Instructions to use stabilityai/stable-video-diffusion-img2vid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-video-diffusion-img2vid 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("stabilityai/stable-video-diffusion-img2vid", 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
run steps
#1
by ameerazam08 - opened
No description provided.
run steps
ameerazam08 changed pull request status to closed
ameerazam08 changed pull request status to open
Now it is running on 24GB. 3090 Ti

Working on 24GB VRam !
Yes but you able to generate 1 sec 8 frames and out size 512,512
Device 0 [NVIDIA GeForce RTX 3080 Ti Laptop GPU] PCIe GEN 2@ 8x RX: 0.000 KiB/s TX: 0.000 KiB/s
GPU 240MHz MEM 810MHz TEMP 51°C FAN N/A% POW 38 / 125 W
GPU[ 0%] MEM[|||||||||||||||||||||||||15.429Gi/16.000Gi]
H256,W256,T10
Barely successful 😅😅😅
how to run this model please
ameerazam08 changed pull request status to closed