Instructions to use Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download transformer/config.json from Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers: direct link, hf CLI and curl.
- Browser
- Download file 493 Bytes
-
https://huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers/resolve/main/transformer/config.json
- Command line
-
hf download hf://Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers/transformer/config.json
-
curl -L -o config.json https://huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers/resolve/main/transformer/config.json
493 Bytes
| { | |
| "_class_name": "HunyuanDiT2DModel", | |
| "_diffusers_version": "0.29.0.dev0", | |
| "activation_fn": "gelu-approximate", | |
| "attention_head_dim": 88, | |
| "cross_attention_dim": 1024, | |
| "cross_attention_dim_t5": 2048, | |
| "hidden_size": 1408, | |
| "in_channels": 4, | |
| "learn_sigma": true, | |
| "mlp_ratio": 4.3637, | |
| "norm_type": "layer_norm", | |
| "num_attention_heads": 16, | |
| "num_layers": 40, | |
| "patch_size": 2, | |
| "pooled_projection_dim": 1024, | |
| "sample_size": 128, | |
| "text_len": 77, | |
| "text_len_t5": 256 | |
| } | |