Kolors
Text-to-Image Synthesis Framework
A Python framework for training and deploying photorealistic text-to-image synthesis models.
Kolors Team
4k stars
40 watching
293 forks
Language: Python
last commit: 3 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 lucidrains/dalle2-pytorch | An implementation of DALL-E 2's text-to-image synthesis neural network in PyTorch | 11,184 |
 cszn/kair | Image restoration toolbox with training and testing codes for various deep learning-based methods | 2,994 |
 ai-forever/kandinsky-2 | A multilingual text2image latent diffusion model with improved aesthetics and controllability | 2,774 |
 transcranial/keras-js | An open source JavaScript library that allows running Keras models in the browser with GPU support using WebGL. | 4,964 |
 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 |
 clovaai/stargan-v2 | A Python implementation of an image-to-image translation model for generating diverse images across multiple domains. | 3,513 |
 doubiiu/dynamicrafter | This project generates animated videos from open-domain images by leveraging pre-trained video diffusion priors. | 2,668 |
 leoxiaobin/deep-high-resolution-net.pytorch | An implementation of a deep learning network for human pose estimation using high-resolution representations | 4,354 |
 lllyasviel/controlnet | An implementation of a neural network structure to control diffusion models by adding extra conditions. | 30,944 |
 openai/guided-diffusion | This project is a software implementation of a diffusion model architecture, allowing users to generate synthetic images based on a learned distribution. | 6,366 |
 modelscope/diffsynth-studio | A software framework for training and utilizing various types of diffusion models. | 6,641 |
 tencent/hunyuandit | A PyTorch model definition and inference/sampling code repository for a powerful diffusion transformer with fine-grained Chinese understanding | 3,678 |
 yangxy/gpen | An open-source software project that develops and provides tools for restoring degraded faces in images using Generative Pre-trained Networks. | 2,456 |
 borisdayma/dalle-mini | Generates images from text prompts using a variant of the DALL-E model | 14,756 |
 dome272/wuerstchen | A framework that enables efficient training of text-to-image models by compressing the computationally expensive stage into a latent space | 531 |