Skip to main content
skill CX Codex

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

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add black-forest-labs/skills --skill flux-3-keyframes-continuation -a claude-code
Open on GitHub

What 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 i2v and v2v for 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-continuation to plan an i2v clip 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 i2v storyboard from 3-10 images with an integer duration, 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-code

2Manually: put the files in place

~/.claude/skills/flux-3-keyframes-continuation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/flux-3-keyframes-continuation/

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

Similar skills

SKILL.md skills catalog →

From the same set8

flux-3-prompt-doctor flux-3-prompt-doctor evaluates video briefs for FLUX 3 before generation. It resolves conflicting constraints and routes requests to the correct pipeline mode. CX Codex +1 203installs flux-3-video Routes general FLUX 3 video requests to the exact sub-skills handling prompt repair, visual staging, audio, and generation. CX Codex +1 185installs flux-3-generate flux-3-generate takes a FLUX 3 video API job from submit to a checked MP4, including polling and drafts. Use it when you render video through the API. CX Codex +1 185installs flux-3-cinematic-inserts flux-3-cinematic-inserts structures FLUX 3 text-to-video prompts for standalone insert shots and B-roll. It locks camera movement, physics, and scene continuity around a single visual event. CX Codex +1 185installs flux-3-audio-dialogue flux-3-audio-dialogue helps you direct FLUX 3 sound layer by layer: lines, voiceover, ambience, effects and music. Useful when a clip's audio comes out muddled. CX Codex +1 181installs flux-3-product-ads flux-3-product-ads — a Claude Code skill for turning FLUX 3 video and voice into a finished product ad. It guides shot planning, audio-based timing, assembly, and quality checks. CX Codex +1 136installs flux-3-archival-formats flux-3-archival-formats — a skill for Claude Code that configures FLUX 3 video generation for period and archival looks. It defines physical recording formats and specific degradation artifacts instead of moody adjectives. CX Codex +1 136installs

Project sponsors

Companies that keep this analytics open