Search results
Stable Diffusion v2 refers to a specific configuration of the model architecture that uses a downsampling-factor 8 autoencoder with an 865M UNet and OpenCLIP ViT-H/14 text encoder for the diffusion model.
- Issues 184
High-Resolution Image Synthesis with Latent Diffusion Models...
- Projects
Projects - Stable Diffusion Version 2 - GitHub
- Security
GitHub is where people build software. More than 100 million...
- Insights
Insights - Stable Diffusion Version 2 - GitHub
- 3.9k Forks
3.9k Forks - Stable Diffusion Version 2 - GitHub
- 30k Stars
30k Stars - Stable Diffusion Version 2 - GitHub
- Permalink
Permalink - Stable Diffusion Version 2 - GitHub
- Issues 184
Star 141k. master. README. AGPL-3.0 license. Stable Diffusion web UI. A web interface for Stable Diffusion, implemented using Gradio library. Features. Detailed feature showcase with images: Original txt2img and img2img modes. One click install and run script (but you still must install python and git) Outpainting. Inpainting. Color Sketch.
Stable Diffusion is a research project by CompVis that uses a frozen CLIP ViT-L/14 text encoder to generate images from text prompts. The project provides the model weights, requirements, usage instructions and a model card on GitHub.
Stable Diffusion is a latent text-to-image diffusion model that generates photo-realistic images from any text input. It has four versions with different training steps and resolutions, and can be accessed through Hugging Face's Diffusers library or the original Stable Diffusion GitHub repository.
Stable Diffusion v2 is a diffusion-based model that can generate and modify images based on text prompts. It is trained on a large-scale dataset of images and captions, and has limitations and biases that should be considered.
This repository contains Stable Diffusion models for text-to-image synthesis, trained from scratch and updated with new checkpoints. Learn how to install, use and customize the models, and explore the latest features such as Stable UnCLIP, depth-guided and inpainting models.
12 cze 2024 · A text-to-image diffusion model with improved performance and efficiency. Learn how to use it with Diffusers, ComfyUI, or Stable API Platform.