Generate per-shot anchor images and keyframes for Flux2 video pipelines.
npx skills add https://github.com/venetanji/creative-skills --skill storyboard-venetanji
Please help me install this Agent Skill. Skill: storyboard Source: https://github.com/venetanji/creative-skills/tree/main/storyboard Command: npx skills add https://github.com/venetanji/creative-skills --skill storyboard-venetanji
Shared toolkit for building per-shot reference images (anchors) and keyframe sequences via flux2 i2i/i2i2/multi-reference. Use when any pipeline — music-video, drama-video, a one-off render — needs a scene-specific anchor, a character pose sheet, or first/last keyframes for a transition. Exposes a generate_anchor CLI + a prompting guide the operator should skim before writing prompts. All production-quality anchors on this deployment go through this skill.
Run the CLI to produce a shot-specific anchor image from a prompt (and optional references) for immediate use in your flux2 workflow.
High-intent search queries and answers about installing and using this skill.
Create consistent scene anchors and per-shot keyframes by preprocessing prompts and resolving reference images via a CLI. It generates reusable anchor images that maintain character identity and scene consistency across music-video or drama-video pipelines.
Generate per-shot keyframes for a Flux2 workflow by running the generate_anchor CLI with a prompt and optional references. It supports i2i, i2i2, t2i, and multi-reference workflows to produce shot-specific anchor images for immediate use in rendering pipelines.
Yes, a Flux2-compatible workflow is required. You need the flux2 CLI or comfy_graph integration alongside the skill's Python tooling, including generate_anchor.py and prompts.py, to preprocess prompts and produce anchor images for your video pipeline.
Yes, multi-reference workflows are supported to maintain character identity across scenes. The CLI handles subject tokens and multiple reference inputs, resolving guides and prompts to produce consistent anchor images for each shot in your music-video or drama-video pipeline.
Prompt preprocessing for scene anchor generation works through Python APIs that parse and refine your input prompts before rendering. The lib/prompts.py module resolves style guides and subject tokens, ensuring the output anchor images match your intended scene composition and character poses.
Per-shot anchors are limited to Flux2-compatible pipelines and require Python CLI tooling to function. They serve as reference images for scene consistency and character poses, but downstream rendering still depends on integration with tools like LTX or comfy_graph for final video output.
talesofaiForge visual concepts into reusable Elementum Tokens for consistent image generation prompts.
nexu-ioGenerate hyperframes sequences with duration metadata for Remotion-compatible output.
fal-ai-communityGenerate consistent character designs and reference sheets from a character anchor.
wwloreyGenerate or modify images using OpenAI GPT Image models.
