sd-turbo
SD-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation. We release SD-Turbo as a research artifact, and to study small, distilled text-to-image models. For increased quality and prompt understanding, we recommend SDXL-Turbo.
Params
870 M
Context
—
Downloads 30d
339 K
Likes
462
Download history
daily snapshots · 55 days
▲ 245 K in the last 30 days (41.9%)
590 K334 K
Aug 22Sep 1Sep 11Sep 20
738 K334 K
Jul 28Aug 15Sep 2Sep 20
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 | 13.0 GB | 14.9 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Parameters
- 870 M
- Tensor type
- F32
- First seen on the Hub
- 2023-11-27
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-to-image model