Stability AI, lab API for Stable Image
Stability AI (stability.ai / platform.stability.ai) is the lab’s developer desk: a billed REST API for stills. Public docs name Stable Image Ultra as the flagship (based on Stable Diffusion 3.5 Large, 1 megapixel, default 1024×1024), Stable Image Core as the fast next step after SDXL, and the SD 3.5 suite on the same API — Large (8B), Large Turbo, Medium (2.5B) and Flash. The lab also names audio, video and 3D on Core Models; this page is the image API. It is not the open Stable Diffusion weights you download to ComfyUI, and it is not SoulGen’s character stills desk. ImgToVid does not run Stability AI; the generator on this page drafts on GPT Image 2.5 Flare.
01 — Capabilities
A billed lab API, not a 4K picker here
Public Stability pages sell Ultra, Core and the SD 3.5 suite on platform.stability.ai. They do not sell this site’s Nano Banana 4K table.
01
Stable Image Ultra: flagship, based on SD 3.5 Large
Docs name 1 megapixel, default 1024×1024. That generate stays on their API. This page does not open that key.
02
Stable Image Core, next after SDXL, named for speed
A fast billed still, not a local checkpoint. Delivery stays on platform.stability.ai.
03
SD 3.5 suite on the same API: Large, Turbo, Medium, Flash
Large is named at 8B; Medium at 2.5B. An API row there is not a 4K still picker here.
04
Not open Stable Diffusion weights, not SoulGen’s character desk
Stable Diffusion is the model family you run locally from Hugging Face. SoulGen sells character stills on soulgen.ai. Stability AI is the lab API. This site does not open Stability AI.
02 — Prompt to output
Prompts that match the stills above
Each prompt describes the picture on its card. “Use this prompt” sends that text to Create. The generator on this page runs GPT Image 2.5 Flare, not Stability AI.
01 · PortraitPromptClose photographic portrait of a young man with curly hair wearing a grey knit sweater, soft window light, he glances aside and smiles warmly, shallow depth of field.
02 · ProductPromptA clean white leather sneaker on a pale grey seamless studio backdrop, soft diffused light, three-quarter view, crisp stitching, minimal commercial photograph.
03 · StreetPromptPhotographic view down a cobblestone lane in an old European village, climbing roses on stone walls, café tables in morning sun, a few people strolling in the distance.
04 · CharacterPromptPhotograph of a young woman with shoulder-length brown hair in an olive t-shirt, golden late-afternoon light, she turns her head and looks into the distance, breeze in her hair.
03 — Where it fits
Jobs a lab API desk is selling
Public pages point at Ultra, Core and SD 3.5 behind an API key. They do not sell a one-shot Nano Banana still on this site.
A flagship Ultra still at 1 megapixel
That job is platform.stability.ai. This page does not open that API.
A fast Core still, or an SD 3.5 Large / Turbo / Medium / Flash call
Delivery stays on their API. Not a character companion product and not a local ComfyUI graph.
Start from an image with strength, or set aspect_ratio
Ultra docs name an image plus strength, and aspect_ratio. Not a 4K Pro still here.
A draft still on ImgToVid
Write the still here. GPT Image 2.5 Flare carries the prompt into Create. Membership and credits are checked there.
04 — Verdict
What Stability AI actually is
Strengths
- platform.stability.ai: billed lab API for stills
- Stable Image Ultra (SD 3.5 Large, 1 megapixel) and Core still listed
- SD 3.5 Large 8B, Large Turbo, Medium 2.5B and Flash named on the same API
- Honest that this is the lab API, not a Nano Banana still on ImgToVid
Trade-offs
- 1 megapixel is named on Ultra / SD 3.5 Large — not a 4K still picker here
- A Stability API job is not a one-shot still here
- Stability AI is not available on ImgToVid
- Marked coming soon on this site
05 — Side by side
Stability AI, Nano Banana 2 and GPT Image 2.5
Stability AI is the lab’s billed image API. Nano Banana 2 and GPT Image 2.5 numbers below are from those vendors’ public docs on ImgToVid. A 1 megapixel Ultra row there is not a 4K still row here.
06 — How it works
Start a still on ImgToVid
Step 1
Describe one still
Subject, light, frame. Stability AI will not be the model that runs it.
Step 2
Use the generator on this page
It runs GPT Image 2.5 Flare, because Stability AI is not offered here. The prompt and the settings carry into Create.
Step 3
Generate in Create
Membership and credits are checked there. Coming back to this page does not switch the model over to Stability AI.
07 — FAQ
Stability AI, in plain terms
What is Stability AI?
Stability AI is the lab behind the billed developer API on platform.stability.ai: Stable Image Ultra (based on SD 3.5 Large, 1 megapixel), Stable Image Core, and the SD 3.5 suite. ImgToVid does not host Stability AI.
What resolution does Stability AI output?
Public Ultra and SD 3.5 Large docs name 1 megapixel, default 1024×1024. That is not a 4K still picker on this site.
Does Stability AI generate images from text?
Yes — on platform.stability.ai, from a prompt, behind an API key. That is the lab API, not a one-shot still on ImgToVid.
How is this different from Stable Diffusion?
Stable Diffusion is the open-weights model family (SDXL, SD 3.5) you download to Hugging Face or ComfyUI. This page is the company’s billed API — Ultra, Core and the same SD 3.5 models hosted for you. SoulGen is a separate character stills product. This site opens none of them.
Can I generate Stability AI images on ImgToVid?
No. The generator on this page runs GPT Image 2.5 Flare so you can draft a still. Stability AI is marked coming soon.
Can I use the results commercially?
Commercial use of anything you generate on ImgToVid depends on your plan. Check Pricing and our Terms before you publish, and make sure prompts and uploads do not infringe someone else’s rights.
08 — Explore more
Other AI image models
Stability AI is not the button on this page
You can still draft the still. The generator runs GPT Image 2.5 Flare, and the prompt goes with you into Create.
Draft in Create