SDXL-Lightning
Distilled SDXL model by ByteDance enabling 2-8 step image generation.
About
SDXL-Lightning by ByteDance is a distilled text-to-image model that generates high-quality 1024 pixel images in just two to eight steps using progressive adversarial diffusion distillation from Stable Diffusion XL. The repository provides 1, 2, 4, and 8-step checkpoints as both full UNet and LoRA variants, with the few-step models offering the best quality. Released under the Open RAIL-M license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Image Generation
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- Open RAIL-M
- Minimum VRAM
- 6 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.