Seedance 1.0 Pro Fast is a Pro variant in ByteDance's Seedance 1.0 series designed for rapid creation, suitable for turning text ideas or static images into short videos. doubao-seedance-1-0-pro-fast-251015 can be used for ad drafts, dynamic visual previews, and batch asset exploration, with a focus on validating motion, composition, and shot plans before moving on to editing and sound production.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
Input parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
Seedance 1.0 is natively designed for image- and text-driven video creation; the durations, aspect ratios, and controls above correspond to the calling scope of this model on this platform.
Pro Fast is suitable for exploring different expressions of the same idea in the early stages of production. Prompts can be organized around the subject, action, scene, lighting, and camera movement, such as comparing the visual difference between a fixed camera and a slow push-in. Use previews first to determine whether the action works, then adjust the aspect ratio and resolution for the selected option.
Image-to-video is suitable for creating from existing product images, illustrations, or scene designs. The first frame determines the video's starting visual, the last frame specifies the ending image, and text describes the action and camera changes in between. It focuses on the starting and ending conditions of the image, rather than a character reference mode that only extracts a person's identity and arbitrarily changes scenes.
With asynchronous tasks, generation can be embedded in asset management or creative tools without keeping the page waiting. Save the task_id after submission, use queries or callbacks to receive completed results, then retrieve the video link. When you need to preview the final composition, you can request the last-frame image to provide a basis for subsequent shot design.
Input a static product image and describe visual actions such as rising steam, swaying fabric, or slow camera movement to generate advertising drafts for discussion. Teams can compare lighting, background atmosphere, and the extent of motion, then pass selected clips to the editing workflow to add brand subtitles, music, and layouts required for formal placement.
Use character illustrations or scene concept art as the first frame, paired with concise action descriptions, to observe the pacing and composition after the image is brought to life. It is suitable for early validation of game cutscenes, animated mood films, and visual proposals; the deliverable is a short video clip for discussion, not a production file that automatically completes an entire animation.
Prepare multiple sets of text descriptions around the same theme, changing the subject's actions, shot size, or camera direction to generate candidate clips. Vertical format can be used for mobile content previews, while horizontal format is suitable for presentations or editing assets. Associate each creative version with a task number to facilitate filtering, downloading, and recording directions for subsequent revisions.
When the task focuses on quick previews, concept selection, and batch exploration of short clips, Pro Fast can be prioritized. It is a different invocation model from the standard 1.0 Pro, and is suitable for generating separately and comparing key actions and visual details. Lite is divided into T2V and I2V entry points; when text and first-and-last-frame workflows need to be used together, Pro Fast makes it easier to organize tasks consistently.
If delivery requires audio to be generated together with the video, choose Seedance 1.5 Pro or 2.x with audio support; if multimodal conditions such as character identity, reference video, or reference audio are needed, consider 2.0. For existing video editing, extension, or longer clips, 2.5 is suitable. Pro Fast is better suited to short videos driven by images and text, and does not cover the workflows of these later versions.
Provide text in content, and use first_frame to define the first frame for images; when an ending image is needed, combine it with last_frame to create a first-and-last-frame input.
Specify model=doubao-seedance-1-0-pro-fast-251015 for /seedance/videos; first test with duration=5, resolution=720p, and a clearly defined aspect ratio. The 1.0 series does not generate native audio.
First obtain the task_id asynchronously, then query /seedance/tasks or receive a callback; after completion, check the subject, action, and ending, and save the selected final video and task records. This model outputs no native audio, so add voiceover and music in post-production when sound is needed.
The first frame shows a camera on a table. The camera slowly circles to the right, highlighting reflections in the lens glass and the metal material, with the background unchanged and no text.
Validate the composition with a single camera movement, and compare 480p or 720p drafts; output speed cannot be guaranteed solely by the Fast name.
Pro Fast is designed for quick previews and batch creation, while the standard 1.0 Pro is a separate model. If the main goal is to screen creative ideas, you can start with Fast; if you have strict requirements for specific visual details, it is recommended to compare the results of both using the same assets and prompts before deciding on a production approach.
Add an image_url item to the content array, and place the image address in image_url.url; do not write image_url directly as a string. Use text to describe the action and set first_frame first; if an ending visual is needed, combine it with last_frame to form first-and-last-frame input; do not describe first-and-last-frame tasks as character multimodal reference tasks.
No, this model belongs to the 1.0 series that does not support generate_audio. You can generate the visuals first, then add voice-over, music, and sound effects during editing. If the task must generate sound at the same time, Seedance 1.5 Pro or a 2.x model that supports audio generation is more suitable.
The main purpose of Pro Fast is to generate short videos from text or images; it does not use reference-video editing and extension modes. For such tasks, choose Seedance 2.5 and provide video assets according to the editing or extension requirements; you cannot turn a generation task into an editing task simply by adding related fields to this model.
Submit model and content to /seedance/videos, and you can set async to true to obtain a task_id, then query the task result; you can also set callback_url to receive completion notifications. After completion, read the video link in data. Applications should distinguish between a submitted task and a generated video to avoid displaying a completed status prematurely.
Choose a development approach or application suited to this model and follow its setup guide.
↗Python SDK Integration Guide
SDK installation, authentication and examples↗TypeScript SDK Integration Guide
SDK installation, authentication and examples
↗
↗
↗Pricing
$0.0067–$0.12· per second
You pay$13,584for 142,800 credits · $0.0951 / credits46% OFF
You're billed in credits. Pick a top-up tier to see its per-credit rate — the larger the top-up, the cheaper each credit.
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs