Stable Diffusion, open text-to-image weights

Stable Diffusion is the open text-to-image model family Stability AI released: weights you download, not a billed REST desk. Public pages name SDXL 1.0 on Hugging Face under CreativeML Open RAIL++-M, and Stable Diffusion 3.5 Large / Large Turbo / Medium under the Stability AI Community License, with local inference named on ComfyUI and consumer GPUs. SD 3.5 Large is named at 1 megapixel for professional stills. It is not the company’s Ultra / Core API landing on platform.stability.ai, and it is not SoulGen’s character stills product. ImgToVid does not run Stable Diffusion; the generator on this page drafts on GPT Image 2.5 Flare.

01 — Capabilities

An open-weights family, not a 4K picker here

Public Stable Diffusion pages sell checkpoints you run locally. They do not sell this site’s Nano Banana 4K table.

01
SDXL 1.0 weights on Hugging Face, CreativeML Open RAIL++-M
A local checkpoint, not a hosted Ultra call. This page does not open that download.
02
SD 3.5 Large, Large Turbo and Medium named
Community License on Hugging Face. Large is named at 1 megapixel. Delivery stays on your GPU, not here.
03
Local inference named on ComfyUI and consumer hardware
A node graph on your machine. That is not a 4K still picker on ImgToVid.
04
Not Stability’s billed Ultra/Core API, not SoulGen’s character desk
The lab API on platform.stability.ai hosts Ultra, Core and SD 3.5 for you. SoulGen sells character stills on soulgen.ai. This page is the open model name. This site does not open Stable Diffusion.

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 Stable Diffusion.

01 · Portrait
PromptClose 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 · Product
PromptA clean white leather sneaker on a pale grey seamless studio backdrop, soft diffused light, three-quarter view, crisp stitching, minimal commercial photograph.
03 · Street
PromptPhotographic 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 · Character
PromptPhotograph 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 an open-weights family is selling

Public pages point at a local checkpoint, a Community License and a ComfyUI graph. They do not sell a one-shot Nano Banana still on this site.

Download SDXL or SD 3.5 and run it on your GPU
That job is Hugging Face plus your machine. This page does not open that job.
A ComfyUI graph for a still from a prompt
Delivery stays on your hardware. Not a billed Ultra key and not a character companion studio.
A 1 megapixel SD 3.5 Large still on your own stack
Named on Stability’s SD 3.5 pages. 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 Stable Diffusion actually is

Strengths

Open text-to-image family from Stability AI: SDXL 1.0 and SD 3.5
SDXL under CreativeML Open RAIL++-M; SD 3.5 under the Community License, still listed
Local ComfyUI and consumer GPU named; Hugging Face weights named
Honest that this is open weights, not a Nano Banana still on ImgToVid

Trade-offs

SD 3.5 Large is named at 1 megapixel — not a 4K still picker here
A local Stable Diffusion job is not a one-shot still here
Stable Diffusion is not available on ImgToVid
Marked coming soon on this site

05 — Side by side

Stable Diffusion, Nano Banana 2 and GPT Image 2.5

Stable Diffusion is an open-weights model family. Nano Banana 2 and GPT Image 2.5 numbers below are from those vendors’ public docs on ImgToVid. A 1 megapixel SD 3.5 Large still there is not a 4K still row here.

	Stable Diffusion	Nano Banana 2	GPT Image 2.5
Developer	Stability AI	Google	OpenAI
Top resolution	1 megapixel named (SD 3.5 Large)	4K	4K
Reference images	Local img2img / ComfyUI named	Up to 14	Up to 16
Images per run	A local generate on your GPU	1	1
Extreme frames	Not a 1:8 still table here	1:8 and 8:1	1:3 and 3:1
On ImgToVid	Coming soon	Available now	Available now

06 — How it works

Start a still on ImgToVid

Step 1
Describe one still
Subject, light, frame. Stable Diffusion will not be the model that runs it.
Step 2
Use the generator on this page
It runs GPT Image 2.5 Flare, because Stable Diffusion 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 Stable Diffusion.

07 — FAQ

Stable Diffusion, in plain terms

What is Stable Diffusion?

Stable Diffusion is the open text-to-image model family from Stability AI: SDXL 1.0 weights on Hugging Face, and SD 3.5 Large / Turbo / Medium under the Community License, with local inference named on ComfyUI. ImgToVid does not host Stable Diffusion.

What resolution does Stable Diffusion output?

Public SD 3.5 Large pages name 1 megapixel. That is not a 4K still picker on this site. Local SDXL resolution depends on the checkpoint and your GPU — this site does not publish a picker for it.

Does Stable Diffusion generate images from text?

Yes — on your machine or a host that loaded the weights, from a prompt. That is Stable Diffusion, not a one-shot still on ImgToVid.

How is this different from Stability AI?

Stability AI is the company and its billed API (Ultra, Core, hosted SD 3.5) on platform.stability.ai. This page is the open model family you download. SoulGen is a separate character stills product. This site opens none of them.

Can I generate Stable Diffusion images on ImgToVid?

No. The generator on this page runs GPT Image 2.5 Flare so you can draft a still. Stable Diffusion 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.