What does the output look like?
We haven’t published an output sample for FLUX.3 Max yet.
Visit the developer’s model pageWhat can FLUX.3 Max do?
Black Forest Labs' post-trained FLUX.3 with stronger prompt adherence and visual quality for text, image, start/end frame, and timed keyframe generation with native audio
- Prompt-faithful cinematic clips with native audio
- Realistic spoken performances
- Sequencing up to 10 timed image anchors in one clip
- Inputs
- Text, Image
- Durations
- 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s, 17s, 18s, 19s, 20s
- Aspect ratios
- auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16
- Output options
- 720p, 1080p
- Typical generation time
- About 10 minutes
- 1080p uses more credits than 720p, especially on longer clips.
- The model expands each prompt before generating, so state the essential action, dialogue, and sound directly.
How much does FLUX.3 Max cost?
Base estimate
$0.17–$0.29 USD / second
1.7–2.9 credits / second
Estimated dollar cost uses the Solo monthly plan at $0.10 USD per credit. Your cost per credit depends on your plan.
Example: a 5-second clip
$0.85–$1.45 USD(8.5–14.5 credits)
Reference media and video editing may add to this estimate.
Video cost scales with duration. Resolution, sound, reference media, and generation mode can affect the final charge. Check the total shown in Starpop before generating.
How to use FLUX.3 Max
- Click “Create with FLUX.3 Max” and sign in or create an account. After setup, Starpop opens a new video workspace tab with the model selected.
- Describe the action, dialogue, and sound directly, and add a start image, start and end frames, or up to 10 timed keyframes when the clip must hit specific images.
- Choose the resolution, aspect ratio, and duration, then generate with native audio.
- Review the credit estimate and generate. Check the result in your workspace, then download it or adjust your inputs to try again.