| { | |
| "_class_name": "QwenImageTransformer2DModel", | |
| "_diffusers_version": "0.35.0.dev0", | |
| "_name_or_path": "/mnt/co-research/home/zeyi/.cache/huggingface/hub/models--Qwen--Qwen-Image/snapshots/9e31a1d489546029df1adfc9e12a08edafc692e7/transformer", | |
| "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, | |
| "pooled_projection_dim": 768 | |
| } | |