Black Forest Labs/flux-3-max-image-to-video/Released Oct 2026

FLUX 3 Max: Image to Video

Low-latency image-to-video with end frame

Commercial use

Video

About FLUX 3 Max: Image to Video

FLUX 3 Max (Image to Video) animates a starting image into a video with native audio, optionally ending on a second image. FLUX 3 Max is a post-trained variant of FLUX 3 Video, built by fal with Black Forest Labs and tuned for stronger prompt adherence, better visual quality and much lower latency.

It generates 5 to 20 second clips at 720p or 1080p with synchronized audio, in aspect ratios from 21:9 to 9:16. A reasoning level controls how much the model expands the prompt before generating: high for closer prompt adherence, low for faster turnaround.

See what this model can do

A handful of real prompts and their outputs.

Drawing to Life

Fridge Dragon

"Animates a crayon drawing from a single still while keeping its waxy crayon look."

Start and End Frame

Blank Canvas to Poppies

"Starts on a blank canvas and ends on the finished painting given as the last frame."

Start and End Frame

Peony Unfurls

"A bud and a full bloom set the first and last frames, and the bloom opens in between."

Product Moment

Shaken Snow Globe

"Hands, glass and swirling snow animated from one macro still, with a music-box melody."

Portrait

Net Mender

"A still portrait becomes a quiet scene with natural hands, a smile and harbor sound."

Toy Animation

Wind-Up Rabbit

"Clockwork motion with tinny clinks and a winding ratchet in the generated audio."

Ready to build with FLUX 3 Max: Image to Video?

Try FLUX 3 Max: Image to Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.

curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "flux-3-max-image-to-video",
  "prompt": "The baker slides the long wooden peel into the glowing wood-fired oven, lifts out a golden sourdough loaf and smiles as steam rises from the crust. Slow push-in, warm firelight. Audio: crackling fire, the scrape of the peel, quiet morning birdsong.",
  "input_image": "https://d32o0jiwwqtsvz.cloudfront.net/models/flux-3-video/input_baker.jpg",
  "aspect_ratio": "auto",
  "resolution": "720p",
  "duration": 5,
  "generate_audio": true,
  "reasoning_level": "high"
}'

Request parameters

Every field FLUX 3 Max: Image to Video accepts in the request body. See the API reference for response formats.

POSThttps://hub.oxen.ai/api/ai/videos/generate

Field	Type	Required	Default	Description
`prompt`	`string`	Yes	—	Describe how the video unfolds from the image, including any sound.
`input_image`	`string` uri	Yes	—	First frame of the video. PNG, JPEG or WebP. With aspect ratio on auto, the video follows this image's shape.
`tail_image_url`	`string` uri · nullable	No	—	Optional last frame of the video. PNG, JPEG or WebP.
`aspect_ratio`	`string`	No	`"auto"`	`auto21:92:116:94:31:13:49:16`
`resolution`	`string`	No	`"720p"`	`720p1080p`
`duration`	`integer`	No	`5`	Length of the generated video. Range: 5 – 20
`generate_audio`	`boolean`	No	`true`	Generate synchronized audio for the video.
`reasoning_level`	`string`	No	`"high"`	How much effort the model spends expanding the prompt before generating. High follows the prompt more closely; low returns faster. `lowhigh`
`seed`	`integer` nullable	No	—	Random seed. A random seed is selected when omitted.

Model JSON Video generation reference Async queue Models endpoint