Image-to-Video
Diffusers
Safetensors
English
Chinese
WanVACEPipeline
video generation
video-to-video editing
reference-to-video
wan2.1
Instructions to use AlekseyCalvin/WanVACE_1.3B_nf4_umT5fp8_Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AlekseyCalvin/WanVACE_1.3B_nf4_umT5fp8_Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AlekseyCalvin/WanVACE_1.3B_nf4_umT5fp8_Diffusers", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Create config.json
Browse files- transformer/config.json +22 -0
transformer/config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "WanTransformer3DModel",
|
| 3 |
+
"added_kv_proj_dim": null,
|
| 4 |
+
"attention_head_dim": 128,
|
| 5 |
+
"cross_attn_norm": true,
|
| 6 |
+
"eps": 1e-06,
|
| 7 |
+
"ffn_dim": 8960,
|
| 8 |
+
"freq_dim": 256,
|
| 9 |
+
"image_dim": null,
|
| 10 |
+
"in_channels": 16,
|
| 11 |
+
"num_attention_heads": 12,
|
| 12 |
+
"num_layers": 30,
|
| 13 |
+
"out_channels": 16,
|
| 14 |
+
"patch_size": [
|
| 15 |
+
1,
|
| 16 |
+
2,
|
| 17 |
+
2
|
| 18 |
+
],
|
| 19 |
+
"qk_norm": "rms_norm_across_heads",
|
| 20 |
+
"rope_max_seq_len": 1024,
|
| 21 |
+
"text_dim": 4096
|
| 22 |
+
}
|