Kandinsky-2 is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named Kandinsky-2 among their alternatives. The relationship is not symmetric — how Kandinsky-2 rates them is a separate judgement, made when Kandinsky-2 is analysed in its own right.
calls Kandinsky-2 “Use it when you need multilingual text prompts or Apache-2.0 licensing rather than Stable Diffusion's original license, though it is no longer actively developed.”
A latent text-to-image diffusion model
calls Kandinsky-2 “A standalone implementation of Kandinsky 2; choose it if that specific architecture is your target and you do not need a general library.”
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
calls Kandinsky-2 “Choose for multilingual text-to-image diffusion generation as a self-contained model.”
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.