Image-to-Video
Diffusers
Safetensors
video-generation
video diffusion transformer
joint-video-audio-generation
sparse-attention
high-resolution
Instructions to use FrancisRing/Prism with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FrancisRing/Prism 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("FrancisRing/Prism", 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") - Notebooks
- Google Colab
- Kaggle
hi boss, insane release, impatiened to see results on it, could you make a comfy integration?
#1
by Perfs - opened
also the github code link isn't working
as someone who identifies with impatience - i suggest an opencode subscription for $10/mth with deepseek - and it's do it yourself.
3 steps
- download - install and open opencode.ai
- ask it to "build comfyui plugin for https://huggingface.co/FrancisRing/Prism"
- are you still reading this??
UPDATE -
apparently the official repo hasnt been made public yet.
not for consumer use -though community
"For inference, 720p can run on a single NVIDIA 80 GB GPU, while 1080p and 2K each require 4 or more NVIDIA 80 GB GPUs."
here's an unoffiical grok created plugin
https://github.com/johndpope/ComfyUI-Prism
also the github code link isn't working
Hi! The code will be released in the next day or two. Please stay tuned!
FrancisRing changed discussion status to closed