stable-diffusion-xl-base-1.0
SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model is used to generate (noisy) latents, which are then further processed with a refinement model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/) specialized for the final denoising steps. Note that the base model can be used as a standalone module.
Params
2.6 B
Context
—
Downloads 30d
4.6 M
Likes
8,458
Download history
daily snapshots · 106 days
▲ 349 K in the last 30 days (8.1%)
4.7 M4.1 M
Oct 12Oct 22Nov 1Nov 10
4.7 M1.4 M
Aug 13Sep 12Oct 12Nov 10
4.7 M1.4 M
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 35.2 GB | 39.7 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 2.6 B
- Tensor type
- F32
- Licence
- openrail++
- First seen on the Hub
- 2023-07-25
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-to-image model