Stable Diffusion XL [img2img, controlnet]
An SDXL-based image generation model with rich feature support. It specializes in high-quality, versatile image synthesis from text prompts and supports LoRA-based person personalization, enabling self-insertion and avatar-style workflows (e.g., Glif Mojis).
Speed
Price
Inputs
TextImageControlNetLoRA
Outputs
Image
Lab
Stability AI
Stable Diffusion XL [img2img, controlnet] sample outputs
Captured directly from our eval suite. Click any tile to inspect the full render.
More from the Stable Diffusion family
Explore other options from the same family.