Image-to-Video
Diffusers
Safetensors
lora
video-generation
pixel-art
sprite-animation
game-development
wan
comfyui
Instructions to use styly-agents/Wan2-2-pixel-animate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use styly-agents/Wan2-2-pixel-animate 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-14B-480P", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("styly-agents/Wan2-2-pixel-animate") 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") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
Documentation missing mysterious loras
#1
by positiveelevation - opened
Hi, I'm glad I found this model, but I can't figure out how to use it.
The example workflow given tries to load the following LoRAs:
- wan2.2_4_step_1030_lora.safetensors
- wan2.2_low_noise_4_step.safetensors
Can you explain where to get them? Those filenames don't have any matches on Google.
Are you renaming loras you download to shorter names or something? That really makes it hard for beginners to use your workflows!