Stable Diffusion XL Models by Stability AI
1 model2023
Last refreshed 2026-04-18. Next refresh: weekly.
Capabilities
MultimodalAll models
Links
WebsiteAbout
Stable Diffusion XL (SDXL) is Stability AI's large-scale image generation model released in July 2023, representing a significant upgrade from the 1.x series. SDXL uses a two-stage pipeline (base + refiner) with a larger UNet backbone and multiple text encoders, producing higher-resolution and more detailed images. It became a widely adopted foundation for fine-tuning and community model development.
Decision facts
- Best fit
- image generationvision and multimodal workcoding
- Capability starting point
- Stable Diffusion XL with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- Stable Virtual Assistant
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Stable Diffusion XLCurrent
Use when the workload needs image generation, 3K parameters, and multimodal inputs.
2023-07image generation3K parametersmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Stable Diffusion XL | Use when the workload needs image generation, 3K parameters, and multimodal inputs. | 2023-07 | image generation3K parametersmultimodal inputs | Current |
Release Timeline
1 release group2023-07
1 current
Stable Diffusion XL
Currentimage generation3K parametersmultimodal inputs
Specifications(1 models)
| Model | Released | Parameters | Multimodal |
|---|---|---|---|
| Stable Diffusion XL | 2023-07 | 3K | Yes |
