FLUX 3 Max (Image-to-Video)

FLUX 3 Max animates your picture into a 5 to 20 second clip with native sound, at 720p or 1080p, with an optional last frame to end on.

FLUX 3 Max (Image-to-Video) is fal's post-trained variant of Black Forest Labs' FLUX 3 Video, started from your picture: the clip opens on it and unfolds as the prompt says, 5 to 20 seconds with native sound. Give it a second picture as end_image_url and the clip ends on that frame.

Use it for product and character shots that come alive, ads and transitions between two frames. aspect_ratio auto follows the picture. reasoning_level high (the default) lets the model think the prompt through and expand it; low is faster. 1080p is upscaled from the 720p generation.

Inputs: image (a link or an upload: PNG, JPEG or WebP), prompt, end_image_url (optional), duration (5-20 seconds, 5 by default), resolution (720p or 1080p), aspect_ratio, generate_audio, reasoning_level and seed. Outputs: video and seed.

Price per second of video: $0.17 at 720p and $0.29 at 1080p (the list price from 2026-11-23). The default 5-second 720p clip costs $0.85, 20 seconds at 1080p $5.80. It starts from a picture: for text alone, use FLUX 3 Max (Text-to-Video). It does not render 2K or 4K and does not edit or extend an existing video.

Price: From $0.17 per second of duration, depending on resolution. One run with default settings costs $0.85.

Run FLUX 3 Max (Image-to-Video) via API

curl -X POST https://api.flymy.ai/api/v1/flymyai/flux-3-max-image-to-video/predict \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image":"https://flymy.ai/img/models/bytedance-seedance-2-5-image-to-video.jpg","prompt":"Slowly move the camera closer to the lake, preserve its composition","duration":5,"resolution":"720p"}'

API documentation · Create a free account · Pricing

Related models