Instructions to use Remade-AI/Deflate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Remade-AI/Deflate 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/Wan2.1-I2V-14B-480P-Diffusers", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Remade-AI/Deflate") prompt = "The video opens with a man. As the video progresses, the man begins to d3d1at3 deflate it, gradually shrinking and losing shape, eventually flattening completely into a lifeless, deflated mass on the ground. " input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png") output = pipe(image=input_image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Download example_videos/man_deflate.mp4 from Remade-AI/Deflate: direct link, hf CLI and curl.
- Browser
- Download file 321 kB
-
https://huggingface.co/Remade-AI/Deflate/resolve/main/example_videos/man_deflate.mp4
- Command line
-
hf download hf://Remade-AI/Deflate/example_videos/man_deflate.mp4
-
curl -L -o man_deflate.mp4 https://huggingface.co/Remade-AI/Deflate/resolve/main/example_videos/man_deflate.mp4
321 kB
- Xet hash:
- 0b0a044c9d9b5e9e8cd08f3f00e38136c1801a9d635b773f52ddef1de03f5a68
- Size of remote file:
- 321 kB
- SHA256:
- 16642cf2d919a77e1e19f840c8d4b461e7f49bdc254d415a492664cd3cc944dd
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.