5–20s clips with native audio, up to 4K. FLUX 3 Video and FLUX 3 Max, by Black Forest Labs.
FLUX 3 video examples made in Renoise: each clip is a single generation at 720p. Hover the clips with sound to hear the native audio.
Pick any whole second from 5 to 20. This 15-second clip is one generation: a 10-second follow shot from the pier through the village, then a cut to the lighthouse reveal, with the waves and gulls carried across. No stitching of short clips.
Dialogue, sound effects and ambience come out with the picture. Write spoken lines in quotes and FLUX 3 voices them; Black Forest Labs says it handles many languages with lip sync. Audio is on by default, can be switched off, and costs the same either way.
Start from one still and FLUX 3 animates it, or give a first and a last frame and it fills the motion between them. Here a sunny lighthouse turns into the same cliff in a night storm. With frames, the output keeps the first frame’s aspect ratio.
FLUX 3 Max is FLUX 3 post-trained by fal with Black Forest Labs; fal says it follows prompts more closely and renders faster. It takes the same text and frame inputs at 720p or 1080p. This is the dialogue prompt above, run on Max.
FLUX 3 is Black Forest Labs’ multimodal AI model, announced on July 23, 2026 and trained on image, video and audio together. Its video model, FLUX 3 Video, opened on the BFL API on August 4, 2026: 5–20 second clips at 24 fps with native audio. FLUX 3 Max, a faster variant post-trained by fal, followed on October 19.
Renoise has FLUX 3 Video and FLUX 3 Max on one subscription with 30+ other models. Use them from the Videos page, switch models shot by shot in the Canvas, or generate from Claude Code, Codex or OpenClaw.
Need reference images or videos? Use Seedance 2.5. Need a 30-second shot? Use Kling 4.0.
Specs as available in Renoise, checked November 11, 2026.
Open Videos and choose FLUX 3 Video for 2K, 4K or a 9:21 frame, or FLUX 3 Max for its fal tuning at 720p or 1080p. Both cost credits per second of output.
For text to video, describe the scene, then the camera move, then the sound, in separate sentences, and put spoken lines in quotes. For image to video, drop in a first frame, or a first and last frame; the ratio then follows the first frame.
Choose 5–20 seconds, a ratio and 720p to 4K, and leave audio on or switch it off. Write “no subtitles” or “no music” when you don’t want them. Then refine the take or chain it with other shots in the Canvas.
From the FLUX 3 announcement to both video models in Renoise.
Black Forest Labs unveils FLUX 3, one model trained on image, video and audio, in early access.
FLUX 3 Video becomes generally available: 5–20s clips with native audio. Black Forest Labs calls it its first video model.
Black Forest Labs adds QHD and UHD tiers, upscaled from the same generation.
fal and Black Forest Labs release FLUX 3 Max, a post-trained variant tuned for prompt adherence and speed.
FLUX 3 Video, then FLUX 3 Max, join the Renoise model picker, API, CLI and MCP.
Sources: Black Forest Labs blog and release notes, fal, Renoise model list. Last updated
Same prompt, 720p, 8 seconds: FLUX 3 Video on the left, FLUX 3 Max on the right.
FLUX 3 Video offers 720p, 1080p and upscaled 2K and 4K. FLUX 3 Max stops at 1080p.
Both cover 21:9, 2:1, 16:9, 4:3, 1:1, 3:4 and 9:16 for text to video. The extra-tall 9:21 frame is FLUX 3 Video only.
At 720p, FLUX 3 Video is 30 credits per second and FLUX 3 Max 34. At 1080p it is 48 against 58.
fal post-trained FLUX 3 for closer prompt following and lower latency. Inputs, lengths and audio are the same, so run one prompt on both and keep the better take.
Four video models in the Renoise picker, compared on the limits Renoise exposes, not each vendor’s full spec sheet.
| In Renoise | FLUX 3 Max | Kling 4.0 | Seedance 2.5 | |
|---|---|---|---|---|
| Clip length | 5–20s | 5–20s | 3–30s | 4–30s |
| Max resolution | 4K (2K/4K upscaled) | 1080p | 4K (2K/4K upscaled) | 1080p |
| Inputs | Text, first + last frame | Text, first + last frame | Text, first + last frame | 30 images, 10 videos, 10 audio |
| Native audio | On, can be off | On, can be off | Always on | On |
| Credits · 5s at 720P | 150 | 170 | 130 | 160 |
| Best for | 4K and tall 9:21 frames | fal-tuned takes at 1080p | Shots up to 30s | Many references |
Renoise model list and credit estimates (checked 2026-11-11).
As of October 2026, 100,000+ creators in 170+ countries and regions use Renoise AI, an AI video, image and audio platform, to generate 300,000+ images and videos with 30+ models.
Source: Renoise internal data, March–October 2026. Figures are rounded down and updated quarterly. Last updated
Real feedback from creators who use Renoise AI to make videos, images and ads.
Renoise is pretty easy to use, with a clean and smooth interface. The results from Seedance 2.5 also feel noticeably smoother in action sequences.
Renoise Ai is a good tool for making ai videos and photos. it puts several Ai models in one place, so you don't need to use many different apps.
あまりAIツールを使ったりしたことなかったですが、キャラクターの固定や動画を続いて作成できて使いやすいです。これからどんどん進んでいくアップデートが楽しみです。
Renoise has been a great platform for AI creativity. The tools are easy to use, the experience is smooth, and it makes creating content more enjoyable and efficient. I really appreciate the work the team is doing and look forward to seeing more improvements. Highly recommended!
What I like about Renoise AI compared to other platforms: Fast generation speed: Slow generation takes up way too much time, but Renoise AI is surprisingly about 30% faster. Intuitive and user-friendly UI: Cheaply made platforms have terrible UIs that make me not even want to log in, but Renoise is very clean and convenient. Remembers my previous settings: It helpfully remembers my last workspace settings. Some odd platforms force you to re-adjust everything every single time you generate a video, which is extremely frustrating. Overall preference: For all these reasons, Renoise AI is definitely my preferred platform. Thank you!
Renoise is your go to one stop all for ai creators. all view and use all models in one place, for any type of content you have your mind on!
I have a creat experience with the app. Consistent characters but also unique. THere were some issues with storyline continuity and non-typical humanoid characters.
One Renoise plan unlocks FLUX 3 Video, FLUX 3 Max and every other video and image model, billed per generation from your plan credits.
For your first AI creations
per month
≈ 150 GPT Image 2 Generations
≈ 60 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For creating every week
per month
≈ 450 GPT Image 2 Generations
≈ 180 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For professional-scale production
per month
≈ 1,750 GPT Image 2 Generations
≈ 700 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For your first AI creations
per month, billed annually
Save $48compared to monthly
≈ 150 GPT Image 2 Generations
≈ 60 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For creating every week
per month, billed annually
Save $216compared to monthly
≈ 450 GPT Image 2 Generations
≈ 180 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For professional-scale production
per month, billed annually
Save $960compared to monthly
≈ 1,750 GPT Image 2 Generations
≈ 700 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
Yes. FLUX 3 Video has been live in Renoise since October 21, 2026, and FLUX 3 Max since October 22. Both are in the Videos page, the Canvas, the API, the CLI and MCP, on the same subscription as every other model. Black Forest Labs opened FLUX 3 Video on its own API on August 4.
FLUX 3 is a family. Black Forest Labs trained one model on image, video and audio, then released FLUX 3 Video, FLUX 3 Image, the open-weight FLUX 3 Image Klein and FLUX 3 Action for robotics. FLUX 3 Max is fal’s video variant. Renoise offers the two video models, FLUX 3 Video and FLUX 3 Max.
Any whole number of seconds from 5 to 20 in one generation, on FLUX 3 Video and FLUX 3 Max alike. Black Forest Labs also offers continuing an existing clip, which is not available in Renoise, so for longer pieces you chain shots in the Canvas or pick Kling 4.0 for up to 30 seconds.
FLUX 3 Video does: Renoise offers 720p, 1080p, 2K and 4K, where 2K and 4K are the same generation upscaled, so the shot does not change. 4K costs 82 credits per second. FLUX 3 Max stops at 1080p. Test a prompt at 720p first: it is the cheapest tier.
Yes. Dialogue, sound effects and ambience are generated with the video and are on by default. You can switch audio off, and the price stays the same. Black Forest Labs says FLUX 3 speaks many languages, including English, Chinese, Spanish, Japanese and German, with lip sync. Put spoken lines in quotes in the prompt.
Not yet. In Renoise, FLUX 3 takes text, a first frame, or a first and last frame, but no reference images, videos or audio. Black Forest Labs lists Omni Reference as coming soon. To keep a person or product consistent from references, use Seedance 2.5 or Kling 4.0 Omni.
In Renoise, FLUX 3 Video costs 30 credits per second at 720p, 48 at 1080p, 56 at 2K and 82 at 4K, so a 5-second 720p clip is 150 credits and a 20-second 4K clip is 1,640. FLUX 3 Max costs 34 at 720p and 58 at 1080p. Audio is included. See pricing.
No. FLUX 3 Video and FLUX 3 Max are billed per generation from the credits in your Renoise subscription, at the rates above, like every other model in the Canvas.
Not the video models. FLUX 3 Video and FLUX 3 Max are closed models offered through APIs. Black Forest Labs says open-weight access to a FLUX 3 Dev backbone is coming soon, without a date. FLUX 3 Image Klein, an image model, already has open weights.
Renoise exposes text to video and first or first-and-last frames. Black Forest Labs’ API also has up to 10 keyframes per shot, continuing an existing video, a cheaper draft mode and automatic duration; those are not in Renoise. FLUX 3 Image is not in Renoise either.
Both are in Renoise. FLUX 3 Video goes up to 4K and 9:21 and costs 150 credits for 5 seconds at 720p. Seedance 2.5 costs 160, stops at 1080p, runs to 30 seconds and takes up to 30 reference images, 10 videos and 10 audio clips. Run the same prompt on both and keep the better take.
Black Forest Labs, the German lab behind the FLUX image models, makes FLUX 3; FLUX 3 Max was post-trained by fal with Black Forest Labs. Renoise does not train video models. Outputs on paid plans are watermark-free and can be used commercially, subject to the Renoise terms.
Generate with FLUX 3 Video or FLUX 3 Max in Renoise, next to Kling 4.0 and Seedance 2.5, and switch models shot by shot.