Instructions to use wiikoo/ComfyUI-Models-Backup-20250821 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wiikoo/ComfyUI-Models-Backup-20250821 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wiikoo/ComfyUI-Models-Backup-20250821", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Upload custom_nodes/ComfyUI-WanVideoWrapper/configs/transformer_config_i2v.json with huggingface_hub
Browse files
custom_nodes/ComfyUI-WanVideoWrapper/configs/transformer_config_i2v.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "WanModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"dim": 5120,
|
| 5 |
+
"eps": 1e-06,
|
| 6 |
+
"ffn_dim": 13824,
|
| 7 |
+
"freq_dim": 256,
|
| 8 |
+
"in_dim": 36,
|
| 9 |
+
"model_type": "i2v",
|
| 10 |
+
"num_heads": 40,
|
| 11 |
+
"num_layers": 40,
|
| 12 |
+
"out_dim": 16,
|
| 13 |
+
"text_len": 512
|
| 14 |
+
}
|