ace-step/audio-inpaint
Edit a precise segment of an audio track while preserving the rest
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | string | — | — | Scene, motion, and camera description |
| aspect_ratio | No | string | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive | Output frame ratio |
| duration | No | integer | 5 | 4–30 (seconds) | Clip length |
| generate_audio | No | boolean | true | true / false | Native synchronized audio |
Seedance 2.5 4K Text to Video bills on generated video length:
Edit a precise segment of an audio track while preserving the rest
HappyHorse 1.0 Reference to Video fuses up to 9 reference images and a prompt into a coherent multi-character clip with stable identity.
AI-powered video creation tool offering 1080p motion and natural expression for precise, artistic storytelling.
Turn images and text into motion-accurate HD videos fast.
LTX 2.5: animate stills to 4K video with synced audio
Seedance 2.5 1080p Text to video: Prompt-to-1080p cinematic clips
Seedance 2.5 4K Text to Video is a ByteDance text-to-video endpoint that renders a written prompt into a 4K clip. It fits large-format screen content, master-resolution ad finals, and establishing shots where fine detail has to survive a big display.
They all share the same prompt-driven path and parameter set; Seedance 2.5 4K Text to Video fixes the output at 4K. A common workflow is to draft cheaply at 480p or 720p, confirm the shot, then re-run the winning prompt through Seedance 2.5 4K Text to Video for the deliverable.
Seedance 2.5 4K Text to Video accepts prompt, aspect_ratio (16:9, 9:16, 1:1, 4:3, 3:4, 21:9, or adaptive), duration from 4 to 30 seconds with a default of 5, and generate_audio for native synchronized sound. Resolution is fixed at 4K, so there is no resolution field to set.
A 4K render moves far more pixels than a 1080p one, so both queue time and price per second are higher. Lock your prompt, aspect ratio, and duration at a lower resolution first, then send only the approved version to Seedance 2.5 4K Text to Video.
Seedance 2.5 4K Text to Video is billed at $1.79 per second of generated video, and the total scales linearly with the duration you pick. Generations draw down your RunComfy usd / credits balance.
Yes. Prototype in the RunComfy model UI, then call the same Seedance 2.5 4K Text to Video template through the RunComfy API using identical parameter names and values. Both paths consume usd / credits from the same balance; reach out at hi@runcomfy.com if you hit integration questions.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
