Würstchen
Efficient latent diffusion model using highly compressed latent space.
Open SourceSelf HostedOffline CapableGPU Required (4GB+ VRAM)
0.0 (0)
About
Würstchen uses a novel three-stage pipeline with an extremely compressed latent space (42x compression). Enables fast training and inference while maintaining high image quality. By Pablo Pernias. MIT 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
- MIT
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Similar Tools
Featured
Neural network architecture for adding spatial control to diffusion models.
Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Image prompt adapter for pre-trained text-to-image diffusion models.
Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Zero-shot identity-preserving image generation from a single face photo.
Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)