text-to-image-to-video

text-to-image-to-video is a skill for Claude Code from danielrosehill/Claude-AI-Video-Producer-Plugin. It costs 61 tokens per session (631 once invoked), scanned A, original, MIT.

A two-step video workflow that first creates a still image from text and then animates that chosen image into a clip. The still acts as a fixed reference for the opening frame.

In plain words
What is it for?
Use it for shots that need a specific starting image, consistent character references, or tightly controlled framing before animation.
Why use it?
It gives you more control over composition and character pose when direct text-to-video changes the scene between attempts. You can refine the cheaper still before generating the more expensive motion.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-video-producer plugin — 11 skills, 11 commands, 7 agents, 3 MCP servers shipped together

Good fit Use it for shots that need a specific starting image, consistent character references, or tightly controlled framing before animation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielrosehill/claude-ai-video-producer-plugin/text-to-image-to-video
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add danielrosehill/Claude-AI-Video-Producer-Plugin --skill text-to-image-to-video
Clone the repo
git clone --depth 1 https://github.com/danielrosehill/Claude-AI-Video-Producer-Plugin

Made for: Claude Code.

Or install ai-video-producer, the plugin that ships this one along with the rest of its 11 skills, 11 commands, 7 agents, 3 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for text-to-image-to-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielrosehill/claude-ai-video-producer-plugin/text-to-image-to-video/github.svg)](https://agentmods.dev/skills/danielrosehill/claude-ai-video-producer-plugin/text-to-image-to-video)
Your own site
<a href="https://agentmods.dev/skills/danielrosehill/claude-ai-video-producer-plugin/text-to-image-to-video"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-ai-video-producer-plugin/text-to-image-to-video/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for text-to-image-to-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/danielrosehill/claude-ai-video-producer-plugin/text-to-image-to-video"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-ai-video-producer-plugin/text-to-image-to-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 631 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.00631
Opus 5 $0.00030 $0.00316
Sonnet 5 $0.00012 $0.00126
Haiku 4.5 $0.00006 $0.00063

Measured 12d ago against content hash acdea5b1a4bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

text-to-image-to-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/text-to-image-to-video/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Text → Image → Video Pipeline

Two-stage chain. Stage 1 produces a still you can iterate on cheaply; stage 2 animates the chosen still.

When to use

  • The shot needs a specific composition or character pose locked before motion.
  • Direct text-to-video drifts off-prompt; this gives you an anchor frame.
  • Cost: one image gen + one video gen per accepted take. Iterating on the still is cheap; iterating on motion is not — get the still right first.

Inputs

  • A shot brief from scripts/storyboards/NN-*.md (visual prompt seed, duration, character refs).
  • Model selection from brief/tools-and-models.md (text-to-image model + image-to-video model).
  • Optional: character reference image from characters/<name>.md.

Steps

  1. Compose image prompt. Combine the shot's visual seed + character seed prompt + style/vibe from brief/creative-brief.md. Show it to the user before generating.
  2. Generate still. Call the configured text-to-image model (typically via Fal or Replicate MCP). Save to generation/text-to-image/NN-shortname-vN.png. Save prompt + model + seed to generation/prompts/NN-shortname-vN.md. Append to logs/production-log.md.
  3. Iterate on still. Show the image. If the user wants to refine, loop on step 2 with an incremented vN. Don't proceed until the user approves a still.
  4. Compose motion prompt. Describe the motion — camera move, subject action, duration. Pull duration from the shot brief.
  5. Animate. Call the configured image-to-video model with the approved still as input. Save to generation/image-to-video/NN-shortname-vN.mp4. Save the motion prompt and parameters to generation/prompts/NN-shortname-vN-motion.md. Log it.
  6. Surface result. Show the clip. Offer: accept (copy to clips/raw/ and suggest /promote-take), retry motion, or go back to step 2 (new still).

Common gotchas

  • Aspect ratio mismatch. The still must match the target video aspect from brief/creative-brief.md. Set it explicitly in the image gen call; don't rely on the model's default.
  • Character drift across shots. Always pass the character's seed prompt verbatim. Consider using a character reference image as a control input if the model supports it.
  • Motion model resolution caps. Some image-to-video models downscale. If final output needs 4K, pair with the upscale-and-interpolate skill.

Read the full file on GitHub · 36 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 36 lines · 61 tokens per session scan A acdea5b1a4bd

Subscribe to this mod's changes

text-to-image-to-video is a skill published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 631 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens