Show-1
Video generator library
This project enables text-to-video generation using a combination of pixel and latent diffusion models.
[IJCV] Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation
1k stars
39 watching
62 forks
Language: Python
last commit: 4 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| showlab/vlog | Transforms video content into a long document containing visual and audio information that can be used for chat or other applications. | 545 |
 antoine77340/howto100m | Provides code and tools for learning joint text-video embeddings using the HowTo100M dataset | 254 |
 pku-yuangroup/magictime | Generates time-lapse videos from text inputs using deep learning models. | 1,312 |
 damo-nlp-sg/videollama2 | An audio-visual language model designed to advance spatial-temporal modeling and audio understanding in video processing. | 957 |
 taoxugit/attngan | Reproduces text-to-image generation with attentional generative adversarial networks. | 1,343 |
 openmotionlab/motiongpt | Develops a unified model to generate high-quality motions and text descriptions from human motion data | 1,531 |
 pixart-alpha/pixart-sigma | Develops a PyTorch model for 4K text-to-image generation using diffusion transformer | 1,711 |
 eps696/aphantasia | A text-to-image tool using CLIP and FFT/DWT parameters to generate detailed images from user-provided text prompts. | 778 |
 dmulyalin/n2g | A Python library to generate diagrams in various formats from structured data | 157 |
 thereforegames/txt2mask | Automatically generates masks for image inpainting using natural language input | 520 |
 transitive-bullshit/ffmpeg-generate-video-preview | Generates image strips or GIFs from video files | 153 |
 aspiers/ly2video | Converts music represented by a GNU LilyPond file into a video containing a horizontally scrolling music staff synchronized with audio rendering. | 158 |
 mingyuan-zhang/motiondiffuse | Generates human motion from text input using a diffusion model | 869 |
 tsinghuaai/cpm-1-generate | Provides tools and scripts for generating text using a pre-trained Chinese language model | 1,588 |
 labforcomputationalvision/texturesynth | Generates synthetic digital images of visual textures based on mathematical models | 34 |