From the model card
Fields below are copied from the tags and counters on the HuggingFace repository stabilityai/stable-diffusion-xl-base-1.0 at our last fetch. They are set by the uploader, not verified by us; rows with no tag are omitted. How this page is made.
- Publisher (HF namespace)
- stabilityai
- Pipeline tag
- text-to-image
- Library
- Diffusers
- Weight formats
- ONNX, safetensors
- License tag
openrail++— read the license file in the repo before relying on it- Papers cited
- arXiv:2307.01952, arXiv:2211.01324, arXiv:2108.01073, arXiv:2112.10752
- Downloads (HF counter at last fetch)
- 1,677,646
- Likes (HF counter at last fetch)
- 8,106
- Model card
- https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
Use cases
- High-quality text-to-image generation at 1024px resolution
- Creative content generation for design and illustration
- Base model for fine-tuning via LoRA or DreamBooth
- Foundation for downstream SDXL variants like SDXL-Turbo and Juggernaut XL
Pros
- Significant image quality improvement over SD 1.x/2.x
- Native 1024px resolution without upscaling artifacts
- Large community ecosystem with many LoRA and checkpoint extensions
- Paired with SDXL-Refiner for optional two-stage generation
Cons
- SDXL requires ~10GB VRAM at BF16 — higher than SD 1.5
- Stability AI's license restricts some commercial applications — verify terms
- Generation speed slower than SD 1.5 due to larger architecture
- Rapidly superseded by FLUX.1 and newer architectures for quality-critical work
Tags
diffusersonnxsafetensorstext-to-imagestable-diffusionarxiv:2307.01952arxiv:2211.01324arxiv:2108.01073arxiv:2112.10752license:openrail++endpoints_compatiblediffusers:StableDiffusionXLPipelineregion:usdeploy:sagemakerdeploy:azure