FLUX.3 Video
Black Forest Labs
- Released
- August 4, 2026
- Data date
- September 24, 2026
- Maximum resolution
- Maximum duration
- Native audio
- Price
- Per generated minute
FLUX.3 Video is Black Forest Labs’ generally available model for text and image inputs. It generates up to 20 seconds with native audio, supports keyframes, and outputs 720p natively; higher resolutions come through upscaling.
Multiple scenes and camera angles, dialogue, sound effects, and ambient sound can be generated in one clip. For continuation, FLUX.3 Video accepts up to 4 seconds of existing video with audio and carries motion, camera behavior, and sound across the seam.
Text-to-video and image-to-video remain separate. Their input tasks differ, so they do not receive a combined overall rank.
Methodology and source
Benchmark sources at a glance
Each evaluator measures different capabilities under its own conditions. Test series, composite indices and their components stay separate. The detailed results below retain their scales, configurations and source dates.
No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.
Coverage is not a quality ranking. Overlapping tests and multiple settings do not count as independent experiments. Vendor claims, historical and disputed results are excluded from this overview and remain labelled in the detailed evidence.
Published benchmarks
LMArena Text to Video
Elo ratings summarize pairwise comparisons within this leaderboard. They are not percentages. The scale does not express absolute quality or linear gaps between models.
higher is betterAs of September 22, 2026Scale: 0 Elo - 1,516 Elo
Methodology and context
- Metric
- elo-rating
- Scale
- No upper bound is documented. The chart spans the recorded values and zero.
- Participants
- 22
- Sample
- 1,302
LMArena Image to Video
Elo ratings summarize pairwise comparisons within this leaderboard. They are not percentages. The scale does not express absolute quality or linear gaps between models.
higher is betterAs of September 22, 2026Scale: 0 Elo - 1,495 Elo
Methodology and context
- Metric
- elo-rating
- Scale
- No upper bound is documented. The chart spans the recorded values and zero.
- Participants
- 21
- Sample
- 37,042
Recorded measurement details
LMArena Text to Video: LMArena Text to Video (Show measurement, test conditions, and source)
- Source value
- 1493
- Score
- 1493
- Metric
- elo-rating
- Unit
- Elo
- Task
- lmarena-text-to-video
- Task label
- LMArena Text to Video
- Direction
- Higher is better
- Source rank
- 3
- Sample
- 1302
- Lower confidence bound
- 1476
- Upper confidence bound
- 1510
- Retrieved at
- 2026-09-22
LMArena Image to Video: LMArena Image to Video (Show measurement, test conditions, and source)
- Source value
- 1449
- Score
- 1449
- Metric
- elo-rating
- Unit
- Elo
- Task
- lmarena-image-to-video
- Task label
- LMArena Image to Video
- Direction
- Higher is better
- Source rank
- 9
- Sample
- 37042
- Lower confidence bound
- 1444
- Upper confidence bound
- 1454
- Retrieved at
- 2026-09-22
Video sample from our test
This video exists as a documented run for the exact model version. Playback is muted.
Motion and physical consistency
This sample tests Anatomy, object consistency, camera tracking, rain, and reflections.
Prompt and settings
Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.
Generated through fal.ai with model blackforestlabs/flux-3/text-to-video. Archived settings were 16:9, one request, first output, requested 5 s, seed 2955816195, request {"prompt":"Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.","aspect_ratio":"16:9","resolution":"720p","duration":5,"generate_audio":false}, configured price estimate $0.85.
Popularity
29.9 / 100
Specifications and access
| Specification | Value and source |
|---|---|
| Weights | ProprietarySource |
| Access | API, WebSource |
| Maximum resolution | 4K (Upscaling)Source |
| Maximum duration | 20 sSource |
| Native audio | YesSource |
| Resolution | 720p native; 1080p, 1440p and 4K via upscalingSource |
| Input modes | Text-to-video, image-to-video, and keyframesSource |
| Video continuation | Up to 4 seconds of existing video and audio as inputSource |
| Scenes | Multiple scenes and camera angles within one clipSource |
| Audio | Generates dialogue, sound effects, and ambient sound nativelySource |
Compare this model
Show all comparisons (23)
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | Black Forest Labs (retrieved September 24, 2026) · Black Forest Labs FLUX 3 Video announcement · Editorial description reviewed October 2, 2026 |
| Additional source | Video pricing (retrieved September 24, 2026) · Black Forest Labs video pricing · Editorial description reviewed October 2, 2026 |
| Additional source | fal.ai |
| Additional source | LMArena (retrieved September 22, 2026) |
| Additional source | LMArena (retrieved September 22, 2026) |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |