zai-org/CogVideoGitHub
calls kandinsky-5 “Pick it for a permissively licensed (MIT) T2V/I2V family with multilingual text conditioning.”
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
13.0kPythonslowing
kandinskylab/kandinsky-5 Alternatives
kandinsky-5 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:
Listed as an alternative to
These projects were analysed and named kandinsky-5 among their alternatives. The relationship is not symmetric — how kandinsky-5 rates them is a separate judgement, made when kandinsky-5 is analysed in its own right.
Tencent-Hunyuan/HunyuanVideoGitHub
calls kandinsky-5 “choose it for a permissively licensed (MIT) video/image generation family with comparable open-weight access”
HunyuanVideo: A Systematic Framework For Large Video Generation Model
12.5kPythonactive
Lightricks/LTX-VideoGitHub
calls kandinsky-5 “choose for a diffusion family covering both image and video if you prefer Kandinsky's trained models and the MIT license.”
Official repository for LTX-Video
11.0kPythonslowing
NVlabs/SanaGitHub
calls kandinsky-5 “Choose when you want Kandinsky 5's MIT-licensed image/video diffusion model family and weights rather than Sana's architecture.”
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
9.1kPythonactive