    converted_count = 0
+    kept_count = 0
+    skipped_count = 0
+    renames = []
+    
+    # Get all keys
+    all_keys = sorted(state_dict.keys())
+    
+    print("\nProcessing keys:")
+    print("-" * 80)
+    
+    for key in all_keys:
+        # Already in correct format (lora_A or lora_B)
+        if ".lora_A." in key or ".lora_B." in key:
+            new_state_dict[key] = state_dict[key]
+            kept_count += 1
+        
+        # Needs conversion: .lora.down. -> .lora_A.
+        elif ".lora.down.weight" in key:
+            new_key = key.replace(".lora.down.weight", ".lora_A.weight")
+            new_state_dict[new_key] = state_dict[key]
+            renames.append((key, new_key))
+            converted_count += 1
+        
+        # Needs conversion: .lora.up. -> .lora_B.
+        elif ".lora.up.weight" in key:
+            new_key = key.replace(".lora.up.weight", ".lora_B.weight")
+            new_state_dict[new_key] = state_dict[key]
+            renames.append((key, new_key))
+            converted_count += 1
+        
+        # Skip alpha keys (not used in PEFT format)
+        elif ".alpha" in key:
+            skipped_count += 1
+            continue
+        
+        # Other keys (shouldn't happen, but keep them just in case)
+        else:
+            new_state_dict[key] = state_dict[key]
+            print(f"⚠ Warning: Unexpected key format: {key}")
+    
+    print(f"\nSummary:")
+    print(f"  ✓ Kept {kept_count} keys already in correct format (lora_A/lora_B)")
+    print(f"  ✓ Converted {converted_count} keys from .lora.down/.lora.up to lora_A/lora_B")
+    print(f"  ✓ Skipped {skipped_count} alpha keys")
+    
+    if renames:
+        print(f"\nRenames applied ({len(renames)} conversions):")
+        print("-" * 80)
+        for old_key, new_key in renames:
+            # Show the difference more clearly
+            if ".lora.down.weight" in old_key:
+                layer = old_key.replace(".lora.down.weight", "")
+                print(f"  {layer}")
+                print(f"    .lora.down.weight  →  .lora_A.weight")
+            elif ".lora.up.weight" in old_key:
+                layer = old_key.replace(".lora.up.weight", "")
+                print(f"  {layer}")
+                print(f"    .lora.up.weight    →  .lora_B.weight")
+    
+    return new_state_dict
+
+
+def convert_simpletuner_transformer_to_diffusers(state_dict: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
+    """
+    Convert SimpleTuner transformer format (already has transformer. prefix but uses lora_down/lora_up)
+    to diffusers PEFT format (transformer. prefix with lora_A/lora_B).
+    
+    This is a simpler conversion since the key structure is already correct.
+    """
+    new_state_dict = {}
+    renames = []
+    
+    # Get all unique LoRA layer base names (without .lora_down/.lora_up/.alpha suffix)
+    all_keys = list(state_dict.keys())
+    base_keys = set()
+    
+    for key in all_keys:
+        if ".lora_down.weight" in key:
+            base_key = key.replace(".lora_down.weight", "")
+            base_keys.add(base_key)
+    
+    print(f"\nFound {len(base_keys)} LoRA layers to convert")
+    print("-" * 80)
+    
+    # Convert each layer
+    for base_key in sorted(base_keys):
+        down_key = f"{base_key}.lora_down.weight"
+        up_key = f"{base_key}.lora_up.weight"
+        alpha_key = f"{base_key}.alpha"
+        
+        if down_key not in state_dict or up_key not in state_dict:
+            print(f"⚠ Warning: Missing weights for {base_key}")
+            continue
+        
+        down_weight = state_dict.pop(down_key)
+        up_weight = state_dict.pop(up_key)
+        
+        # Handle alpha scaling
+        has_alpha = False
+        if alpha_key in state_dict:
+            alpha = state_dict.pop(alpha_key)
+            lora_rank = down_weight.shape[0]
+            scale = alpha / lora_rank
+            
+            # Calculate scale_down and scale_up to preserve the scale value
+            scale_down = scale
+            scale_up = 1.0
+            while scale_down * 2 < scale_up:
+                scale_down *= 2
+                scale_up /= 2
+            
+            down_weight = down_weight * scale_down
+            up_weight = up_weight * scale_up
+            has_alpha = True
+        
+        # Store in PEFT format (lora_A = down, lora_B = up)
+        new_down_key = f"{base_key}.lora_A.weight"
+        new_up_key = f"{base_key}.lora_B.weight"
+        
+        new_state_dict[new_down_key] = down_weight
+        new_state_dict[new_up_key] = up_weight
+        
+        renames.append((down_key, new_down_key, has_alpha))
+        renames.append((up_key, new_up_key, has_alpha))
+    
+    # Check for any remaining keys
+    remaining = [k for k in state_dict.keys() if not k.startswith("text_encoder")]
+    if remaining:
+        print(f"⚠ Warning: {len(remaining)} keys were not converted: {remaining[:5]}")
+    
+    print(f"\nRenames applied ({len(renames)} conversions):")
+    print("-" * 80)
+    
+    # Group by layer
+    current_layer = None
+    for old_key, new_key, has_alpha in renames:
+        layer = old_key.replace(".lora_down.weight", "").replace(".lora_up.weight", "")
+        
+        if layer != current_layer:
+            alpha_str = " (alpha scaled)" if has_alpha else ""
+            print(f"\n  {layer}{alpha_str}")
+            current_layer = layer
+        
+        if ".lora_down.weight" in old_key:
+            print(f"    .lora_down.weight  →  .lora_A.weight")
+        elif ".lora_up.weight" in old_key:
+            print(f"    .lora_up.weight    →  .lora_B.weight")
+    
+    return new_state_dict
+
+
+def convert_simpletuner_auraflow_to_diffusers(state_dict: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
+    """
+    Convert SimpleTuner AuraFlow LoRA format to diffusers PEFT format.
+    
+    SimpleTuner typically saves LoRAs in a format similar to Kohya's sd-scripts,
+    but for transformer-based models like AuraFlow, the keys may differ.
+    """
+    new_state_dict = {}
+    
+    def _convert(original_key, diffusers_key, state_dict, new_state_dict):
+        """Helper to convert a single LoRA layer."""
+        down_key = f"{original_key}.lora_down.weight"
+        if down_key not in state_dict:
+            return False
+            
+        down_weight = state_dict.pop(down_key)
+        lora_rank = down_weight.shape[0]
+        
+        up_weight_key = f"{original_key}.lora_up.weight"
+        up_weight = state_dict.pop(up_weight_key)
+        
+        # Handle alpha scaling
+        alpha_key = f"{original_key}.alpha"
+        if alpha_key in state_dict:
+            alpha = state_dict.pop(alpha_key)
+            scale = alpha / lora_rank
+            
+            # Calculate scale_down and scale_up to preserve the scale value
+            scale_down = scale
+            scale_up = 1.0
+            while scale_down * 2 < scale_up:
+                scale_down *= 2
+                scale_up /= 2
+            
+            down_weight = down_weight * scale_down
+            up_weight = up_weight * scale_up
+        
+        # Store in PEFT format (lora_A = down, lora_B = up)
+        diffusers_down_key = f"{diffusers_key}.lora_A.weight"
+        new_state_dict[diffusers_down_key] = down_weight
+        new_state_dict[diffusers_down_key.replace(".lora_A.", ".lora_B.")] = up_weight
+        
+        return True
+    
+    # Get all unique LoRA layer names
+    all_unique_keys = {
+        k.replace(".lora_down.weight", "").replace(".lora_up.weight", "").replace(".alpha", "")
+        for k in state_dict
+        if ".lora_down.weight" in k or ".lora_up.weight" in k or ".alpha" in k
+    }
+    
+    # Process transformer blocks
+    for original_key in sorted(all_unique_keys):
+        if original_key.startswith("lora_transformer_single_transformer_blocks_"):
+            # Single transformer blocks
+            parts = original_key.split("lora_transformer_single_transformer_blocks_")[-1].split("_")
+            block_idx = int(parts[0])
+            diffusers_key = f"single_transformer_blocks.{block_idx}"
+            
+            # Map the rest of the key
+            remaining = "_".join(parts[1:])
+            if "attn_to_q" in remaining:
+                diffusers_key += ".attn.to_q"
+            elif "attn_to_k" in remaining:
+                diffusers_key += ".attn.to_k"
+            elif "attn_to_v" in remaining:
+                diffusers_key += ".attn.to_v"
+            elif "proj_out" in remaining:
+                diffusers_key += ".proj_out"
+            elif "proj_mlp" in remaining:
+                diffusers_key += ".proj_mlp"
+            elif "norm_linear" in remaining:
+                diffusers_key += ".norm.linear"
+            else:
+                print(f"Warning: Unhandled single block key pattern: {original_key}")
+                continue
+                
+        elif original_key.startswith("lora_transformer_transformer_blocks_"):
+            # Double transformer blocks
+            parts = original_key.split("lora_transformer_transformer_blocks_")[-1].split("_")
+            block_idx = int(parts[0])
+            diffusers_key = f"transformer_blocks.{block_idx}"
+            
+            # Map the rest of the key
+            remaining = "_".join(parts[1:])
+            if "attn_to_out_0" in remaining:
+                diffusers_key += ".attn.to_out.0"
+            elif "attn_to_add_out" in remaining:
+                diffusers_key += ".attn.to_add_out"
+            elif "attn_to_q" in remaining:
+                diffusers_key += ".attn.to_q"
+            elif "attn_to_k" in remaining:
+                diffusers_key += ".attn.to_k"
+            elif "attn_to_v" in remaining:
+                diffusers_key += ".attn.to_v"
+            elif "attn_add_q_proj" in remaining:
+                diffusers_key += ".attn.add_q_proj"
+            elif "attn_add_k_proj" in remaining:
+                diffusers_key += ".attn.add_k_proj"
+            elif "attn_add_v_proj" in remaining:
+                diffusers_key += ".attn.add_v_proj"
+            elif "ff_net_0_proj" in remaining:
+                diffusers_key += ".ff.net.0.proj"
+            elif "ff_net_2" in remaining:
+                diffusers_key += ".ff.net.2"
+            elif "ff_context_net_0_proj" in remaining:
+                diffusers_key += ".ff_context.net.0.proj"
+            elif "ff_context_net_2" in remaining:
+                diffusers_key += ".ff_context.net.2"
+            elif "norm1_linear" in remaining:
+                diffusers_key += ".norm1.linear"
+            elif "norm1_context_linear" in remaining:
+                diffusers_key += ".norm1_context.linear"
+            else:
+                print(f"Warning: Unhandled double block key pattern: {original_key}")
+                continue
+        
+        elif original_key.startswith("lora_te1_") or original_key.startswith("lora_te_"):
+            # Text encoder keys - handle separately
+            print(f"Found text encoder key: {original_key}")
+            continue
+        
+        else:
+            print(f"Warning: Unknown key pattern: {original_key}")
+            continue
+        
+        # Perform the conversion
+        _convert(original_key, diffusers_key, state_dict, new_state_dict)
+    
+    # Add "transformer." prefix to all keys
+    transformer_state_dict = {
+        f"transformer.{k}": v for k, v in new_state_dict.items() if not k.startswith("text_model.")
+    }
+    
+    # Check for remaining unconverted keys
+    if len(state_dict) > 0:
+        remaining_keys = [k for k in state_dict.keys() if not k.startswith("lora_te")]
+        if remaining_keys:
+            print(f"Warning: Some keys were not converted: {remaining_keys[:10]}")
+    
+    return transformer_state_dict
+
+
+def convert_lora(input_path: str, output_path: str) -> None:
+    """
+    Main conversion function.
+    
+    Args:
+        input_path: Path to input LoRA safetensors file
+        output_path: Path to output diffusers-compatible safetensors file
+    """
+    print(f"Loading LoRA from: {input_path}")
+    state_dict = safetensors.torch.load_file(input_path)
+    
+    print(f"Detecting LoRA format...")
+    format_type = detect_lora_format(state_dict)
+    print(f"Detected format: {format_type}")
+    
+    if format_type == "peft":
+        print("LoRA is already in diffusers-compatible PEFT format!")
+        print("No conversion needed. Copying file...")
+        import shutil
+        shutil.copy(input_path, output_path)
+        return
+    
+    elif format_type == "mixed":
+        print("Converting MIXED format LoRA to pure PEFT format...")
+        print("(Some layers use lora_A/B, others use .lora.down/.lora.up)")
+        converted_state_dict = convert_mixed_lora_to_diffusers(state_dict.copy())
+    
+    elif format_type == "simpletuner_transformer":
+        print("Converting SimpleTuner transformer format to diffusers...")
+        print("(has transformer. prefix but uses lora_down/lora_up naming)")
+        converted_state_dict = convert_simpletuner_transformer_to_diffusers(state_dict.copy())
+    
+    elif format_type == "simpletuner_auraflow":
+        print("Converting SimpleTuner AuraFlow format to diffusers...")
+        converted_state_dict = convert_simpletuner_auraflow_to_diffusers(state_dict.copy())
+    
+    elif format_type == "kohya":
+        print("Note: Detected Kohya format. This converter is optimized for AuraFlow.")
+        print("For other models, diffusers has built-in conversion.")
+        converted_state_dict = convert_simpletuner_auraflow_to_diffusers(state_dict.copy())
+    
+    else:
+        print("Error: Unknown LoRA format!")
+        print("Sample keys from the state dict:")
+        for i, key in enumerate(list(state_dict.keys())[:20]):
+            print(f"  {key}")
+        sys.exit(1)
+    
+    print(f"Saving converted LoRA to: {output_path}")
+    safetensors.torch.save_file(converted_state_dict, output_path)
+    
+    print("\nConversion complete!")
+    print(f"Original keys: {len(state_dict)}")
+    print(f"Converted keys: {len(converted_state_dict)}")
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Convert SimpleTuner LoRA to diffusers-compatible format",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Convert a SimpleTuner LoRA for AuraFlow
+  python convert_simpletuner_lora.py my_lora.safetensors diffusers_lora.safetensors
+  
+  # Check format without converting
+  python convert_simpletuner_lora.py my_lora.safetensors /tmp/test.safetensors
+        """
+    )
+    
+    parser.add_argument(
+        "input",
+        type=str,
+        help="Input LoRA file (SimpleTuner format)"
+    )
+    
+    parser.add_argument(
+        "output",
+        type=str,
+        help="Output LoRA file (diffusers-compatible format)"
+    )
+    
+    parser.add_argument(
+        "--dry-run",
+        action="store_true",
+        help="Only detect format, don't convert"
+    )
+    
+    args = parser.parse_args()
+    
+    # Validate input file exists
+    if not Path(args.input).exists():
+        print(f"Error: Input file not found: {args.input}")
+        sys.exit(1)
+    
+    if args.dry_run:
+        print(f"Loading LoRA from: {args.input}")
+        state_dict = safetensors.torch.load_file(args.input)
+        format_type = detect_lora_format(state_dict)
+        print(f"Detected format: {format_type}")
+        print(f"\nSample keys ({min(10, len(state_dict))} of {len(state_dict)}):")
+        for key in list(state_dict.keys())[:10]:
+            print(f"  {key}")
+        return
+    
+    convert_lora(args.input, args.output)
+
+
+if __name__ == "__main__":
+    main()
+

model_index.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "AuraFlowPipeline",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "purplesmartai/pony-v7-base",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "UMT5EncoderModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "LlamaTokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "AuraFlowTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

safetensor/pony-v7-base.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9354578234390fc0cf2302b99da1d5dfec324834b536dff8ad328fc0982235
+size 13717249520

scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.30.0.dev0",
+  "num_train_timesteps": 1000,
+  "shift": 1.73
+}

text_encoder/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/raid/.cache/huggingface/models--fal--AuraFlow/snapshots/edf69bec4c8c57f5278a655aaca3ceb60d82c0b4/text_encoder",
+  "architectures": [
+    "UMT5EncoderModel"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "umt5",
+  "num_decoder_layers": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "scalable_attention": true,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:decf9b70814ed5e9965bfca9fbd0483462e2bf743790663025b7742f8c014c72
+size 2950448704

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a07449cf1141c0ec86e653c00465f6f0d79c6e58a2c60c8bcf4203d0e4ec4f6
+size 4894234112

tokenizer/added_tokens.json

@@ -0,0 +1,102 @@
+{
+  "<extra_id_0>": 32099,
+  "<extra_id_10>": 32089,
+  "<extra_id_11>": 32088,
+  "<extra_id_12>": 32087,
+  "<extra_id_13>": 32086,
+  "<extra_id_14>": 32085,
+  "<extra_id_15>": 32084,
+  "<extra_id_16>": 32083,
+  "<extra_id_17>": 32082,
+  "<extra_id_18>": 32081,
+  "<extra_id_19>": 32080,
+  "<extra_id_1>": 32098,
+  "<extra_id_20>": 32079,
+  "<extra_id_21>": 32078,
+  "<extra_id_22>": 32077,
+  "<extra_id_23>": 32076,
+  "<extra_id_24>": 32075,
+  "<extra_id_25>": 32074,
+  "<extra_id_26>": 32073,
+  "<extra_id_27>": 32072,
+  "<extra_id_28>": 32071,
+  "<extra_id_29>": 32070,
+  "<extra_id_2>": 32097,
+  "<extra_id_30>": 32069,
+  "<extra_id_31>": 32068,
+  "<extra_id_32>": 32067,
+  "<extra_id_33>": 32066,
+  "<extra_id_34>": 32065,
+  "<extra_id_35>": 32064,
+  "<extra_id_36>": 32063,
+  "<extra_id_37>": 32062,
+  "<extra_id_38>": 32061,
+  "<extra_id_39>": 32060,
+  "<extra_id_3>": 32096,
+  "<extra_id_40>": 32059,
+  "<extra_id_41>": 32058,
+  "<extra_id_42>": 32057,
+  "<extra_id_43>": 32056,
+  "<extra_id_44>": 32055,
+  "<extra_id_45>": 32054,
+  "<extra_id_46>": 32053,
+  "<extra_id_47>": 32052,
+  "<extra_id_48>": 32051,
+  "<extra_id_49>": 32050,
+  "<extra_id_4>": 32095,
+  "<extra_id_50>": 32049,
+  "<extra_id_51>": 32048,
+  "<extra_id_52>": 32047,
+  "<extra_id_53>": 32046,
+  "<extra_id_54>": 32045,
+  "<extra_id_55>": 32044,
+  "<extra_id_56>": 32043,
+  "<extra_id_57>": 32042,
+  "<extra_id_58>": 32041,
+  "<extra_id_59>": 32040,
+  "<extra_id_5>": 32094,
+  "<extra_id_60>": 32039,
+  "<extra_id_61>": 32038,
+  "<extra_id_62>": 32037,
+  "<extra_id_63>": 32036,
+  "<extra_id_64>": 32035,
+  "<extra_id_65>": 32034,
+  "<extra_id_66>": 32033,
+  "<extra_id_67>": 32032,
+  "<extra_id_68>": 32031,
+  "<extra_id_69>": 32030,
+  "<extra_id_6>": 32093,
+  "<extra_id_70>": 32029,
+  "<extra_id_71>": 32028,
+  "<extra_id_72>": 32027,
+  "<extra_id_73>": 32026,
+  "<extra_id_74>": 32025,
+  "<extra_id_75>": 32024,
+  "<extra_id_76>": 32023,
+  "<extra_id_77>": 32022,
+  "<extra_id_78>": 32021,
+  "<extra_id_79>": 32020,
+  "<extra_id_7>": 32092,
+  "<extra_id_80>": 32019,
+  "<extra_id_81>": 32018,
+  "<extra_id_82>": 32017,
+  "<extra_id_83>": 32016,
+  "<extra_id_84>": 32015,
+  "<extra_id_85>": 32014,
+  "<extra_id_86>": 32013,
+  "<extra_id_87>": 32012,
+  "<extra_id_88>": 32011,
+  "<extra_id_89>": 32010,
+  "<extra_id_8>": 32091,
+  "<extra_id_90>": 32009,
+  "<extra_id_91>": 32008,
+  "<extra_id_92>": 32007,
+  "<extra_id_93>": 32006,
+  "<extra_id_94>": 32005,
+  "<extra_id_95>": 32004,
+  "<extra_id_96>": 32003,
+  "<extra_id_97>": 32002,
+  "<extra_id_98>": 32001,
+  "<extra_id_99>": 32000,
+  "<extra_id_9>": 32090
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,132 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_99>",
+    "<extra_id_98>",
+    "<extra_id_97>",
+    "<extra_id_96>",
+    "<extra_id_95>",
+    "<extra_id_94>",
+    "<extra_id_93>",
+    "<extra_id_92>",
+    "<extra_id_91>",
+    "<extra_id_90>",
+    "<extra_id_89>",
+    "<extra_id_88>",
+    "<extra_id_87>",
+    "<extra_id_86>",
+    "<extra_id_85>",
+    "<extra_id_84>",
+    "<extra_id_83>",
+    "<extra_id_82>",
+    "<extra_id_81>",
+    "<extra_id_80>",
+    "<extra_id_79>",
+    "<extra_id_78>",
+    "<extra_id_77>",
+    "<extra_id_76>",
+    "<extra_id_75>",
+    "<extra_id_74>",
+    "<extra_id_73>",
+    "<extra_id_72>",
+    "<extra_id_71>",
+    "<extra_id_70>",
+    "<extra_id_69>",
+    "<extra_id_68>",
+    "<extra_id_67>",
+    "<extra_id_66>",
+    "<extra_id_65>",
+    "<extra_id_64>",
+    "<extra_id_63>",
+    "<extra_id_62>",
+    "<extra_id_61>",
+    "<extra_id_60>",
+    "<extra_id_59>",
+    "<extra_id_58>",
+    "<extra_id_57>",
+    "<extra_id_56>",
+    "<extra_id_55>",
+    "<extra_id_54>",
+    "<extra_id_53>",
+    "<extra_id_52>",
+    "<extra_id_51>",
+    "<extra_id_50>",
+    "<extra_id_49>",
+    "<extra_id_48>",
+    "<extra_id_47>",
+    "<extra_id_46>",
+    "<extra_id_45>",
+    "<extra_id_44>",
+    "<extra_id_43>",
+    "<extra_id_42>",
+    "<extra_id_41>",
+    "<extra_id_40>",
+    "<extra_id_39>",
+    "<extra_id_38>",
+    "<extra_id_37>",
+    "<extra_id_36>",
+    "<extra_id_35>",
+    "<extra_id_34>",
+    "<extra_id_33>",
+    "<extra_id_32>",
+    "<extra_id_31>",
+    "<extra_id_30>",
+    "<extra_id_29>",
+    "<extra_id_28>",
+    "<extra_id_27>",
+    "<extra_id_26>",
+    "<extra_id_25>",
+    "<extra_id_24>",
+    "<extra_id_23>",
+    "<extra_id_22>",
+    "<extra_id_21>",
+    "<extra_id_20>",
+    "<extra_id_19>",
+    "<extra_id_18>",
+    "<extra_id_17>",
+    "<extra_id_16>",
+    "<extra_id_15>",
+    "<extra_id_14>",
+    "<extra_id_13>",
+    "<extra_id_12>",
+    "<extra_id_11>",
+    "<extra_id_10>",
+    "<extra_id_9>",
+    "<extra_id_8>",
+    "<extra_id_7>",
+    "<extra_id_6>",
+    "<extra_id_5>",
+    "<extra_id_4>",
+    "<extra_id_3>",
+    "<extra_id_2>",
+    "<extra_id_1>",
+    "<extra_id_0>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer/tokenizer_config.json

@@ -0,0 +1,945 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_99>",
+    "<extra_id_98>",
+    "<extra_id_97>",
+    "<extra_id_96>",
+    "<extra_id_95>",
+    "<extra_id_94>",
+    "<extra_id_93>",
+    "<extra_id_92>",
+    "<extra_id_91>",
+    "<extra_id_90>",
+    "<extra_id_89>",
+    "<extra_id_88>",
+    "<extra_id_87>",
+    "<extra_id_86>",
+    "<extra_id_85>",
+    "<extra_id_84>",
+    "<extra_id_83>",
+    "<extra_id_82>",
+    "<extra_id_81>",
+    "<extra_id_80>",
+    "<extra_id_79>",
+    "<extra_id_78>",
+    "<extra_id_77>",
+    "<extra_id_76>",
+    "<extra_id_75>",
+    "<extra_id_74>",
+    "<extra_id_73>",
+    "<extra_id_72>",
+    "<extra_id_71>",
+    "<extra_id_70>",
+    "<extra_id_69>",
+    "<extra_id_68>",
+    "<extra_id_67>",
+    "<extra_id_66>",
+    "<extra_id_65>",
+    "<extra_id_64>",
+    "<extra_id_63>",
+    "<extra_id_62>",
+    "<extra_id_61>",
+    "<extra_id_60>",
+    "<extra_id_59>",
+    "<extra_id_58>",
+    "<extra_id_57>",
+    "<extra_id_56>",
+    "<extra_id_55>",
+    "<extra_id_54>",
+    "<extra_id_53>",
+    "<extra_id_52>",
+    "<extra_id_51>",
+    "<extra_id_50>",
+    "<extra_id_49>",
+    "<extra_id_48>",
+    "<extra_id_47>",
+    "<extra_id_46>",
+    "<extra_id_45>",
+    "<extra_id_44>",
+    "<extra_id_43>",
+    "<extra_id_42>",
+    "<extra_id_41>",
+    "<extra_id_40>",
+    "<extra_id_39>",
+    "<extra_id_38>",
+    "<extra_id_37>",
+    "<extra_id_36>",
+    "<extra_id_35>",
+    "<extra_id_34>",
+    "<extra_id_33>",
+    "<extra_id_32>",
+    "<extra_id_31>",
+    "<extra_id_30>",
+    "<extra_id_29>",
+    "<extra_id_28>",
+    "<extra_id_27>",
+    "<extra_id_26>",
+    "<extra_id_25>",
+    "<extra_id_24>",
+    "<extra_id_23>",
+    "<extra_id_22>",
+    "<extra_id_21>",
+    "<extra_id_20>",
+    "<extra_id_19>",
+    "<extra_id_18>",
+    "<extra_id_17>",
+    "<extra_id_16>",
+    "<extra_id_15>",
+    "<extra_id_14>",
+    "<extra_id_13>",
+    "<extra_id_12>",
+    "<extra_id_11>",
+    "<extra_id_10>",
+    "<extra_id_9>",
+    "<extra_id_8>",
+    "<extra_id_7>",
+    "<extra_id_6>",
+    "<extra_id_5>",
+    "<extra_id_4>",
+    "<extra_id_3>",
+    "<extra_id_2>",
+    "<extra_id_1>",
+    "<extra_id_0>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 768,
+  "pad_token": "<s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

transformer/config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "AuraFlowTransformer2DModel",
+  "_diffusers_version": "0.34.0.dev0",
+  "attention_head_dim": 256,
+  "caption_projection_dim": 3072,
+  "in_channels": 4,
+  "joint_attention_dim": 2048,
+  "num_attention_heads": 12,
+  "num_mmdit_layers": 4,
+  "num_single_dit_layers": 32,
+  "out_channels": 4,
+  "patch_size": 2,
+  "pos_embed_max_size": 9216,
+  "sample_size": 64
+}

transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9193bcfa8e27546ca1daa0f6318dc06fc943c61740a397f8dd40bd88382c7a82
+size 9994324992

transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b44e4e6a4d2e7dede29a27bd17bd2e65447111f26f47a4b488b9a731614b212
+size 9890183496

transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b14abad4e7e98999646b595ef93a5e35911785c2d84a921885d744da716a83
+size 7549955048

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,338 @@
+{
+  "metadata": {
+    "total_size": 27434422272
+  },
+  "weight_map": {
+    "context_embedder.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.ff_context.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.ff_context.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.ff_context.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.0.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.ff_context.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.ff_context.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.ff_context.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.1.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.ff_context.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.ff_context.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.ff_context.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.2.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.ff_context.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.ff_context.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.ff_context.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "joint_transformer_blocks.3.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "pos_embed.pos_embed": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "pos_embed.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "pos_embed.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "register_tokens": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.0.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.0.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.0.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.0.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.1.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.1.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.1.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.1.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.10.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.10.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.10.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.10.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.10.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.10.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.10.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.10.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.11.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.11.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.11.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.11.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.11.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.11.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.11.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.11.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.12.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.12.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.12.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.12.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.12.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.12.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.12.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.12.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.13.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.13.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.13.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.13.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.13.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.13.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.13.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.13.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.14.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.14.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.14.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.14.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.14.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.14.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.14.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.14.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.15.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.15.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.15.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.15.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.15.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.15.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.15.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.15.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.16.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.16.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.16.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.16.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.16.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.16.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.16.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.16.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.17.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.17.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.17.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.17.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.17.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.17.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.17.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.17.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.18.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.18.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.18.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.18.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.18.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.18.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.18.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.18.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.19.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.19.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.19.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.19.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.19.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.19.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.19.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.19.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.2.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.2.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.2.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.2.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.20.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.20.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.20.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.20.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.20.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.20.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.20.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.20.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.21.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.21.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.21.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.21.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.21.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.21.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.21.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.21.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.22.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.22.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.22.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.22.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.22.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.22.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.22.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.22.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.23.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.23.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.23.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.23.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.23.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.23.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.23.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.23.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.24.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.24.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.24.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.24.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.24.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.24.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.24.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.24.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.25.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.25.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.25.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.25.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.25.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.25.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.25.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.25.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.26.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.26.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.26.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.26.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.26.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.26.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.26.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.26.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.27.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.27.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.27.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.27.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.27.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.27.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.27.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.27.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.28.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.28.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.28.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.28.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.28.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.28.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.28.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.28.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.29.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.29.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.29.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.29.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.29.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.29.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.29.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.29.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.3.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.3.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.3.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.3.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.30.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.30.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.30.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.30.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.30.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.30.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.30.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.30.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.31.attn.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.31.attn.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.31.attn.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.31.attn.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.31.ff.linear_1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.31.ff.linear_2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.31.ff.out_projection.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.31.norm1.linear.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "single_transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.4.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.4.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.4.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.4.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.5.ff.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.5.ff.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.5.ff.out_projection.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.5.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.6.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.6.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.6.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.6.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "single_transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.7.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.7.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.7.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.7.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.8.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.8.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.8.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.8.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.8.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.8.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.8.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.8.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.9.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.9.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.9.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.9.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.9.ff.linear_1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.9.ff.linear_2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.9.ff.out_projection.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "single_transformer_blocks.9.norm1.linear.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "time_step_proj.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_step_proj.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_step_proj.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_step_proj.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors"
+  }
+}

vae/config.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.30.0.dev0",
+  "_name_or_path": "/raid/.cache/huggingface/models--fal--AuraFlow/snapshots/edf69bec4c8c57f5278a655aaca3ceb60d82c0b4/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68
+size 167335342

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341
+size 334643268

workflows/README.md

@@ -0,0 +1,28 @@
+# Pony V7 ComfyUI Workflows
+
+## How to Use
+
+Simply drag and drop any of the workflow images below directly into your ComfyUI canvas to load them. ComfyUI will automatically parse the embedded workflow data from the image.
+
+## Available Workflows
+
+### [Basic Workflow](pony-v7-simple.png)
+![Basic Workflow](pony-v7-simple.png)
+
+A simple, straightforward workflow for generating images with Pony V7 using the SafeTensor. Perfect for getting started quickly.
+
+### [GGUF Workflow](pony-v7-simple-gguf.png)
+![GGUF Workflow](pony-v7-simple-gguf.png)
+
+Workflow optimized for using GGUF quantized models. Requires the [GGUF nodes by City96](https://github.com/city96/ComfyUI-GGUF). GGUF formats allow lower VRAM use with minimal degradation to quality and no noticeable impact to performance. Q8_0 version is recommended. See the [GGUF README](../gguf/) for more details.
+
+### [LoRA Workflow](pony-v7-lora.png)
+![LoRA Workflow](pony-v7-lora.png)
+
+Workflow demonstrating how to use LoRA models with Pony V7. Shows proper setup for loading and applying LoRA weights to enhance or modify generation results. See the [LoRA README](../lora/) for training and conversion information.
+
+### [Noise Selection Workflow](pony-v7-noise-selection.png)
+![Noise Selection Workflow](pony-v7-noise-selection.png)
+
+Advanced workflow featuring the custom PonyNoise node that allows switching between GPU and CPU noise generation. Use this to match `diffusers` output or ensure cross-platform consistency. Requires the [PonyNoise node](../comfy_nodes/).
+