flux-3-keyframes-continuation — Claude Code skill: FLUX 3 video
flux-3-keyframes-continuation is a Claude Code skill for building FLUX 3 videos from images or clips with keyframes, storyboards, and continuation planning.
MIT 183 installs ★ 138 updated 2026-09-09
npx skills add black-forest-labs/skills --skill flux-3-keyframes-continuation -a claude-codeWhat flux-3-keyframes-continuation does
This skill guides i2v generation from one image, a start and end pair, a storyboard, or timestamped keyframes. It also covers v2v continuation, where the next segment follows the source clip’s ending. Prompts focus on motion, camera continuity, subject identity, framing, and sound instead of restating visible pixels.
Media can be supplied as a public URL or inline base64. Keyframe images must be at least 256x256. Storyboards use 3-10 images, while timestamped pins use [seconds, image] pairs; both forms require an integer duration. The skill produces a conditioning plan, final prompt, pin map, and transition risks.
A v2v input is capped at 15 s and 50 MB, with output capped at 15 s. Higher-resolution input can reduce the usable segment length, so longer chains need seam review and careful segment planning.
What it helps with
- choose between
i2vandv2vfor a FLUX 3 clip - connect opening and closing keyframes
- turn several images into an ordered storyboard
- pin a frame at an exact timestamp
- extend a clip while preserving motion and sound
Example prompts for the agent
- Use
flux-3-keyframes-continuationto plan ani2vclip from two images, keeping the camera steady while the scene changes. - Continue this video with
v2v; carry the existing camera angle, subject motion, and sound across the cut. - Create an
i2vstoryboard from3-10images with an integerduration, then list transition risks.
How to install flux-3-keyframes-continuation
1Skills CLI (Vercel)
npx skills add black-forest-labs/skills --skill flux-3-keyframes-continuation -a claude-code2Manually: put the files in place
~/.claude/skills/flux-3-keyframes-continuation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/flux-3-keyframes-continuation/
1Skills CLI (Vercel)
npx skills add black-forest-labs/skills --skill flux-3-keyframes-continuation -a codex2Manually: put the files in place
.agents/skills/flux-3-keyframes-continuation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add black-forest-labs/skills --skill flux-3-keyframes-continuation -a cursor2Manually: put the files in place
.cursor/skills/flux-3-keyframes-continuation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install black-forest-labs/skills skills/flux-3-keyframes-continuation2Manually: put the files in place
.github/skills/flux-3-keyframes-continuation/SKILL.md1Skills CLI (Vercel)
npx skills add black-forest-labs/skills --skill flux-3-keyframes-continuation -a gemini-cli2Platform CLI
gemini skills install https://github.com/black-forest-labs/skills --path skills/flux-3-keyframes-continuationManually: put the files in place
.devin/skills/flux-3-keyframes-continuation/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add black-forest-labs/skills --skill flux-3-keyframes-continuation -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about flux-3-keyframes-continuation
How do I install flux-3-keyframes-continuation in Claude Code?
Run npx skills add black-forest-labs/skills --skill flux-3-keyframes-continuation -a claude-code, then use ~/.claude/skills/flux-3-keyframes-continuation/SKILL.md.
What does flux-3-keyframes-continuation do?
It helps plan FLUX 3 video generation from images or an existing video. The skill selects an i2v or v2v shape, writes the prompt, and tracks continuity risks between segments.
What limits apply to video continuation?
For v2v, the source video can be up to 15 s and 50 MB, while the generated output can be up to 15 s. Media is passed through a public URL or inline base64.
Source text
SKILL.md · MIT
--- name: flux-3-keyframes-continuation description: Use when a FLUX 3 video must be built from supplied images or video. Covers keyframes (i2v) and continuation (v2v). metadata: author: Black Forest Labs version: "1.0.0" tags: flux, flux-3, bfl, keyframes, continuation --- # FLUX 3 Keyframes and Continuation Every supplied source gets one declared job, or is dropped. Two modes condition on media, and each carries exactly one media field: | Required relationship | Request | | --- | --- | | These exact pixels open the clip (the stable path) | `mode: "i2v"`, `keyframes`: one image | | Exact opening and closing frames, filled in between | `mode: "i2v"`, `keyframes`: two images | | An ordered storyboard the model connects | `mode: "i2v"`, `keyframes`: 3-10 images plus an integer `duration` | | Frames pinned at exact moments | `mode: "i2v"`, `keyframes`: `[seconds, image]` pairs, ascending, integer `duration` | | Keep going from where this clip ends | `mode: "v2v"`, `start_video` (input max 15 s / 50 MB; output max 15 s) | Keyframes appear **on screen, pixel-exact**. There is no field that carries a subject without showing the source image; a source used only as inspiration is described in the prompt instead. Media is a public URL or inline base64; keyframe images are at least 256x256. ## Prompting each shape - **One keyframe:** the image opens the clip. Prompt what moves; redescribing visible pixels invites re-imagination. - **Two keyframes:** opening and closing are pinned, so describe the stages of the change in order and hold the camera still. Keep the two ends related enough for a plausible path; large jumps invite drift. - **Storyboard:** frames become ordered waypoints. Keep identity, palette, and viewpoint coherent unless a change is intentional. - **Timestamped pins:** a mid-clip pin is a deadline; say what the remaining seconds are for, or they trail off. Pin only what matters; extra anchors stiffen motion. - **Continuation:** write from the ending. Say what happens next and which momentum, framing, subjects, and sound carry across the boundary; do not recap completed action. ```text The camera continues a slow push-in as the closed flower opens naturally into the final bloom. The stem remains fixed in place, the same soft morning light holds across the shot, and a light breeze moves the surrounding leaves without changing the composition. ``` ```text Continue from the rider's existing forward momentum. The camera keeps the same low trailing angle as the horse crests the hill and enters dense fog; hoofbeats and wind carry across the boundary without a reset. ``` ## Chains For clips longer than one generation: preserve a clean ending and record the subject's direction, speed, and camera relationship; continue from the actual ending artifact; restate only invariants and the next action; review each seam before extending; change one continuity variable at a time when repairing drift. A video input at higher resolution may cap duration below the general maximum, which changes segment planning. Return the conditioning plan (which mode and shape, and why), the invariants that must survive, the final prompt, and any pin map or transition risks. Field limits and current constraints: [API reference](https://docs.bfl.ai)
© Black Forest Labs · MIT · black-forest-labs/skills