Can I start without an uploaded image?

Yes. Choose text-to-video and describe your shot. Use image-to-video or video-to-video when a visual reference is part of your brief.

How should I prepare several reference images?

Stay within the nine-image interface limit and the 30 MB limit per image. Explain each reference’s role in the prompt, and check that all intended files have finished uploading.

Will Mini return the last frame separately?

No. The Mini request omits the returned-last-frame option. Sound can be configured separately; review the actual video rather than assuming it will match a reference exactly.

Can I start without an uploaded image?

Yes. Choose text-to-video and describe your shot. Use image-to-video or video-to-video when a visual reference is part of your brief.

How should I prepare several reference images?

Stay within the nine-image interface limit and the 30 MB limit per image. Explain each reference’s role in the prompt, and check that all intended files have finished uploading.

Will Mini return the last frame separately?

No. The Mini request omits the returned-last-frame option. Sound can be configured separately; review the actual video rather than assuming it will match a reference exactly.

Seedance 2 Mini video workflows

Shape a short video with Seedance 2 Mini

Start with an idea, a still image or a reference clip in the GPT Image 2.5 video generator. Select Seedance 2 Mini explicitly, describe the action and camera movement, then choose the inputs that fit your scene. This page explains the controls available for Mini without borrowing promises from other Seedance variants.

About

About this workflow

For a product reveal, a character gesture or a short transition, write one clear shot before adding references. Name the subject, setting and movement in that order. GPT Image 2.5 offers text-to-video, image-to-video and video-to-video for Seedance 2 Mini; the chosen mode determines which upload controls you use. Check the selected model again when switching between workflows.

Plan the shot before generating

A practical guide to inputs, framing and sound for this specific variant.

Core Features Overview

Choose the starting material

For text input, describe a single camera setup and a visible action. With image or video input, explain which appearance should remain recognizable and which motion you want changed. Avoid filling the prompt with unrelated scenes; a short clip benefits from a clear beginning and end.

Fit the clip to its destination

Available aspect ratios include 16:9, 4:3, 1:1, 3:4, 9:16 and 21:9, plus adaptive. Match the ratio to the placement you have in mind. Neither a resolution choice nor the Mini name guarantees a particular visual result or processing time.

Prepare references deliberately

Image uploads have a 30 MB limit, video files 50 MB and audio files 15 MB. Images accept JPEG, PNG, WebP and GIF; videos accept MP4, MOV and MKV; audio accepts MP3 and WAV. Recheck the preview and upload status after changing input modes.

Decide how sound should work

Mini does not request a separate returned last-frame image. If you need a still from the finished video, plan a separate review or editing step. Listen for unintended audio and check the opening and closing frames before using the result in a larger sequence.

Questions about Mini

Shape a short video with Seedance 2 Mini FAQ

No. Select Seedance 2 Mini by name in GPT Image 2.5. This page describes Mini’s current controls; settings and capabilities of the other variants should not be assumed to apply.

Explore More AI Video Models

Veo 3.1

New

Veo 3.1 represents Google DeepMind's most advanced AI video generation technology, featuring groundbreaking native audio generation that creates synchronized sound effects, dialogue, and environmental audio alongside video content.

Try now

Wan 2.6

New

Wan 2.6 is Alibaba's video generation model delivering high-quality videos with diverse style support, smooth motion, and cinematic output from text prompts and reference images.

Try now

Sora 2

Sora 2 is OpenAI's flagship video generation model capable of producing high-quality videos from both text descriptions and image inputs. It understands complex scene compositions, character interactions, camera movements, and real-world physics to deliver cinematic results. Sora 2 represents a major leap in AI video generation with improved temporal consistency, longer duration support, and more faithful prompt interpretation.

Try now

Vidu Q4 Video Generator

New

Vidu Q4 is a video model developed by ShengShu Technology. Image-to-video turns one image into a 3–16 second clip, while reference-to-video combines 1–15 images into a 3–16 second clip. Optional audio and up to three voice references let you explore scenes in which appearance, movement and sound work together.

Try now

Kling 2.6

Kling 2.6 is Kuaishou's latest AI video generation model, recognized for its exceptional motion quality and cinematic output. Built on advanced spatiotemporal modeling, Kling 2.6 produces videos with fluid character movement, dynamic camera transitions, and rich visual detail. It supports both text-to-video and image-to-video generation, making it a versatile tool for creators seeking professional-quality AI video content.

Try now

Seedance 2.0

New

Seedance 2.0 is ByteDance's most advanced AI video generation model, unveiled in February 2026. It adopts a unified multimodal audio-video joint generation architecture supporting 4 input modalities simultaneously — text, up to 9 images, up to 3 video clips, and up to 3 audio tracks. The ground-breaking @-reference system lets you tag specific elements in your prompt and bind them to uploaded references for granular control over camera movement, character appearance, audio rhythm, and visual style. Outputs reach up to 2K resolution with native synchronized audio including multilingual lip-sync, sound effects, and background music.

Try now

Open Seedance 2 Mini

Choose Mini in the video generator, set the shot and review the active inputs before generating.

Open Seedance 2 Mini

+1k