Stable Diffusion Models Hub
Two Stable Diffusion family models are selectable here — Stable Diffusion and Stable Diffusion XL, both on every plan — alongside 13 other image models and 36 video models. Each has a page describing its inputs and controls.
Who uses the Stable Diffusion models hub?
People who already know which result they want and need to pick the model that produces it. Each model page states the inputs its form accepts, the controls it exposes and the plan it needs.
You know the output, not the model
A product photo, a poster and a 6-second clip are three different model choices. The pages below name what each model is good at rather than ranking them.
You need to know what it costs first
Every generator shows the credit cost of a run before you submit it, and /pricing lists the per-model rows. Nothing is charged for reading a model page.
You need to know if it is on your plan
Availability differs per model: Stable Diffusion, Stable Diffusion XL, Nano Banana and WAN 2.7 are on all plans, while Flux 2 Flex, Seedream 4.5 and Veo 3.1 need a paid one. /ai-models is the current list.
Model pages on this site
Twenty-two model pages, thirteen for images and nine for video. A model page is a description, not a separate generator: every one of them runs from the same two forms.
Stable Diffusion and SDXL
The Stable Diffusion family models, both selectable on every plan. /sdxl covers prompt behavior and the image-to-image route.
Other image models
Flux 2, Flux Kontext, Nano Banana, Nano Banana 2, Nano Banana Pro, Midjourney, GPT Image 2, Seedream 4.5, Seedream 5 Lite, Z-Image and DreamShaper each have a page.
Video models
Veo 3, Kling, Wan, Runway, Hailuo, Grok Imagine, Midjourney Video, Seedance and Seedance 2.0 Mini. Video runs from /ai-video-generator, not the image form.
What a model page does not do
It does not benchmark models against each other or promise a quality ranking. The comparison a model page supports is inputs, controls, plan and credit cost.
How to choose a Stable Diffusion model
Decide still or motion first
Images and video run from different forms. A still-image model cannot be selected in the video generator and the reverse is also true.
Start with Stable Diffusion XL for images
It is on every plan, takes both a text prompt and a source image, and is the baseline the other image pages compare against.
Check the plan before you commit to a model
Roughly half the models here need a paid plan. /ai-models lists every selectable model with its current availability.
Test the prompt, then switch models
The same prompt behaves differently per model. Generate once, then change only the model to see what the model itself is contributing.
Models Hub FAQ
Pick a model, then generate
A model page should answer the input, control, plan and cost question in one read, then send you back to the form.
