Image to Video API
Build the same workflow into your product: upload one source image, provide a motion prompt and selected model, estimate credits, and retrieve the generated video through its task.
Read the Image to Video API referenceTurn one photo or illustration into motion with six advanced AI video models in one place: Wan 3.0, Seedance 2.0 Mini, Seedance 2.0 Fast, Seedance 2.0, Seedance 2.5, and MiniMax H3. Eligible new users start with 3,000 free trial credits. Choose a model and motion prompt, then check its credit estimate before generating.
Choose a model, upload one source image, and describe the motion. Duration, clarity, and aspect ratio follow the selected model's supported settings.
| Model | Credit 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.
No video yet. Generate one to see it here.
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.
Build the same workflow into your product: upload one source image, provide a motion prompt and selected model, estimate credits, and retrieve the generated video through its task.
Read the Image to Video API referenceUse the corresponding medux_video_generate_image_to_video tool from a connected AI agent. The reference covers source image uploads, model selection, credit estimates, and task retrieval.
Open the Image to Video MCP toolChoose one clear JPG, PNG, or WebP image. This can be a product photo, landscape, illustration, or another image suited to the selected model.
Select one of the six models and write what should happen in the shot. Choose a supported duration, clarity, and aspect ratio. Use the sample prompt as a starting point.
Review the account-specific model rate and estimated total. Generate once, follow progress here or in Account Results, then preview and download the completed video.
Bring one still image into motion, compare six advanced model choices, and start with free trial credits. Explore these video examples from the Medux home gallery, then make a clip of your own.
Start with a photo, drawing, or product image. Describe the subject's movement and camera direction, then let the selected AI video model build a short clip from that single frame. This animated football scene shows how much energy a clear motion idea can add.
Try the AI video generatorChoose Wan 3.0, Seedance 2.0 Mini, Seedance 2.0 Fast, Seedance 2.0, Seedance 2.5, or MiniMax H3. Each model exposes its supported duration, clarity, and aspect ratio. Match the source image to the model's guidance: for example, the current Seedance catalog excludes real human faces.
Try the AI video generatorEligible new users receive 3,000 free trial credits. Try a short animated illustration, compare the current model rates, and review the estimated total before generating. Every finished video uses credits, so you can choose a model and settings that fit your balance.
Try the AI video generatorTurn a product image into a short reveal or promotional shot by describing the movement, lighting, and camera behavior.
Add movement to artwork, stylized characters, and illustrated worlds while guiding the shot with a written prompt.
Bring scenery to life with moving clouds, rippling water, swaying foliage, or another detail already present in your image.
Focus on what changes over time: which subject moves, how fast it moves, and whether the camera should remain still. Start with one simple action.
The current catalog states that the four Seedance models do not support real human faces. Check the model summary and choose an image appropriate to its capabilities.
Credit rates and supported output options differ by model. Check the live total whenever you change duration, clarity, aspect ratio, or model.
Every Medux tool has open examples on GitHub: copy a prompt for Claude or Codex, or start from a working API request.
A ready-to-paste prompt and approval checklist for running medux_video_generate_image_to_video from Claude.
View on GitHubThe same workflow for Codex: expected tool call, arguments to review and how to verify the result.
View on GitHubRequest fields, curl, Python and JavaScript samples, and response handling for this endpoint.
View on GitHubEligible new accounts receive 3,000 trial credits. Upload one image, choose a model, and explore unlimited motion ideas online. Review the estimated credits before submitting.
Choose Wan 3.0, Seedance 2.0 Mini, Seedance 2.0 Fast, Seedance 2.0, Seedance 2.5, or MiniMax H3. The model menu shows these six options and loads supported settings from the same catalog as Playground.
Sign in to see your current rate for each model. For per-second billing, credits equal the rate multiplied by video duration. The total estimate uses your selected model, duration, clarity, and aspect ratio. The completed task shows the final credit cost.
Upload exactly one source image and enter a motion prompt. To define both the beginning and ending of a video, use the separate First & Last Frame to Video Workshop.
The menus display the selected model's current supported settings. Seedance 2.5 currently offers selected durations up to 30 seconds; the other five models offer selected durations up to 15 seconds. Resolution options vary by model and account availability.
Read the selected model's guidance before submitting a portrait. The current catalog states that the Seedance models do not support real human faces. For an audio-driven speaking portrait, explore the Lip Sync Workshop.
Once Medux returns a task ID, processing continues on the server. Return with the same account and browser to restore your latest task, or find it in Account Results.