MCP / Models / Image to video
FLUX 3 Video Image to Video MCP: stills to clips with sound
Black Forest Labs FLUX 3 Video builds a 5 to 20 second clip on one to ten keyframe images: one starts it, two frame it, more storyboard it. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use FLUX 3 Video Image to Video in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/flux-3-video-i2v.md. Help me connect the FlyMy.AI MCP to this assistant, then run FLUX 3 Video Image to Video (flymyai/flux-3-video-i2v) for this task: Animate the photo I attach with FLUX 3 Video Image to Video: the camera slowly pushes in while the hair moves in the wind.
What FLUX 3 Video Image to Video does
Send prompt and keyframes: one to ten image links or uploads that become real frames of the clip. One image starts the video, two are its first and last frame, and three to ten are spread in between, so give a duration then; pairs of a time in seconds and a link pin each picture to a moment of the clip. duration is 5 to 20 whole seconds, resolution is hd (the default), fhd, qhd or uhd, and generate_audio is on by default, so speech, effects and ambience come with the picture. draft true makes a quick, cheaper preview at hd only. It does not start from text alone: FLUX 3 Video Text to Video does.
FLUX 3 Video Image to Video inputs
Every input of flymyai/flux-3-video-i2v as its live schema lists them. Returns video (array).
| Input | Type, values and default |
|---|---|
# prompt | string required What happens: scene, camera, lighting and sound; put spoken lines in quotes |
# keyframes | string required The images the video is built on, 1-10 links (a JSON array or one link) or uploads: one starts the video, two are its first and last frame, more are spread in between (then give a duration); or [seconds, link] pairs such as [[0, link], [4.5, link]] that pin each picture to a time |
# duration | integer optional Allowed: 5 to 20 Default: 5 Length in whole seconds, 5-20; billed per second of video made |
# resolution | string optional Allowed: hd, fhd, qhd, uhd Default: hd Billed per second of video: hd $0.15, fhd $0.24, qhd $0.28, uhd $0.41. fhd, qhd and uhd are upscales of the same footage |
# aspect_ratio | string optional Allowed: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21 Default: auto Shape of the video; auto follows the prompt and the pictures |
# generate_audio | boolean optional Default: true Speech, sound effects and ambience with the video; no extra charge |
# draft | boolean optional Default: false A quick preview, hd only, at $0.06 per second instead of $0.15; a full render of the same prompt is a new generation and can differ |
# safety_tolerance | integer optional Allowed: 0 to 4 Default: 2 Content filter: 0 strictest to 4 most permissive |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/flux-3-video-i2vflymyai/flux-3-video-i2vflymyai/flux-3-video-i2vFLUX 3 Video Image to Video price
From $0.15 per second of duration, depending on resolution and draft; whole seconds of video, 5-20 s, sound free; a draft preview (hd only) $0.06 per second. A run at the default settings costs $0.75. A run costs $0.75 to $8.20, depending on resolution and duration and draft. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
| Setting | Price |
|---|---|
| resolution hd | $0.15 per second |
| resolution fhd | $0.24 per second |
| resolution qhd | $0.28 per second |
| resolution uhd | $0.41 per second |
Call FLUX 3 Video Image to Video from code
The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.
From an agent, through the MCP
The agent calls get_model_schema, then run_model with:
{
"endpoint_id": "flymyai/flux-3-video-i2v",
"input": {
"prompt": "Slow camera push-in with gentle, natural motion in the scene",
"keyframes": [
"https://example.com/first.jpg",
"https://example.com/last.jpg"
]
}
}From your code, over HTTP
Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/flux-3-video-i2v/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/flux-3-video-i2v/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=Slow camera push-in with gentle, natural motion in the scene' \
-F 'keyframes=["https://example.com/first.jpg", "https://example.com/last.jpg"]'Questions about FLUX 3 Video Image to Video
Do I need a Black Forest Labs API key for FLUX 3 Video Image to Video?
No. FLUX 3 Video Image to Video runs on FlyMy.AI's account, so you need no Black Forest Labs key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does FLUX 3 Video Image to Video cost?
From $0.15 per second of duration, depending on resolution and draft; whole seconds of video, 5-20 s, sound free; a draft preview (hd only) $0.06 per second. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use FLUX 3 Video Image to Video in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Animate the photo I attach with FLUX 3 Video Image to Video: the camera slowly pushes in while the hair moves in the wind." Your agent reads the inputs with get_model_schema and runs flymyai/flux-3-video-i2v with run_model.
What does FLUX 3 Video Image to Video need as input?
FLUX 3 Video Image to Video requires prompt and keyframes; it also takes 6 optional inputs, each listed on this page with its allowed values and default.
Can I call FLUX 3 Video Image to Video from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/flux-3-video-i2v/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.





