Instructions to use inference-sh/Wan2.2-TI2V-5B-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use inference-sh/Wan2.2-TI2V-5B-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("inference-sh/Wan2.2-TI2V-5B-Diffusers", 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 folder using huggingface_hub
Browse files- transformer/config.json +1 -2
transformer/config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "WanTransformer3DModel",
|
| 3 |
"_diffusers_version": "0.35.0.dev0",
|
| 4 |
-
"added_kv_proj_dim":
|
| 5 |
"attention_head_dim": 128,
|
| 6 |
"cross_attn_norm": true,
|
| 7 |
"eps": 1e-06,
|
|
@@ -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": "0.35.0.dev0",
|
| 4 |
+
"added_kv_proj_dim": 5120,
|
| 5 |
"attention_head_dim": 128,
|
| 6 |
"cross_attn_norm": true,
|
| 7 |
"eps": 1e-06,
|
|
|
|
| 17 |
2,
|
| 18 |
2
|
| 19 |
],
|
|
|
|
| 20 |
"qk_norm": "rms_norm_across_heads",
|
| 21 |
"rope_max_seq_len": 1024,
|
| 22 |
"text_dim": 4096
|