Kandinsky 3
Text-to-image model by Sber AI with latent diffusion architecture.
About
Sber AI's Kandinsky 3 is a large scale text-to-image model based on latent diffusion. The pipeline pairs an 8.6 billion parameter Flan-UL2 text encoder with a 3 billion parameter diffusion U-Net and a MoVQ image encoder and decoder, giving it stronger prompt understanding than earlier Kandinsky releases. Beyond text-to-image generation the repository covers inpainting, outpainting, image fusion, and image variations, while a distilled Kandinsky Flash variant samples in four steps for roughly three times faster inference. Extensions include an HED based ControlNet, an IP-Adapter for image conditioning, and the KandiSuperRes upscaler. Training paid particular attention to Russian cultural content, and the model handles both Russian and English prompts. Code and checkpoints are openly released, with demos on Hugging Face and the FusionBrain web service. Researchers and developers seeking an alternative to Stable Diffusion lineage models are the typical users. Apache 2.0 license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Image Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Minimum VRAM
- 8 GB
- Added
- Apr 3, 2026
Related Tools
State-of-the-art open image generation model by Black Forest Labs with rectified flow transformers.
Next-generation image generation model by Black Forest Labs.
Bilingual text-to-image diffusion transformer by Tencent with Chinese and English support.
Zero-shot identity-preserving image generation from a single face photo.
Image prompt adapter for pre-trained text-to-image diffusion models.
Neural network architecture for adding spatial control to diffusion models.