Stable Diffusion 3.5
the ecosystem that started it all, twenty-one months without a successor
still the widest tooling ecosystem in open image models, and now a full generation behind — there is no stable diffusion 4, whatever you have read.
stable diffusion 3.5 shipped in october 2024 and remains stability's newest image model. that is twenty-one months without a successor while the rest of the category shipped two or three generations.
to be explicit, because there is a lot of confident misinformation about this: there is no stable diffusion 4. stability's own model page lists 3.5 as current, and its only 2026 announcements are stable audio 3.0 and brand studio — neither an image model. articles describing sd4 tiers and 4096px output are fabricated.
the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.
- category
- ai image models
- pricing
- free below $1M annual revenue
- website
- stability.ai
still the widest tooling ecosystem in open image models, and now a full generation behind — there is no stable diffusion 4, whatever you have read.
we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.
more ai image models
Leonardo.Ai
image generation platform with fine-tuned community models and a canvas editor
Google Imagen
google's text-to-image family, available through the gemini api and vertex ai