base_model: black-forest-labs/FLUX.1-dev
library_name: diffusers
license: other
instance_prompt: a woman, alphonse mucha style
widget:
- text: >-
Serene raven-haired woman, moonlit lilies, swirling botanicals, alphonse
mucha style
output:
url: images/alphonse_mucha_merged1_fp8.png
- text: a puppy in a pond, alphonse mucha style
output:
url: images/alphonse_mucha_merged2_fp8.png
- text: >-
Ornate fox with a collar of autumn leaves and berries, amidst a tapestry
of forest foliage, alphonse mucha style
output:
url: images/alphonse_mucha_merged3_fp8.png
tags:
- text-to-image
- diffusers-training
- diffusers
- lora
- flux
- flux-diffusers
- template:sd-lora
datasets:
- derekl35/alphonse-mucha-style
Flux DreamBooth LoRA - derekl35/alphonse-mucha-fp8-lora-flux
- Prompt
- Serene raven-haired woman, moonlit lilies, swirling botanicals, alphonse mucha style
- Prompt
- a puppy in a pond, alphonse mucha style
- Prompt
- Ornate fox with a collar of autumn leaves and berries, amidst a tapestry of forest foliage, alphonse mucha style
Model description
These are derekl35/alphonse-mucha-fp8-lora-flux DreamBooth LoRA weights for black-forest-labs/FLUX.1-dev. This work is part of the blog post, "Fine-Tuning FLUX.1-dev on consumer hardware and in FP8".
The weights were trained using DreamBooth with the Flux diffusers trainer.
Was LoRA for the text encoder enabled? False.
FP8 training? True
Trigger words
You should use , alphonse mucha style to trigger the image generation.
Download model
Download the *.safetensors LoRA in the Files & versions tab.
Use it with the 🧨 diffusers library
There are two main ways to use this LoRA for inference: loading the adapter on the fly or merging it with the base model.
Option 1: Loading LoRA Adapters
This approach offers flexibility, allowing you to easily switch between different LoRA styles.
from diffusers import FluxPipeline
import torch
ckpt_id = "black-forest-labs/FLUX.1-dev"
pipeline = FluxPipeline.from_pretrained(
ckpt_id, torch_dtype=torch.float16
)
pipeline.load_lora_weights("derekl35/alphonse-mucha-fp8-lora-flux", weight_name="pytorch_lora_weights.safetensors")
pipeline.enable_model_cpu_offload()
image = pipeline(
"a puppy in a pond, alphonse mucha style",
num_inference_steps=28,
guidance_scale=3.5,
height=768,
width=512,
generator=torch.manual_seed(0)
).images[0]
image.save("alphonse_mucha_loaded.png")
Option 2: Merging LoRA into Base Model
Merging the LoRA into the base model can lead to slightly faster inference and is useful when you want to use a single style consistently.
from diffusers import FluxPipeline, AutoPipelineForText2Image, FluxTransformer2DModel
import torch
ckpt_id = "black-forest-labs/FLUX.1-dev"
pipeline = FluxPipeline.from_pretrained(
ckpt_id, text_encoder=None, text_encoder_2=None, torch_dtype=torch.float16
)
pipeline.load_lora_weights("derekl35/alphonse-mucha-fp8-lora-flux", weight_name="pytorch_lora_weights.safetensors")
pipeline.fuse_lora()
pipeline.unload_lora_weights()
# You can save the fused transformer for later use
# pipeline.transformer.save_pretrained("fused_transformer")
pipeline.enable_model_cpu_offload()
image = pipeline(
"a puppy in a pond, alphonse mucha style",
num_inference_steps=28,
guidance_scale=3.5,
height=768,
width=512,
generator=torch.manual_seed(0)
).images[0]
image.save("alphonse_mucha_merged.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
License
Please adhere to the licensing terms as described here.