Any-to-Any
Transformers
Diffusers
Safetensors
text-to-image
image-editing
image-understanding
vision-language
multimodal
unified-model
teacher-model
diffusion
Instructions to use Skywork/Unipic3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Skywork/Unipic3 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Skywork/Unipic3", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_class_name": "QwenImageTransformer2DModel", | |
| "_diffusers_version": "0.35.1", | |
| "_name_or_path": "Qwen-Image-Edit", | |
| "attention_head_dim": 128, | |
| "axes_dims_rope": [ | |
| 16, | |
| 56, | |
| 56 | |
| ], | |
| "guidance_embeds": false, | |
| "in_channels": 64, | |
| "joint_attention_dim": 3584, | |
| "num_attention_heads": 24, | |
| "num_layers": 60, | |
| "out_channels": 16, | |
| "patch_size": 2 | |
| } |