Instructions to use Wan-AI/Wan2.2-I2V-A14B-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wan-AI/Wan2.2-I2V-A14B-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("Wan-AI/Wan2.2-I2V-A14B-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") - Inference
- Notebooks
- Google Colab
- Kaggle
Update transformer/config.json
Browse files- transformer/config.json +3 -4
transformer/config.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "WanTransformer3DModel",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
-
"added_kv_proj_dim":
|
| 5 |
"attention_head_dim": 128,
|
| 6 |
"cross_attn_norm": true,
|
| 7 |
"eps": 1e-06,
|
| 8 |
"ffn_dim": 13824,
|
| 9 |
"freq_dim": 256,
|
| 10 |
-
"image_dim":
|
| 11 |
"in_channels": 36,
|
| 12 |
"num_attention_heads": 40,
|
| 13 |
"num_layers": 40,
|
|
@@ -17,7 +17,6 @@
|
|
| 17 |
2,
|
| 18 |
2
|
| 19 |
],
|
| 20 |
-
"pos_embed_seq_len": null,
|
| 21 |
"qk_norm": "rms_norm_across_heads",
|
| 22 |
"rope_max_seq_len": 1024,
|
| 23 |
"text_dim": 4096
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "WanTransformer3DModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"added_kv_proj_dim": 5120,
|
| 5 |
"attention_head_dim": 128,
|
| 6 |
"cross_attn_norm": true,
|
| 7 |
"eps": 1e-06,
|
| 8 |
"ffn_dim": 13824,
|
| 9 |
"freq_dim": 256,
|
| 10 |
+
"image_dim": 1280,
|
| 11 |
"in_channels": 36,
|
| 12 |
"num_attention_heads": 40,
|
| 13 |
"num_layers": 40,
|
|
|
|
| 17 |
2,
|
| 18 |
2
|
| 19 |
],
|
|
|
|
| 20 |
"qk_norm": "rms_norm_across_heads",
|
| 21 |
"rope_max_seq_len": 1024,
|
| 22 |
"text_dim": 4096
|