Floyo
Floyo
Workflows
API
Pricing
Floyo
Floyo
Workflows
API
Pricing

FLUX 3 · Extend Video

FLUX 3 is Black Forest Labs' video model that continues a clip where it left off. Upload a video for up to 20 seconds of new footage, with sound.

34

Gen time: -- secs

Nodes & Models

Flux3ExtendVideo_floyo
VideoToFrames
LoadVideo
CreateVideo
SaveVideo
FloyoStickyNote

ABOUT THE WORKFLOW

Continue a video clip
Upload a video and the model generates new footage that continues the scene from where the clip ends, keeping the subject, lighting, and motion consistent. It builds picture and sound together, so the new footage has audio. A prompt is optional.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

  • FLUX 3 by Black Forest Labs. The lab's first multimodal video model, trained jointly on images, video, and audio in one architecture. In extend mode, it picks up from the last frame of your clip and generates up to 20 seconds of new footage that continues the scene, with native audio and consistent subjects, lighting, and motion.


HOW IT WORKS

Step 1. Upload your video
The clip you want to extend. The model picks up from its last frame.
Works great with: clean scene endings · steady shots · single continuous scenes

Step 2. Describe what happens next (optional)
Steer the new footage with a prompt: an action, a camera move, dialogue, or sound. Leave it empty to let the model decide.

Step 3. Hit run
The model generates new footage that continues the scene, with audio. This is a large model, so give it longer to finish.

Step 4. Download and stitch
The saved file is the new footage only, with sound. Join it to your original in an editor to get the full extended clip.
Ready for: editing timelines · social · ads

First time? Leave every setting as-is. The defaults (auto ratio · 720p · 5 seconds) are the right starting point for almost everyone.


RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

  • Standard use (most people) — auto aspect ratio, 720p, 5 seconds of new footage. The right starting point for almost everyone.

  • Want higher quality — switch the resolution to Full HD. It sharpens the new footage and costs more per second.

  • Want more new footage — raise the duration up to the 20-second maximum. To go further, run the workflow again on the extended clip.

  • Keeping cost down — lower the duration and the resolution, since both drive the per-run cost. A 20-second Full HD run costs much more than a 5-second HD one.

  • The continuation drifts — start from a clip with a clean ending on a steady shot, since a clear last frame gives the model a better starting point.

  • Making vertical content — set the aspect ratio to 9:16 for phones and short-form feeds. Auto matches your input video.

Prompt: The prompt is optional here. Leave it empty and the model continues the scene on its own, or add a prompt to direct what happens next, like "she stands and walks toward the door, footsteps echoing." A clip that ends on a clean, steady frame continues more smoothly than one that cuts mid-action.


LEARN

📹 Videos

✨ Quick links


USE CASES

⏭️ Extend a Clip
Add more seconds to a shot that ended too soon.

🎬 Continue a Scene
Keep an action going with a consistent subject and motion.

📱 Fill a Format
Stretch a short clip to fit a longer slot or feed.

🔁 Build in Passes
Extend again on the result to grow a clip beyond one run.


WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

  • Clips that end on a clean, steady frame

  • A single continuous scene

  • Consistent subject and lighting

  • New footage of 20 seconds or less per run

⚠️ May produce softer results

  • Clips that end mid-action or on a cut

  • Busy scenes with many moving parts

  • Asking for more than 20 seconds in one run

  • A source clip with an unclear last frame


FAQ

What is FLUX 3?
FLUX 3 is Black Forest Labs' first multimodal video model, announced in July 2026 and made generally available in August 2026. It is trained jointly on images, video, and audio, and generates HD video up to 20 seconds with native sound. This workflow runs it in extend mode, continuing a clip you upload from its last frame.

How does extending a video work?
You upload a source clip, and the model reads its final frames and generates new footage that continues the scene, matching the subject, lighting, and motion. It builds the sound for the new footage in the same pass. A prompt is optional and only steers what happens next.

Is the output the whole video or only the new part?
The saved file is the new footage only, not your original with the extension attached. To get the full clip, join the generated segment to the end of your source video in any editor. This keeps each run focused on the part the model creates.

Does the extended footage have sound?
Yes. FLUX 3 generates native audio for the new footage, and this workflow keeps it in the saved file. The sound is built alongside the picture, so the extended segment arrives with its own audio rather than silent.

How much can I add, and can I extend further?
Each run generates up to 20 seconds of new footage. To go longer, run the workflow again using the extended clip as the new source, and repeat until you have the length you want. Duration and resolution both affect the cost of each run.

Can I use FLUX 3 videos commercially?
FLUX 3 is a proprietary model accessed through Black Forest Labs' API, so commercial use is governed by BFL's terms and its pay-as-you-go pricing rather than an open license. Commercial use is generally supported for ads and content, but review BFL's current terms and make sure you have the rights to the video you upload.

How to run FLUX 3 online?
You can run FLUX 3 online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload a video, and hit run. Free to try.


WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A creator extends a clip and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.


Ready to try it?
Upload a video and run it. Then stitch the new footage to your clip.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.

Read more

N