--- title: "AI Image & Video Models | Made" description: "Every AI image and video model on Made, with real outputs from each: Seedance 2.5, Kling 3, Veo 3.1, GPT Image 2.5, Nano Banana Pro, FLUX and more, on one balance." url: https://www.made.app/models --- # AI image and video models 73 models from OpenAI, Google, ByteDance, Kling, Black Forest Labs and more, on one balance. See what each one makes, then make yours. [Price sheet](https://www.made.app/price-sheet) [API playground](https://www.made.app/playground) ## Video models Text and image to video, most with sound ### [Seedance 2.5](https://www.made.app/models/seedance-2-5) ByteDance’s newest, up to 30s with audio ### [Kling 3 Pro](https://www.made.app/models/kling-3-pro) Cinematic clips with audio ### [Veo 3.1 Lite](https://www.made.app/models/veo-3-1-lite) Google’s Veo with synchronized audio ### [Happy Horse 1.1](https://www.made.app/models/happy-horse-1-1) Alibaba’s arena-leading video model ### [Veo 3.1](https://www.made.app/models/veo-3-1) Google’s flagship video, with sound ### [Seedance 2.0](https://www.made.app/models/seedance-2-0) Up to 15 seconds with native audio ### [WAN 3.0](https://www.made.app/models/wan-3-0) Up to 30 seconds at 1080p ### [Kling O3 Pro](https://www.made.app/models/kling-o3-pro) Steady, believable motion ### [FLUX 3](https://www.made.app/models/flux-3) Black Forest Labs’ first video model ### [MiniMax H3 Max](https://www.made.app/models/minimax-h3-max) Fast, with strong prompt adherence ### [Grok Imagine Video 1.5](https://www.made.app/models/grok-imagine-video-1-5) xAI’s video model, audio on ### [LTX-2.5 Fast](https://www.made.app/models/ltx-2-5-fast) Open audio-video model, up to 20s ### [Seedance 2.0 Mini](https://www.made.app/models/seedance-2-0-mini) Quick drafts before a Seedance 2.5 pass ### [Gemini Omni Flash 1.1](https://www.made.app/models/gemini-omni-flash-1-1) Fast iteration on short scene ideas ### [MiniMax H3 Max Turbo](https://www.made.app/models/minimax-h3-max-turbo) The faster MiniMax H3 Max ### [Kling O3 4K](https://www.made.app/models/kling-o3-4k) Realistic 4K footage with grounded motion ### [Kling 3 4K](https://www.made.app/models/kling-3-4k) Native 4K for big screens, timelines, and crops ### [Grok Imagine Video](https://www.made.app/models/grok-imagine-video) xAI’s first video model ### [WAN 3.0 Prime](https://www.made.app/models/wan-3-0-prime) Fast turnaround when someone is waiting on the clip ### [Seedance 2.0 Fast](https://www.made.app/models/seedance-2-0-fast) Quicker takes that stay close to the flagship look ### [Seedance 2.5 · Person Reference](https://www.made.app/create?model=seedance-2.5-person-reference) Create a video from an authorized person portrait. PiAPI reviews the reference before generation. ### [Gemini Omni Flash](https://www.made.app/models/gemini-omni-flash) Natural scene motion from concise prompts ### [WAN 2.7](https://www.made.app/models/wan-2-7) 1080p video with synced audio, up to 15 seconds ### [Kling 3 Turbo](https://www.made.app/models/kling-3-turbo) Fast 720p clips with native audio ### [Veo 3.1 Native Dialogue](https://www.made.app/models/veo-3-1-native-dialogue) Dialogue, lip sync and sound in one pass ### [Seedance 1.0 Pro](https://www.made.app/models/seedance-1-pro) Silent clips up to 12 seconds at 1080p ### [Seedance 1.5 Pro](https://www.made.app/models/seedance-1-5-pro) Dialogue, foley and score, up to 12 seconds ### [WAN 2.2 5B](https://www.made.app/models/wan-2-2-5b) Fast video drafts from text or an image ### [Kling 2.6 Pro](https://www.made.app/models/kling-2-6-pro) Cinematic shots with stable, controlled motion ### [Kling 2.5 Turbo](https://www.made.app/models/kling-2-5-turbo) Fast image-to-video in 5 or 10 seconds ### [WAN 2.2 Turbo](https://www.made.app/models/wan-2.2-turbo) Fast video concept iteration ## Image models Generate stills from a prompt, and edit them ### [GPT Image 2.5 Flare](https://www.made.app/models/gpt-image-2-5-flare) OpenAI’s newest, with precise edits ### [Nano Banana Pro](https://www.made.app/models/nano-banana-pro) Google’s top tier, up to 4K ### [Nano Banana 2.1](https://www.made.app/models/nano-banana-2-1) Google’s newest, faster than Nano Banana 2 ### [Seedream 5 Pro](https://www.made.app/models/seedream-5-pro) ByteDance’s flagship, strong typography ### [Nano Banana 2](https://www.made.app/models/nano-banana-2) Fast, everyday Google image model ### [GPT Image 2.5 Sunburst](https://www.made.app/models/gpt-image-2-5-sunburst) Maximum detail for demanding edits ### [Flux 2 Pro](https://www.made.app/models/flux-2-pro) Black Forest Labs’ flagship ### [Krea 2](https://www.made.app/models/krea-2) Aesthetic-first, no generic AI look ### [GPT Image 2](https://www.made.app/models/gpt-image-2) Photoreal, with readable text ### [Recraft 4.1](https://www.made.app/models/recraft-4-1) Design-first images for brands ### [Grok Imagine Image 2.0](https://www.made.app/models/grok-imagine-image-2) xAI’s newest image model ### [Muse Image](https://www.made.app/models/muse-image) Meta’s model for precise edits ### [Qwen Image 3](https://www.made.app/models/qwen-image-3) Alibaba’s open model, reliable text ### [Seedream 5 Lite](https://www.made.app/models/seedream-5-lite) Photoreal portraits and product shots ### [Grok Imagine Image Quality](https://www.made.app/models/grok-imagine-image-quality) Grok Imagine’s high-quality tier ### [Grok Imagine Image](https://www.made.app/models/grok-imagine-image) Fast, high-volume image ideas ### [Nano Banana 2 Lite](https://www.made.app/models/nano-banana-2-lite) Sub-2-second generation and editing turnarounds ### [GPT Image 2.5 Fast](https://www.made.app/models/gpt-image-2-5-fast) Fast first drafts before a Flare final ### [FLUX.2 Klein](https://www.made.app/models/flux-2-klein) Sub-second drafts and rapid prompt iteration ### [Z Image](https://www.made.app/models/z-image) Rapid visual concept exploration ### [Reve Create](https://www.made.app/create?model=reve-create) Reve’s text-to-image model ### [Flux 1.1 Pro](https://www.made.app/models/flux-1.1-pro) Photorealistic concepts ### [Qwen Image](https://www.made.app/models/qwen-image) Posters and graphics with a short headline ### [Seedream 4.0](https://www.made.app/models/seedream-4-0) High-resolution editorial and product concepts ### [Nano Banana](https://www.made.app/models/nano-banana) Quick photo edits described in plain language ## Edit, upscale and restore Change, enlarge or repair what you already have ### [Seedream 5 Pro Edit](https://www.made.app/models/seedream-5-pro-edit) Change only what you ask, with references ### [Flux Kontext Max](https://www.made.app/models/flux-kontext-max) Product color, material, and background changes ### [Flux Kontext Pro](https://www.made.app/models/flux-kontext-pro) Rapid background and wardrobe variations ### [Topaz Image Upscale](https://www.made.app/models/topaz-upscale-image) Enlarge photos 2× or 4× with real detail ### [SeedVR2 Video Upscale](https://www.made.app/models/seedvr-video-upscale) Upscale clips 2× or 4×, up to 4K ### [Restore Image](https://www.made.app/models/restore-image) Repair faded and damaged photos ## Lip sync and avatars Make a face talk. Most run on one test photo, so you can compare ### [VEED Fabric 1.0](https://www.made.app/models/veed-fabric) Talking-head videos from a single portrait photo ### [Kling LipSync](https://www.made.app/models/kling-lipsync) Re-voice a video with a new script ### [OmniHuman 1.5](https://www.made.app/tools/lipsync?model=omnihuman-1.5) A photo speaks, with gesture and emotion ### [Kling AI Avatar v2 Pro](https://www.made.app/tools/lipsync?model=kling-avatar-pro) The 1080p Kling talking avatar ### [Kling AI Avatar v2](https://www.made.app/tools/lipsync?model=kling-avatar) A photo speaks your voice track ### [Veo 3](https://www.made.app/tools/lipsync?model=veo-3) Speech, sound and picture from a photo ### [Veo 3 Fast](https://www.made.app/tools/lipsync?model=veo-3-fast) The faster Veo 3, with speech and sound ### [Kling 2.6 (Image to Video)](https://www.made.app/tools/lipsync?model=kling-2.6) A photo speaks the line in your prompt ### [WAN 2.5 (Image to Video)](https://www.made.app/tools/lipsync?model=wan-2.5) A photo speaks a line or your voice track ### [Creatify Aurora](https://www.made.app/tools/lipsync?model=aurora) A photo speaks your voice track, up to 720p ### [Sync Lipsync 3](https://www.made.app/tools/lipsync?model=sync-3) Re-time the mouth in a video to new audio Made Auto ## Not sure which model? Describe the result you want. Made Auto picks the tool and model, and keeps your follow-up edits in one conversation. [Meet Made Auto](https://www.made.app/models/made-auto) ![A portrait edited by Made Auto from a plain-language request](https://www.made.app/images/tools/ai-photo-editor-hero.jpg) Looking for a ready-made workflow? [Browse every tool](https://www.made.app/tools) --- Markdown version of https://www.made.app/models. Every public Made page has one at its URL plus .md (https://www.made.app/models.md). Site summary for AI assistants: https://www.made.app/llms.txt