sora-2/pro/image-to-video
Animate an image into a high quality video with OpenAI Sora 2 Pro.
Seedance 2.5 First & Last Frame 720p builds a believable transition between two keyframes at 720p. Provide a first frame and a last frame plus a prompt that describes how the shot should move between them; Seedance 2.5 generates the in-between motion with optional synchronized native audio. The output aspect ratio follows your input frames.
| Advantage | What it means for you |
|---|---|
| Keyframe-controlled motion | Both endpoint looks stay intact while the model fills the motion between them. |
| Native audio in one pass | Generate synchronized speech, effects, and music with the clip, or turn audio off for silent video. |
| Up to 30-second clips | Bridge two frames over a longer, steadier shot. |
| Ratio follows your frames | Output keeps the framing of your input images — no separate aspect-ratio setting to manage. |
The table below lists the controls exposed by the Seedance 2.5 First & Last Frame 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 shot should move between the two frames, plus any audio. |
first_frame* | Yes (*) | String (image URL) | Example image | jpeg, png, webp, bmp, tiff, gif | The opening frame; sets the starting look and output aspect ratio. |
last_frame* | Yes (*) | String (image URL) | Example image | jpeg, png, webp, bmp, tiff, gif | The closing frame; sets the ending look. |
duration | No | Integer | 5 | 4–30 seconds, in 1-second steps | Longer durations give the transition more room; keep it tight for quick bridges. |
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 frames) and no other reference inputs.
Seedance 2.5 First & Last Frame 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
> A cinematic golden-hour safari sequence: the camera glides across the sunlit savanna past a herd of grazing zebras and settles on a majestic lion resting on a rocky outcrop as the sun sinks toward the horizon, warm volumetric light, drifting dust, smooth continuous motion, natural wildlife ambience.
Animate an image into a high quality video with OpenAI Sora 2 Pro.
Film-quality Seedance 2.0 grade video generation with stunning visual fidelity and cinematic motion
Turn text prompts into high quality videos with Tencent Hunyuan Video.
Open-weights text-to-video with 480p/768p and native stereo audio.
Turn still visuals into motion-synced, high-detail video content with flexible control.
AI-powered tool for fast video-to-video backdrop swaps with pro-level precision.
It builds a 720p transition between a first frame and a last frame. It fits scene-to-scene bridges, product pack-to-use reveals, and before-to-after story beats.
It requires a prompt plus exactly two images (a first frame and a last frame). 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 frames.
No. The output ratio follows your input frames, and the page takes only the two frames. Its API accepts only prompt, first_frame, last_frame, duration, and generate_audio. For multi-reference 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 share the same first/last-frame path and 4–30-second window; this page outputs at 720p. For cheaper, faster drafts, use the 480p first-and-last-frame page.
Yes. Prototype in the RunComfy model UI, then call the same template through the API with matching fields (prompt, first_frame, last_frame, 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.
