StreamDiffusion
Diffusion pipeline
A pipeline-level solution for real-time interactive image generation using advanced diffusion techniques
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
10k stars
80 watching
709 forks
Language: Python
last commit: 12 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 doubiiu/dynamicrafter | This project generates animated videos from open-domain images by leveraging pre-trained video diffusion priors. | 2,668 |
 hvision-nku/storydiffusion | This project provides an implementation of a self-attention mechanism for long-range image and video generation, enabling the creation of consistent narratives. | 6,030 |
 huggingface/diffusers | A PyTorch-based library for training and using state-of-the-art diffusion models to generate images, audio, and 3D structures | 26,676 |
 jina-ai/dalle-flow | An interactive workflow for generating high-definition images from text prompts using a human-in-the-loop approach | 2,837 |
 pkuliyi2015/multidiffusion-upscaler-for-automatic1111 | A Python-based image generation tool utilizing advanced diffusion techniques to upscale or generate large images with limited VRAM resources. | 4,790 |
 stability-ai/stablediffusion | A software project that enables high-resolution image synthesis through a specific type of generative model using latent diffusion processes. | 39,501 |
 openai/glide-text2im | A diffusion-based text-conditional image synthesis model | 3,562 |
| doubiiu/tooncrafter | Generates cartoon-style videos from two images using pre-trained diffusion models | 5,447 |
 modelscope/diffsynth-studio | A software framework for training and utilizing various types of diffusion models. | 6,641 |
 mingyuan-zhang/motiondiffuse | Generates human motion from text input using a diffusion model | 869 |
 nateraw/stable-diffusion-videos | Generates videos by manipulating the latent space of Stable Diffusion to create morphing sequences from text prompts. | 4,470 |
 compvis/stable-diffusion | A text-to-image model trained on images and text prompts using a diffusion process | 68,750 |
 xpixelgroup/diffbir | This project provides a deep learning-based pipeline for restoring degraded images | 3,445 |
 ashawkey/stable-dreamfusion | Generates 3D content from text using a combination of neural networks and image synthesis. | 8,351 |
 lkwq007/stablediffusion-infinity | An application that uses Stable Diffusion to generate outpainting results on an infinite canvas | 3,859 |