sora-2/pro/text-to-video
Generate premium videos with synced audio from text using OpenAI Sora 2 Pro.
Seedance 2.5 Image to Video 720p animates a still image into a short cinematic clip at 720p. Provide one image and a prompt that describes motion and camera work; Seedance 2.5 adds movement and optional synchronized native audio while keeping your subject, wardrobe, and composition consistent. The output aspect ratio follows your input image.
| Advantage | What it means for you |
|---|---|
| Single-image animation | Turn one still into motion — no keyframing or masking — while the subject stays consistent. |
| Native audio in one pass | Generate synchronized speech, sound effects, and music with the clip, or turn audio off for silent video. |
| Up to 30-second clips | Extend a single shot with steadier quality than short takes stitched together. |
| Ratio follows your image | Output keeps the framing of your source still, so product and portrait shots stay composed as shot. |
The table below lists the controls exposed by the Seedance 2.5 Image to Video 720p tool on this page.
| Parameter | Required | Type | Default | Range / Options | How to choose |
|---|---|---|---|---|---|
prompt* | Yes (*) | String | Example prompt | Chinese ~≤500 characters or English ~≤1000 words recommended | Describe how the subject and camera should move, plus any audio. |
image* | Yes (*) | String (image URL) | Example image | jpeg, png, webp, bmp, tiff, gif | The still to animate; it anchors identity and sets the output aspect ratio. |
duration | No | Integer | 5 | 4–30 seconds, in 1-second steps | Short clips for a single action; longer only when the prompt defines a clear beginning, development, and ending. |
generate_audio | No | Boolean | true | true / false | Leave on for synchronized speech, effects, and music; turn off for silent video. |
\* Required field. This page has no aspect-ratio control (the output ratio follows the input image) and no multi-reference input.
Seedance 2.5 Image to Video 720p is billed per second of generated video at a fixed 720p:
| Duration | Price at $0.35/s |
|---|---|
| 5s | $1.75 |
| 10s | $3.50 |
| 15s | $5.25 |
| 30s | $10.50 |
For batches of multiple outputs, calculate the total as duration × $0.35 × output count.
Improved prompt example
> The lion slowly lifts its head and opens its mouth in a powerful roar, mane rippling in the warm wind, dust and tiny insects drifting through golden backlight, subtle slow-motion, cinematic wildlife shot with shallow depth of field and natural savanna ambience.
Generate premium videos with synced audio from text using OpenAI Sora 2 Pro.
LTX 2.5 Fast text-to-video with synced AV drafts up to 4K
Wan 3.0 Reference To Video builds clips from image, video, audio refs
High-speed text-to-motion generator for cinematic storytelling use.
Turn reference images and a prompt into short video with synced audio.
Create fluid, expressive animations with multi-shot storytelling features.
Yes. Seedance 2.5 Image to Video 720p is available on RunComfy for browser testing and API integration.
It animates a single still image into a short cinematic clip at 720p, adding motion, camera moves, and optional native audio. It suits product shots brought to life, character animation from stills, and social or ad variants where the subject must stay consistent.
It requires a prompt and one input image. Duration is a whole number of seconds from 4 to 30 (default 5), and output is fixed at 720p. There is no aspect-ratio control — the output aspect ratio follows your input image.
No. This is a single-image path, and the output ratio follows the image. Its API accepts only prompt, image, duration, and generate_audio. If you need multiple references or an aspect-ratio control, use the Seedance 2.5 reference-to-video page.
Yes. generate_audio is on by default, so the model can output synchronized speech, effects, and music. Turn it off when you only need silent video.
Both take a still plus a motion prompt; the 720p page outputs at 720p ($0.35/s), while the 480p page targets a different price and sharpness. For cheaper, faster drafts, use the 480p image-to-video page.
Yes. Prototype in the RunComfy model UI, then call the same template through the API with matching fields (prompt, image, duration, generate_audio). Generations consume credits on both paths.
It is billed at $0.35 per second of generated video. Longer durations scale linearly with the length you select.
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.
