Vibe Coding Discoverstable-diffusion
View on GitHubA latent text-to-image diffusion model
Reference code and checkpoints for Stable Diffusion v1, a latent text-to-image diffusion model conditioned by CLIP. Includes scripts for text-to-image generation, image-to-image editing, and inpainting, with PyTorch and Diffusers support.
Use Cases
Generate images from text promptsEdit images with text-guided image-to-image translationInpaint image regionsUpscale or modify generated imagesRun and evaluate diffusion-model sampling
Built With
- Language
- Jupyter Notebook
- Frameworks
- PyTorch · Hugging Face Diffusers · Hugging Face Transformers · Latent Diffusion Models
Tags
image-generation · text-to-image · image-to-image · latent-diffusion · inpainting · open-source-model · image-synthesis