Kandinsky-2
Text generator
A multilingual text2image latent diffusion model with improved aesthetics and controllability
Kandinsky 2 — multilingual text2image latent diffusion model
3k stars
49 watching
310 forks
Language: Jupyter Notebook
last commit: 10 months ago diffusionimage-generationimage2imageinpaintingipython-notebookkandinskyoutpaintingtext-to-imagetext2image
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 |
 compvis/stable-diffusion | A text-to-image model trained on images and text prompts using a diffusion process | 68,750 |
 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 |
 lllyasviel/controlnet | An implementation of a neural network structure to control diffusion models by adding extra conditions. | 30,944 |
 open-mmlab/mmagic | A toolkit for building and experimenting with generative AI models for image and video generation, restoration, enhancement, and other tasks. | 6,986 |
 jina-ai/dalle-flow | An interactive workflow for generating high-definition images from text prompts using a human-in-the-loop approach | 2,837 |
| ai-forever/ru-dalle | Generates images from Russian texts using AI models | 1,643 |
 dair-ai/ml-papers-explained | An explanation of key concepts and advancements in the field of Machine Learning | 7,352 |
 deep-floyd/if | A text-to-image synthesis model with a modular design, utilizing a frozen text encoder and cascaded pixel diffusion modules to generate photorealistic images. | 7,699 |
 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 |
| lucidrains/imagen-pytorch | Implements Google's Text-to-Image Neural Network in PyTorch using a cascading DDPM architecture with dynamic clipping and noise level conditioning. | 8,127 |
| openai/clip | A neural network trained on image and text pairs to predict the most relevant text snippet given an image | 26,460 |
| stability-ai/stablecascade | An image generation model that balances efficiency and quality, utilizing a cascade architecture to compress images before training a text-conditional model in a highly compressed latent space. | 6,560 |
 labmlai/annotated_deep_learning_paper_implementations | Implementations of various deep learning algorithms and techniques with accompanying documentation | 57,177 |
 doubiiu/dynamicrafter | This project generates animated videos from open-domain images by leveraging pre-trained video diffusion priors. | 2,668 |