Images · Stability AI
Stable Diffusion 3.5
Stability AI's SD 3.5 Large, private and about 0.5 credit. It is the Sub Rosa agent's default when you don't name a model.
Private Low costWhat sets it apart
Stability AI's Stable Diffusion 3.5 Large, an 8.1B open-weight model from October 2024. It is the oldest model here, but still useful: private and about half a credit, for quick illustrations and mood images.
- 8.1B open weights, October 2024
- Private and about 0.5 credit
- Short prompts only, 1,500 characters
Recommended for: try many ideas quickly for almost nothing.
Strengths and limits
Where it shines
- Private and among the cheapest (about 0.5 credit)
- Fine for quick illustrations and mood images
Think twice when
- Older (2024): weaker text and prompt following than recent models
- Short prompts only: 1,500 characters
- Shown as "Venice SD35" in the model list
- 8B parameters
Use cases
A quick mood image
A cozy cabin in the mountains at dusk, warm window light, falling snow, painterly style.
Fine for fast, cheap atmosphere shots.
A simple illustration
A flat illustration of a hot air balloon over green hills, pastel colors, simple shapes.
Short prompts work well and cost about 0.5 credit.
Against its rivals
- ChromaChroma is newer and open, with longer prompts allowed.
- Z-Image TurboZ-Image is faster, newer and renders English and Chinese text.#35 of 37 on Artificial Analysis Text to Image Arena (941 Elo)
- FLUXFLUX.2 is far more detailed but pricier and not private.#20 of 37 on Artificial Analysis Text to Image Arena (1,020 Elo)
Version history
Each version, dated, with what it changed over the one before.
- Stable Diffusion 3.5 LargeLatest
- Released with Large Turbo and Medium variants under the Stability AI Community License
Benchmarks
How to read these scores: what a benchmark tells you.
Artificial Analysis Text to Image Arena: #37 of 37 models measured in the catalog. Thousands of people compare two images made from the same prompt without knowing the models, and pick the better one. An Elo rating, as in chess: higher is preferred more often. 100 points apart means the higher one wins about 64% of duels.
- 1. GPT Image 2.5 SunburstGPT Image1,197
- 2. GPT Image 2.5 FlareGPT Image1,191
- 3. GPT Image 2GPT Image1,172
- 4. Nano Banana 2.1Nano Banana1,172
- 5. Grok Imagine 2.0Grok Imagine1,155
- 6. Nano Banana 2Nano Banana1,125
- 7. Muse ImageMuse Image1,115
- 8. GPT Image 1.5GPT Image1,107
- 9. Nano Banana ProNano Banana1,102
- 10. Nano Banana 2 LiteNano Banana1,096
- 37. Venice SD35Stable Diffusion 3.5840
See the numbers
| Model | Elo |
|---|---|
| 1. GPT Image 2.5 Sunburst | 1,197 |
| 2. GPT Image 2.5 Flare | 1,191 |
| 3. GPT Image 2 | 1,172 |
| 4. Nano Banana 2.1 | 1,172 |
| 5. Grok Imagine 2.0 | 1,155 |
| 6. Nano Banana 2 | 1,125 |
| 7. Muse Image | 1,115 |
| 8. GPT Image 1.5 | 1,107 |
| 9. Nano Banana Pro | 1,102 |
| 10. Nano Banana 2 Lite | 1,096 |
| 37. Venice SD35 | 840 |
The model in this family
| Model | Use | Privacy | Price |
|---|---|---|---|
Venice SD35venice-sd35 | Image | Private | $0.0045 per image |
Specifications
| Specification | Stable Diffusion 3.5 Large |
|---|---|
| Released | October 22, 2024 |
| Parameters | 8.1B |
| Weights | Open, Stability AI Community License |
| Accepts | text |
| Produces | images |
| Price | $0.0045 per image |
| Privacy | Private |
Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.
Sources
Everything on this page comes from these pages, read on October 16, 2026 or as dated on each score.