# Hermoso: Seedance 2.5 Draft on Hermoso: 4–30s, 480p, native sound > Machine-readable twin of https://hermoso.ai/models/seedance-2-5-draft/. Generated from the shipped page. Do not edit by hand. > Full agent guide: https://hermoso.ai/llms.txt · MCP: https://app.hermoso.ai/mcp [Models](https://hermoso.ai/models/) › [Video models](https://hermoso.ai/models/video/) # Seedance 2.5 Draft A quick 480p draft of a Seedance 2.5 take at a fraction of the price; like it, then finish that same take at 1080p ByteDance · video model **4–30s** clip length **480p** best resolution **Native sound** speech and world audio in the render **up to 9** reference images Seedance 2.5 Draft is one of 49 video models Hermoso can render a video ad, product sizzle or UGC clip with. Name it, or leave the model out and the router picks a sound default. The same catalog is available from the app, the [MCP server](https://hermoso.ai/mcp/) and the CLI, on one account and one credit balance; the exact price of every render is shown in the app before it runs. ## What people make with it - [UGC testimonials and talking creators](https://hermoso.ai/recipes/testimonial-video/) - [Product sizzles and packshot spins](https://hermoso.ai/recipes/orbit-360/) - [Cinematic brand films](https://hermoso.ai/recipes/cinematic/) - [Faceless product demos and explainers](https://hermoso.ai/recipes/explainer/) The linked formats are [creative recipes](https://hermoso.ai/recipes/) Hermoso plans and renders for your brand. ## About ByteDance ByteDance makes the Seedance video family and the Seedream image models, known for native audio and long unbroken takes. ## Specs Lengths 4s 5s 6s 8s 10s 12s 15s 20s 25s 30s Longest single take 30s in one unbroken shot Resolutions 480p Aspect ratios 9:16 16:9 1:1 4:3 3:4 21:9 Sound Native audio (can be switched off per render) Modes text to video, image to video, reference to video Reference images up to 9 per render in Hermoso (our fidelity cap, measured on paid renders; the model itself accepts more), addressed in the prompt as @Image1, @Image2… Reference videos up to 10 Reference audio up to 10 Edit an existing video No Model id `seedance-2.5-draft` ## Where it fits Each aspect ratio Seedance 2.5 Draft renders maps to a placement: - **9:16** for Reels, TikTok, Shorts and Stories - **16:9** for YouTube, in-stream and display - **1:1** for Feed posts and carousels - **4:3** for Presentations and display - **3:4** for Pinterest and tablet feed - **21:9** for Cinematic banners and hero films ## Seedance 2.5 Draft compared with other video models Model Lengths Top resolution Sound Refs **Seedance 2.5 Draft** 4–30s 480p Native up to 9 [Seedance 2.5](https://hermoso.ai/models/seedance-2-5/) 4–30s 1080p Native up to 9 [Seedance 2.0](https://hermoso.ai/models/seedance-2-0/) 5–15s 4k Native up to 5 [Seedance 2.5 Edit](https://hermoso.ai/models/seedance-2-5-edit/) 4–30s 1080p Native n/a [Gemini Omni 1.1](https://hermoso.ai/models/gemini-omni-1-1/) 4–10s 4k Native up to 3 [Kling 4.0 Edit](https://hermoso.ai/models/kling-4-0-edit/) 5–30s 1080p Silent up to 4 [Gemini Omni](https://hermoso.ai/models/gemini-omni/) 4–10s n/a Native up to 3 See [all 49 video models](https://hermoso.ai/models/video/) side by side. ## Just ask for it In Claude, ChatGPT, Cursor or any assistant connected to Hermoso, name the model in plain English. Or pick it from the model menu in the app. Make a 15 second UGC ad for our olive oil with Seedance 2.5 Draft, kitchen at golden hour, 9:16. Render the packshot spin on Seedance 2.5 Draft and post it to TikTok and Reels. Redo yesterday's ad on Seedance 2.5 Draft with the new label. ## Getting the best out of Seedance 2.5 Draft - Describe one continuous camera move and where it ends. The model renders motion, not a shot list. - Attach the real product photo as a reference and ask for it matched exactly. Never describe a lookalike. - Name colours in words. A hex code turns into text on screen. - Keep spoken lines short. Roughly two words per second is what a clip can carry cleanly. - Ask for the placement's ratio up front (9:16 for Reels and TikTok) instead of cropping afterwards. Make a video ad with Seedance 2.5 Draft. Start free, and every feature is on every plan. [Start free →](https://app.hermoso.ai/?src=model-seedance-2-5-draft#models/m/video:seedance-2.5-draft) [See pricing](https://hermoso.ai/pricing) ## Frequently asked questions ### How long a video can Seedance 2.5 Draft make? Seedance 2.5 Draft renders clips from 4 to 30 seconds, and up to 30 seconds in one unbroken take. Longer spots are built from several clips. ### Does Seedance 2.5 Draft make sound? Yes. Seedance 2.5 Draft renders native audio with the picture, so a talking creator or a voiceover is part of the same take. ### Can Seedance 2.5 Draft use my product photos? Yes. Attach up to 9 reference images of the product and Hermoso keeps the real product in the render. ### How much does Seedance 2.5 Draft cost? The exact credit price is shown in the app before every render and settled at cost. See pricing for what a credit is worth. ## Related video models Other ByteDance models first, then the video models listed nearest to Seedance 2.5 Draft in the catalog. [Seedance 2.5 default Up to 30s in ONE unbroken take · synced audio · keeps a person’s face from a saved creator or a photo you have the rights to 4–30s · 1080p / 720p / 480p · native sound](https://hermoso.ai/models/seedance-2-5/)[Seedance 2.0 Synced audio · up to 15s · people come out visibly AI (waxy skin, glossy light): use it for objects, food, b-roll or stylised clips, and Seedance 2.5 for real-looking people 5–15s · 720p / 1080p / 480p · native sound](https://hermoso.ai/models/seedance-2-0/)[Seedance 2.5 Edit Region-level edits on a clip you already have: change one object, face or setting and the rest stays untouched · keeps synced audio · up to 30s 4–30s · 1080p / 720p / 480p · native sound](https://hermoso.ai/models/seedance-2-5-edit/)[Gemini Omni 1.1 Newest Omni: sound included, better at whole scenes 4–10s · 720p / 1080p / 4k · native sound](https://hermoso.ai/models/gemini-omni-1-1/)[Kling 4.0 Edit Newest Kling editor: edits a clip you already have from a text instruction and up to four reference images, keeping its motion, timing and sound; one pass up to 30s, 720p or 1080p 5–30s · 720p / 1080p · silent](https://hermoso.ai/models/kling-4-0-edit/)[Gemini Omni Fast and cheapest with sound. Start from text, an image or a video 4–10s · native sound](https://hermoso.ai/models/gemini-omni/)[Kling O3 Edit Edits a clip you already have from a text instruction and up to four reference images, keeping its motion, timing and sound; clips of 3 to 15s at 720px or wider 5–15s · silent](https://hermoso.ai/models/kling-o3-edit/)[Veo 3.1 Top quality with sound, cinematic 4–8s · native sound](https://hermoso.ai/models/veo-3-1/) See [all 49 video models](https://hermoso.ai/models/video/) or [every model Hermoso offers](https://hermoso.ai/models/).