wan-2-5/text-to-video
Generate videos from text prompts with audio using Wan 2.5 Preview.
Seedance 2.0 Mini is ByteDance's leaner, lower-latency entry in the Seedance line, built to turn ideas into finished video quickly and cheaply. The wider model is not a single-trick generator: the same system covers text-to-video, image-to-video, and video editing, so you can start from a written idea, a still frame, or existing footage and stay in one toolset.
What sets it apart is shot-level storytelling. Rather than a single moving frame, it assembles short narrative sequences with directed camera moves and characters that stay recognizable from cut to cut. Sound is generated jointly with the picture, so dialogue, ambience, and effects land in time with the action instead of being layered in afterward.
Reference inputs sharpen the result further. Supplying reference images, videos, or audio steers visual style, character likeness, motion direction, or sound character, giving you tighter control without re-prompting from scratch.
On RunComfy, this page exposes the text-to-video mode: you write a prompt and receive a short clip with built-in audio. The image-to-video and editing capabilities belong to the same model family.
Output format: Resolution 480p, 720p, 1080p, or 4K / duration 4-15s / aspect ratio 16:9, 9:16, 4:3, 3:4, 1:1, 21:9 / audio optional
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | string | — | — | Scene, subject, action, camera movement, and mood. |
| resolution | No | string | 720p | 480p, 720p, 1080p, 4k | Output resolution tier. |
| aspect_ratio | No | string | 16:9 | 16:9, 9:16, 4:3, 3:4, 1:1, 21:9 | Aspect ratio of the video. |
| duration | No | integer | 5 | 4-15 | Clip length in seconds. |
| generate_audio | No | boolean | enabled | true/false | Generate synchronized native audio. |
| enable_web_search | No | boolean | disabled | true/false | Pull in real-time information when needed. |
Pricing is time-based and scales with the chosen resolution:
| Resolution | Rate |
|---|---|
| 480p | $0.06 per second |
| 720p | $0.12 per second |
| 1080p | $0.30 per second |
| 4K | $0.60 per second |
Estimated cost examples
| Duration | 480p | 720p | 1080p | 4K |
|---|---|---|---|---|
| 5 s (default) | ~$0.30 | ~$0.60 | ~$1.50 | ~$3.00 |
| 10 s | ~$0.60 | ~$1.20 | ~$3.00 | ~$6.00 |
| 15 s | ~$0.90 | ~$1.80 | ~$4.50 | ~$9.00 |
Generate videos from text prompts with audio using Wan 2.5 Preview.
Turn static images into fluid, realistic 1080p motion with smart style control.
Transform still visuals into cinematic motion clips with smooth, realistic transitions and creative flexibility.
Create lifelike 1080p clips from text with synced audio and flexible ratios.
Create lifelike synced videos from voices or images with precise motion and creative control.
Animate between two images with smooth keyframe transitions using Pikaframes.
Seedance 2.0 Mini is ByteDance's fast, low-cost video model that turns a text prompt into a short, multi-shot clip with directed camera movement and synchronized audio. The wider model also covers image-to-video and video editing, so it suits cinematic short clips, social spots, and quick narrative prototyping from a single description.
No. The Seedance 2.0 Mini model family spans text-to-video, image-to-video, and video editing within one system. This RunComfy page currently runs the text-to-video mode, where you write a prompt and receive a clip with optional native audio.
Yes. Seedance 2.0 Mini can generate synchronized native audio together with the video in a single pass, controlled by the generate_audio switch. Leave it on for a clip with sound, or turn it off when you only need silent footage.
Seedance 2.0 Mini outputs 480p, 720p, 1080p, or 4K video, with clip lengths from 4 to 15 seconds. You can also pick an aspect ratio of 16:9, 9:16, 4:3, 3:4, 1:1, or 21:9 to fit landscape, vertical, square, or ultra-wide placements.
Seedance 2.0 Mini holds character identity and visual style steady across cuts, and you can sharpen that with reference inputs where supported. Naming the subject, action, and camera move clearly in the prompt also helps keep multi-shot sequences coherent.
Lead with the main subject and one clear action, then add setting, lighting, camera movement, and mood. Because Seedance 2.0 Mini generates motion and sound together, describing the camera move and any audio cues gives more predictable results.
The text-to-video mode takes a prompt plus resolution, aspect ratio, duration, audio, and web-search controls, with durations between 4 and 15 seconds. Check the current RunComfy parameter panel for exact limits, since some options may vary by provider settings.
Yes. You can prototype Seedance 2.0 Mini in the RunComfy model UI, then call the same model via the RunComfy API with identical parameters for automation. You don't need to host or scale the model yourself.
Generations with Seedance 2.0 Mini are billed per second of video and consume usd or credits: $0.06 at 480p, $0.12 at 720p, $0.30 at 1080p, and $0.60 at 4K. For example, a 5-second 720p clip costs about $0.60; see the Generation section on the page for current details.
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.
