Kandinsky 3

Text-to-image model by Sber AI with latent diffusion architecture.

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

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

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.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

SDXL fine-tune optimized for high-quality anime-style image generation.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)

Versatile Stable Diffusion fine-tune for creative and realistic imagery.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

High-quality SDXL fine-tune optimized for photorealism and detail.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)
Featured

Node-based UI for powerful Stable Diffusion workflows

Open SourceSelf HostedOfflineGPU 4GB+
Advanced
0.0 (0)
Featured

Neural network architecture for adding spatial control to diffusion models.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Browse all Image Generation tools