🇬🇧 United Kingdom🎨 Image generationReleased October 2024
Stable Diffusion 3.5
Stability AI
Open-sourceFreeSelf-hostRGPD
Verdict
A solid pick for self-hosting and full data control.
Overview
Stable Diffusion 3.5 remains the open-source reference for image generation. Widely supported by the ecosystem (ComfyUI, A1111), thousands of community LoRAs enable custom styles. Ideal for self-host and fine-tuning. Raw quality trailing FLUX.1 and Midjourney but infinite customization.
Skill profile
Not disclosed
Strengths
- Has a free tier
- Open-source and self-hostable
Limitations
- Light safety filters
- API pricing not disclosed
Who is it for
A good fit if…
- you want to control cost or self-host
- you have GDPR constraints
Skip it if…
- you want strict guardrails
Ideal use cases
- Self-hosting image gen
- Custom fine-tuning
- Community LoRAs
- No filters
Access & availability
Free tier availableSelf-hostable (open weights)
Key specifications
Context
4K
Input price
—
Output price
—
Speed
—
Price not auditedBenchmarks not audited
Privacy
GDPR-compliantHosting : selfAnonymizable data
Advanced data · for expertsArchitecture, modalities, detailed cost, full benchmarks▾
Advanced data · for experts
Architecture, modalities, detailed cost, full benchmarks
Architecture
—
Size
—
Cutoff date
—
Inputs
text, image
Outputs
image
License
stability-community
Hosting
self
Hallucination score
3/5
Estimated cost (API)
Typical exchange (~3k in / 1k out)
Not disclosed
1M in + 1M out
Not disclosed
All benchmarks
| Arena Elo | — |
| MMLU | — |
| GPQA | — |
| HumanEval | — |
| SWE-Bench | — |
| MATH | — |