Instructions to use FastVideo/FastWan-QAD-FP8-1.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FastVideo/FastWan-QAD-FP8-1.3B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FastVideo/FastWan-QAD-FP8-1.3B", 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
ema/generator_ema.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3be416fc1819b5a5fe0806cf37acabc8276c79885b52d4ca29b56da9c66efaa1
|
| 3 |
+
size 5676070784
|
generator_inference_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 |
+
}
|
generator_inference_transformer/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57614090ee61cfaf3c4647e6c29d3e9b5ae5a89f620fa1ba7edc9bea4ba6b37b
|
| 3 |
+
size 5676070784
|