Image-to-Image
Diffusers
Safetensors
English
Chinese
WanImageToVideoPipeline
image editing
video generation
Instructions to use eyaler/chronoedit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use eyaler/chronoedit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("eyaler/chronoedit", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "_class_name": "WanTransformer3DModel", | |
| "_diffusers_version": "0.33.1", | |
| "added_kv_proj_dim": 5120, | |
| "attention_head_dim": 128, | |
| "cross_attn_norm": true, | |
| "eps": 1e-06, | |
| "ffn_dim": 13824, | |
| "freq_dim": 256, | |
| "image_dim": 1280, | |
| "in_channels": 36, | |
| "num_attention_heads": 40, | |
| "num_layers": 40, | |
| "out_channels": 16, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "qk_norm": "rms_norm_across_heads", | |
| "rope_max_seq_len": 1024, | |
| "text_dim": 4096 | |
| } | |