Image-to-Video
Diffusers
Safetensors
Wan2.2
English
Chinese
WanPipeline
video-generation
visual-reasoning
reinforcement-learning
rlvr
vbvr-pro
Instructions to use Video-Reason/VBVR-Pro-Wan2.2-TI2V-5B-RLVR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Video-Reason/VBVR-Pro-Wan2.2-TI2V-5B-RLVR 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("Video-Reason/VBVR-Pro-Wan2.2-TI2V-5B-RLVR", 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") - Wan2.2
How to use Video-Reason/VBVR-Pro-Wan2.2-TI2V-5B-RLVR with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update model ID after organization transfer
Browse files
README.md
CHANGED
|
@@ -72,7 +72,7 @@ import torch
|
|
| 72 |
from diffusers import AutoencoderKLWan, DiffusionPipeline
|
| 73 |
from diffusers.utils import export_to_video, load_image
|
| 74 |
|
| 75 |
-
model_id = "
|
| 76 |
|
| 77 |
# Wan's VAE is kept in float32 for stable decoding.
|
| 78 |
vae = AutoencoderKLWan.from_pretrained(
|
|
@@ -123,7 +123,7 @@ remote custom code:
|
|
| 123 |
import torch
|
| 124 |
from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
|
| 125 |
|
| 126 |
-
model_id = "
|
| 127 |
|
| 128 |
vae = AutoencoderKLWan.from_pretrained(
|
| 129 |
model_id,
|
|
|
|
| 72 |
from diffusers import AutoencoderKLWan, DiffusionPipeline
|
| 73 |
from diffusers.utils import export_to_video, load_image
|
| 74 |
|
| 75 |
+
model_id = "Video-Reason/VBVR-Pro-Wan2.2-TI2V-5B-RLVR"
|
| 76 |
|
| 77 |
# Wan's VAE is kept in float32 for stable decoding.
|
| 78 |
vae = AutoencoderKLWan.from_pretrained(
|
|
|
|
| 123 |
import torch
|
| 124 |
from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
|
| 125 |
|
| 126 |
+
model_id = "Video-Reason/VBVR-Pro-Wan2.2-TI2V-5B-RLVR"
|
| 127 |
|
| 128 |
vae = AutoencoderKLWan.from_pretrained(
|
| 129 |
model_id,
|