Stable Diffusion 3.5 Large
Open weights, runs on a single GPU — community’s preferred base model.
Intelligence index
—
Composite of MMLU, GPQA, MATH & HumanEval
Speed
—
Median across providers, steady state
Price per image
$0.010
At default resolution
At a glance
- Time to first token
- 5s
- Input modalities
- text
- Output modalities
- image
- License
- Open source
- Provider
- Stability AI
Strengths
- Open weights
- Huge LoRA ecosystem
- Cheap to host
Weaknesses
- Aesthetic quality below Midjourney v6
Best for
- Self-hosting
- Custom style fine-tunes
- On-prem deployment
Models you should also evaluate
DeepSeek
DeepSeek R1
Open-weights reasoning model that matches o1 at 1/25 the price.
73 intel60 tok/s$0.96 /1M
DeepSeek
DeepSeek V3
Frontier-class quality at fast-tier prices — and open weights.
67 intel90 tok/s$0.48 /1M
Meta
Llama 3.3 70B
Open-weights 70B that matches GPT-4o on most benchmarks.
66 intel200 tok/s$0.27 /1M
Stable Diffusion 3.5 Large vs… popular head-to-heads
One-click matchups against the models people compare Stable Diffusion 3.5 Large with most.
Stable Diffusion 3.5 Large — frequently asked questions
Stable Diffusion 3.5 Large is a text-to-image model from Stability AI, released on 22 October 2024. Open weights, runs on a single GPU — community’s preferred base model.
Need help choosing between models?
Compare every option in one sortable table — intelligence, speed and price on a single page.