pikaframes
Animate between two images with smooth keyframe transitions using Pikaframes.
Seedance 2.0 Mini is ByteDance's leaner, lower-latency entry in the Seedance line, tuned to produce finished video quickly and at a low price point. This page runs its image-to-video mode: you supply a still frame, describe the motion you want, and receive a short clip that animates from that image.
The focus here is shot-level storytelling rather than a single drifting frame. The model builds a brief narrative sequence with directed camera moves while holding the subject's identity steady from the first frame onward. Audio is generated together with the picture, so ambience and effects land in time with the action instead of being added later.
An optional end frame sharpens control over how a clip resolves. Supplying a last image steers the closing moment or the direction of a continuation, which is useful when you already know where a shot should land.
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 |
|---|---|---|---|---|---|
| image* | Yes (*) | string | — | image URL | Start frame that guides the first frame and look. |
| prompt* | Yes (*) | string | — | — | Motion, action, camera movement, and mood to add. |
| last_image | No | string | — | image URL | Optional end frame for the clip's finish or continuation. |
| 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 |
Animate between two images with smooth keyframe transitions using Pikaframes.
Efficient video transformation with cinematic motion and design precision.
Transform reference clips with cinematic fidelity, refined motion, and seamless style control for creative professionals.
Transform visuals into smooth 4K motion clips with sync audio and rapid rendering.
Generate native 4K cinematic text-to-video with synchronized dialogue and consistent characters.
Realistic motion, dynamic camerawork, and improved physics.
Seedance 2.0 Mini Image To Video is ByteDance's fast, low-cost model that animates a single start image into a short cinematic clip guided by a text prompt. It is built for adding directed motion, camera movement, and synchronized native audio to a still frame while keeping the subject recognizable. Typical uses include photo-to-motion clips, social spots, and product hero shots.
The model treats your uploaded image as the first frame and animates outward from it, so the main subject's appearance stays anchored to what you provided. Because it builds a brief multi-shot sequence with directed camera moves rather than a single drifting pan, the subject reads consistently from start to finish. Clear, well-framed start images give the steadiest results.
Yes. Native audio is generated together with the picture in the same pass, so ambience and effects line up with the on-screen action instead of being added afterward. Audio is controlled by the generate_audio switch, which is on by default. Turn it off when you only need silent footage.
You can output 480p, 720p, 1080p, or 4K, with 720p as the default tier. Durations run from 4 to 15 seconds, defaulting to 5 seconds. Use 480p for quick tests and reserve 1080p or 4K for final delivery.
Yes. Alongside the required start image, you can supply an optional last_image to steer the closing frame or the direction of a continuation. This is helpful when you already know where the shot should land. Leave it empty to let the model resolve the motion on its own.
You provide a start image, a text prompt, and optional settings for aspect ratio (16:9, 9:16, 4:3, 3:4, 1:1, or 21:9), resolution, and duration. Aspect ratio adapts to your input image when left unset. For exact file size and format limits, check the current RunComfy parameter panel before generating.
Yes. You can prototype Seedance 2.0 Mini Image To Video in the RunComfy model UI and then call the same model via the RunComfy HTTP API using identical parameters. This lets you move from a tested setup in the browser to production or automation without rebuilding your configuration or hosting the model yourself.
Pricing is time-based and scales with resolution: $0.06 per second at 480p, $0.12 at 720p, $0.30 at 1080p, and $0.60 at 4K. A 5-second 720p clip therefore costs about $0.60, while a 5-second 4K clip is about $3.00. Generations draw from your RunComfy credits, and new users typically start with a free trial balance.
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.
