Kandinsky 3
Text-to-image model by Sber AI with latent diffusion architecture.
About
Kandinsky 3 is an open-source text-to-image model by Sber AI Lab. Uses a latent diffusion architecture with improved text understanding and image quality over previous versions. Supports Russian and English prompts. Requires GPU with 8+ GB VRAM. 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
Image prompt adapter for pre-trained text-to-image diffusion models.
SDXL fine-tune optimized for high-quality anime-style image generation.
Versatile Stable Diffusion fine-tune for creative and realistic imagery.
High-quality SDXL fine-tune optimized for photorealism and detail.
Node-based UI for powerful Stable Diffusion workflows
Neural network architecture for adding spatial control to diffusion models.