Two images, one continuous video

Unlimited AI First & Last Frame Video Ideas — Try Free Online

Give your video a starting image and an ending image, then describe how the shot should connect them. Choose Seedance 2.0 Fast, Seedance 2.5, or MiniMax H3 and review the credit estimate before generating.

Start with 3,000 free trial credits for eligible tasks. Compare free credits and usage limits.

Try it now

Create a video between two frames

Open in Playground
01

Set up your video

Upload your images into the labeled slots below. First frame is the beginning; last frame is the ending. Duration and output options follow the selected model's current limits.

Model credit rates

ModelCredit rate

Rates are loaded for your account. For a rate billed per second, credits = rate × video duration. The total below is estimated by Medux for your selected model, duration, clarity, and aspect ratio.

Sign in to see the current credit cost for each model.

The latest task appears below. Processing continues on the server if you leave this page.

Result preview

Your result will appear here

No video yet. Generate one to see it here.

Build with Medux

From your browser to the API and MCP

Use the service behind this Workshop in your application or AI agent. Explore the API reference and its corresponding MCP tool before starting an integration.

First & Last Frame to Video API

Use the same service in your application. Upload two images, pass their IDs in first-frame then last-frame order, select a model and duration, estimate credits, and poll the generated task.

Read the First & Last Frame to Video API reference

Generate transitions through MCP

The corresponding medux_video_generate_first_last_frame_to_video tool lets a connected agent create a video between two uploaded frames. Review its current parameters and model availability in the API reference.

Open the First & Last Frame video MCP tool
One connected workflow

How it works

01

Upload the first and last frames

Choose two images with a coherent subject and setting. Put the starting image in First frame and the ending image in Last frame; their order determines the transition.

02

Choose a model and describe motion

Select Seedance 2.0 Fast, Seedance 2.5, or MiniMax H3. Write what should happen between the images, and choose a supported duration, clarity, and aspect ratio.

03

Review credits and generate

Check the model's billing rate and the estimated total for your settings. Submit once, follow the task here or in Account Results, then preview and download the completed video.

Creative control

Guide the beginning and ending of your shot

Product reveals

Connect two product compositions to explore a reveal, changing viewpoint, or visual transition.

Illustrated story moments

Turn two frames from the same illustrated world into a short scene with a clear beginning and ending.

Planned visual transitions

Control both endpoints while describing the motion between them, from an environmental change to a camera move.

Explore all Workshop tools or review the First & Last Frame to Video API for integration details.

Better results

Prepare frames that work together

Keep a shared visual language

Use frames with similar subjects, composition, and art style. A large change between unrelated images can make the transition harder to follow.

Match the model to your images

The current model catalog states that Seedance 2.0 Fast and Seedance 2.5 do not support real human faces. Read the selected model's summary before submitting.

Check duration and credits together

Longer durations can consume more credits. Review the live estimate whenever you change the model, duration, or output settings.

Build with Medux

Run this tool from your agent or code

Every Medux tool has open examples on GitHub: copy a prompt for Claude or Codex, or start from a working API request.

Claude MCP

Claude MCP example

A ready-to-paste prompt and approval checklist for running medux_video_generate_first_last_frame_to_video from Claude.

View on GitHub
REST API

API example

Request fields, curl, Python and JavaScript samples, and response handling for this endpoint.

View on GitHub
Prompts, workflows, and integrations

Make your next creative step clearer

All tutorials
Frequently asked questions

First & Last Frame video generation FAQ

Which models can I choose?

This Workshop offers Seedance 2.0 Fast, Seedance 2.5, and MiniMax H3. Each model's current settings and your account's availability are read from the same catalog used by Playground.

How are credits calculated?

Sign in to see the current credit rate for each model. For a model billed per video second, the cost follows its rate multiplied by duration. Medux estimates the total using your selected model and output settings before submission. The completed task shows its final credit cost.

What is the difference between the two frame slots?

First frame defines the beginning of the video; last frame defines the ending. Both images are required and are submitted in that order. The prompt describes the transition between them.

Which durations can I choose?

The current catalog offers 4–15 seconds for Seedance 2.0 Fast and MiniMax H3, and selected durations up to 30 seconds for Seedance 2.5. The duration menu displays the exact supported choices for the model you select.

Can I leave while the video is generating?

Yes. Once the service returns a task ID, processing continues on the server. Return with the same account and browser to restore your latest task, or find the task in Account Results.

Your next creation starts here

Connect two frames into your next video

Try it now