Skip to content
Agentmart
Submit a tool

text-to-image-to-video

Two-stage pipeline that generates a still image from a text prompt (Flux/SDXL/Imagen) then animates it into a video clip (Kling/Runway/Hailuo/Wan).

Skill by shotcowboystyle

IndexedMIT
Write a review

Chalk Labs

Need help deploying text-to-image-to-video?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/shotcowboystyle-text-to-image-to-video

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Two-stage pipeline that generates a still image from a text prompt (Flux/SDXL/Imagen) then animates it into a video clip (Kling/Runway/Hailuo/Wan). Use when the user wants tight visual control over the opening frame before motion.

Use cases: data, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/text-to-image-to-video

What's inside

Skill name
text-to-image-to-video
Description
Two-stage pipeline that generates a still image from a text prompt (Flux/SDXL/Imagen) then animates it into a video clip (Kling/Runway/Hailuo/Wan). Use when the user wants tight visual control over the opening frame before motion.
License
MIT
Instructions
32 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# 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. Run it through the provider that hosts the model: fal.ai and WaveSpeed models via the `provider-runners` skill (pass `--output` with the target folder); Replicate and MiniMax via their MCP servers. 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, the same way. 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.

From shotcowboystyle/ag-skills, MIT.

Signals

Stars
0
Forks
0
Open issues
29
Last commit (this folder)
Oct 18, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get text-to-image-to-video running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying text-to-image-to-video?

CallGet help
Cite this page

text-to-image-to-video skill. Agent Mart. https://agentmart.dev/skills/shotcowboystyle-text-to-image-to-video (last updated 2026-10-24)