Seedream 5.5 is live on Atlas Cloud — native transparent PNG & 80+ round editing
Inicio
Explorar
Black Forest Labs
Flux.2 Image Models
black-forest-labs/flux-3/image-to-video
Atlas Cloud Estudio de Creación IADesata tu potencial como director.Empezar a crear
BLACKFORESTLABS FLUX 3 Image-to-Video
Imagen a Video

BLACKFORESTLABS FLUX 3 Image-to-Video API by Black Forest Labs

black-forest-labs/flux-3/image-to-video
Image-to-video

Generate a video that starts from an input image using FLUX 3.

Comparar modelos

BLACKFORESTLABS FLUX 3 Image-to-Video ha sido desarrollado por Black Forest Labs. Atlas Cloud (operado por Atlas Cloud AI LLC) proporciona acceso al modelo, pero no es su propietario. Todas las marcas comerciales pertenecen a sus respectivos titulares.

FLUX 3 Image-to-Video

FLUX 3 Image-to-Video brings a static image to life. Provide a starting image and a text prompt describing the motion, and the model generates a smooth cinematic clip that begins exactly on your image — with optional native audio.

Why Choose This?

  • Image-driven generation Animate any photo, illustration, or render with natural, controllable motion.

  • Native audio generation Produce video and synchronized audio in a single request.

  • Explicit duration required Duration must be set explicitly to validate keyframe positions.

  • Auto aspect ratio Use auto to match the input image's proportions, or specify any ratio.

  • High resolution output Generate videos in 720p or 1080p.

Parameters

ParameterRequiredDescription
image_urlYesURL of the image the video starts from (PNG, JPEG, or WebP)
promptNoText description of the desired motion and action
aspect_ratioNoAspect ratio of the generated video. Default: auto. Options: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16
resolutionNoVideo resolution. Default: 720p. Options: 720p, 1080p
durationNoDuration in seconds. Default: 5. Options: 5–20. Cannot be auto — required to validate keyframe positions
generate_audioNoWhether to generate audio. Default: true
safety_toleranceNoSafety level 0 (strictest) to 4 (most permissive). Default: 2
seedNoRandom seed for reproducibility

How to Use

  1. Provide your starting image — the video will begin from this frame.
  2. Write your prompt — describe the motion, camera movement, and action.
  3. Choose resolution — 1080p for final output, 720p for faster iteration.
  4. Set aspect ratio — use auto to match the image, or specify a ratio.
  5. Set duration — use auto or specify a value (5–20 seconds).
  6. Run — submit and download your video.

Pricing

Billed per second of generated video, by resolution:

ResolutionCost per second
1080p$0.319
720p$0.187

Best Use Cases

  • Photo Animation — Bring portraits, landscapes, and product images to life.
  • Marketing & Ads — Turn product photos into dynamic promotional videos.
  • Storytelling — Animate illustrations and artwork for narratives.
  • Creative Exploration — Experiment with motion starting from any visual.

Pro Tips

  • Be specific about movement: "slowly zooms in", "pans left", "subject walks toward camera".
  • Use aspect_ratio: "auto" to preserve the original image's proportions.
  • Describe ambient sounds in your prompt for richer audio when generate_audio: true.
  • Use high-quality, well-lit images for best video results.

Notes

  • image_url is the only required field; prompt is optional but improves motion control.
  • Accepted image formats: PNG, JPEG, WebP.
  • Generation is asynchronous — submit, then poll for the finished video.

Explorar Modelos Similares

Una sola API para toda la IA multimedia.

Explorar Todos los Modelos