Instructions to use iitolstykh/VIBE-Image-Edit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use iitolstykh/VIBE-Image-Edit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("iitolstykh/VIBE-Image-Edit", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Sana
How to use iitolstykh/VIBE-Image-Edit with Sana:
# Load the model and infer image from text import torch from app.sana_pipeline import SanaPipeline from torchvision.utils import save_image sana = SanaPipeline("configs/sana_config/1024ms/Sana_1600M_img1024.yaml") sana.from_pretrained("hf://iitolstykh/VIBE-Image-Edit") image = sana( prompt='a cyberpunk cat with a neon sign that says "Sana"', height=1024, width=1024, guidance_scale=5.0, pag_guidance_scale=2.0, num_inference_steps=18, ) - Notebooks
- Google Colab
- Kaggle
Windows GUI / Local Installer with RTX 5090 support
Hey everyone! π
I created a local Gradio Web-UI wrapper for this model to make it run easily on Windows. It includes a fix for the RTX 5090 (Blackwell) issues and adds controls for Seed, Steps, and Guidance Scales.
If you struggle with the installation or want a UI like the demo, check it out here: https://github.com/Detoxfox4234/VIBE-Local-GUI-Windows
Hope this helps! π
Thanks for the π₯! Your model is amazing. I wanted to make it more accessible for Windows users and the new RTX 50-series. Happy to contribute to the community!
We are grateful for your contribution and for your interest in our work! Thank you for making the model more accessible to the community.