Stable Diffusion Web
만들기
이미지
비디오
모델

AI Models We Use

The specific third-party AI models behind every generation on Stable Diffusion Web, who builds them, and how we access them.

What powers Stable Diffusion Web

Stable Diffusion Web does not train its own generative models. Every generation you run is carried out by a third-party foundation model built by Alibaba, Black Forest Labs, ByteDance, Google, Google DeepMind, Kuaishou, Midjourney, MiniMax, OpenAI, Runway, Stability AI and the Stable Diffusion community, Topaz Labs, the open-source InfiniTalk project and xAI.

The tables below name the exact models available on Stable Diffusion Web today. The model used for a given generation is either the one you select in the generator, or — where Stable Diffusion Web selects one for you — the model named in the "Underlying model" column. Where our name for a tool differs from the model behind it, that column names the model.

Image models

ModelBuilt byUnderlying modelAvailability
WAN 2.7 ImageAlibaba—All plans
Z-Image TurboAlibaba—Paid plan
Flux 2 FlexBlack Forest Labs—Paid plan
Flux Kontext ProBlack Forest Labs—Paid plan
Seedream 4.5ByteDance—Paid plan
Seedream 5 LiteByteDance—Paid plan
Nano BananaGoogleGoogle gemini-2.5-flash-image.All plans
Nano Banana 2GoogleGoogle gemini-3.1-flash-image-preview.All plans
Nano Banana 2 LiteGoogleGoogle nano-banana-2-lite (Gemini flash image tier).All plans
Nano Banana ProGoogleGoogle gemini-3-pro-image-preview.Paid plan
MidjourneyMidjourney—Paid plan
GPT Image 1.5OpenAIOpenAI GPT Image 1.5.Paid plan
GPT Images 2OpenAIOpenAI GPT Image 2.Paid plan
Stable DiffusionStability AI and the Stable Diffusion communityLykon dreamshaper-8-lcm, a Stable Diffusion community fine-tune, run on Cloudflare Workers AI.All plans
Stable Diffusion XLStability AI and the Stable Diffusion communityStability AI stable-diffusion-xl-base-1.0, run on Cloudflare Workers AI.All plans

Video models

ModelBuilt byUnderlying modelAvailability
Wan 2.2 AnimateAlibaba—Paid plan
Wan 2.5Alibaba—Paid plan
Wan 2.6Alibaba—Paid plan
Wan 2.6 FlashAlibaba—Paid plan
Wan 2.6 R2VAlibaba—Paid plan
WAN 2.7Alibaba—All plans
OmniHuman 1.5ByteDance—All plans
Seedance 2.0ByteDance—Paid plan
Seedance 2.0 FastByteDance—Paid plan
Seedance 2.0 MiniByteDance—All plans
Seedance V1 LiteByteDance—Paid plan
Seedance V1 ProByteDance—Paid plan
Seedance V1 Pro FastByteDance—All plans
Seedance V1.5 ProByteDance—Paid plan
Gemini Omni VideoGoogle—All plans
Veo 3Google DeepMind—Paid plan
Veo 3.1Google DeepMind—Paid plan
Veo 3.1 FastGoogle DeepMind—Paid plan
Kling V2.1Kuaishou—Paid plan
Kling V2.1 MasterKuaishou—Paid plan
Kling V2.1 ProKuaishou—Paid plan
Kling V2.6Kuaishou—Paid plan
Kling V2.6 Motion ControlKuaishou—Paid plan
Kling V2VKuaishou—Paid plan
Kling V3Kuaishou—Paid plan
Kling Video O1Kuaishou—Paid plan
Midjourney VideoMidjourney—Paid plan
Hailuo V2MiniMax—Paid plan
Runway AlephRunway—Paid plan
Runway Gen4 TurboRunway—Paid plan
InfiniTalkthe open-source InfiniTalk project—All plans
Topaz Video UpscaleTopaz Labs—All plans
Grok ExtendxAI—All plans
Grok Imagine VideoxAI—Paid plan
Grok Imagine Video 1.5 PreviewxAI—Paid plan
Grok UpscalexAI—All plans

How we access these models

We reach these models through their providers' own APIs and through commercial inference aggregators, including KIE.ai, fal.ai, Replicate, Cloudflare Workers AI, and Google's Gemini API. The aggregator is a delivery route, not the model author: the "Built by" column above names the organisation that built and trains each model.

Your prompts and uploads are sent to the provider of the model you are using, for the sole purpose of producing your output. We do not use your content to train models, and we do not sell it. See our Privacy Policy for how your data is handled, and our Terms of Service for the rules that apply to what you generate.

Changes to this list

Model availability changes as providers release, update, and retire models. This page is generated from the service's own model configuration, so it reflects what is actually running rather than a separately maintained list. If a model you used previously is no longer listed, it is no longer available on Stable Diffusion Web.

Questions about a specific model can be sent to our support team, listed on the Support page.