Instructions to use obsxrver/wan2.2-i2v-scat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use obsxrver/wan2.2-i2v-scat 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", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("obsxrver/wan2.2-i2v-scat") prompt = "A man with short gray hair plays a red electric guitar." input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png") image = pipe(image=input_image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
XX vs XXI version ?
#1
by cyberdog94 - opened
Hello and thanks for producing the I2V version ! I see 2 models are available "xx" & "xxi", can you explain what are the differences, I couldn't find in the readme. Thanks
xxi is the newer one ☝️
Try adding “she spreads her legs and…” or a longer duration sometimes that fixes it