# Consistent Asset Sets: one approved reference, style files and review sheets for AI-made art, props and cards

> A small production system for making many AI-made assets that belong together: approve one reference, write STYLE.md from it, request only deltas, build props as code, and review every batch on one sheet with a ten-point check.

- URL: https://paperchasewebb.ai/bots/marketplace/items/consistent-asset-sets-reference-lock-style-files-review-sheets/
- Type: Prompt pack
- Category: Creative and video
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Claude, ChatGPT (named in the listing); Plain .md
- Price: $24 USD
- Difficulty: Beginner
- Setup time: 20 min
- Time to result: Reference approved and first batch reviewed in one session
- Format: Markdown (.md) file, consistent-asset-sets-reference-lock-style-files-review-sheets.md
- Version: 1.0, updated 2026-10-27
- License: Personal and commercial use. Your assets are yours, subject to each tool's terms. Do not resell or republish this pack.

## What you end up with

Card sets, game props and campaign images that match each other, with every prompt, cost and license written down.

## What you get

- 14 sections in one .md file, about 12 pages
- Five causes of drift and the fix for each
- A generate, code or premade tradeoff table
- The reference lock method
- STYLE.md and PROMPTS.json templates
- Assets as code with Blender Python and the annotate loop
- A review sheet and ten-point check
- 3D as a camera guide for generated video
- Cost and rights ledgers and a client brand set flow
- A rules block, a set-reviewer SKILL.md and 12 prompts
- Linked credits for the 9 public sources we studied

## Who it is for

People making card sets, game props, campaign images or 3D scenes with AI who want forty assets that look like one set instead of forty experiments.

## Tools needed

- Claude, ChatGPT, Claude Code or Codex: writes style files, scripts and review sheets
- Your image, 3D or video generator: makes generated assets against the reference
- Blender: optional: script-built props and camera guides
- You need: An asset list for one set
- You need: Any image or 3D tool that accepts a reference

Cost to run: Free. Uses the image, 3D or coding tools you already have. Generation costs depend on your services.

## Sample prompt: Delta request (Claude, ChatGPT, your image tool)

```
Match the attached reference exactly in style, framing and light. Change only: [delta from data row].
No text in the image.
```

Deltas drift less than fresh descriptions.

## Sample prompt: Build the review sheet (Claude Code, Codex)

```
Write a script that renders every item in [folder] at the same size and camera, tiles them in a grid with reference/REF-001 top-left and names underneath.
Save it to review/sheet-[date].png.
```

Drift hides one at a time and shows on a sheet.

## Free preview of consistent-asset-sets-reference-lock-style-files-review-sheets.md

````markdown
# Consistent Asset Sets: one approved reference, style files and review sheets for AI-made art, props and cards

A PaperChaseWebb pack, version 1.0. Written for Claude, ChatGPT, Claude Code and Codex, and plain Markdown, so the style file, the reference lock method, the review sheet and the prompts work with any image, 3D or coding tool you already use.

Making one good image with AI is easy now. Making forty that look like they belong together is not. Card sets drift in line weight. Props for one game come out at five different scales. A client's campaign images slowly change palette from Monday to Friday. The fix is not a better prompt. It is a small production system: approve one piece, lock it as the reference, write the style down, make the rest against it, and review the whole set on one sheet.

This pack is that system, for three ways of making assets: generating them, writing them as code and picking from premade libraries. It is built from public build reports by people who made card sets, game props, 3D previs and full game art sets with agents, plus our own client asset work. Sources are credited by link in the Sources section.

## What is inside

| Section | What it is for |
|---|---|
| 1. Why sets drift | Five causes, and which step in this pack fixes each |
| 2. Choose a mode per asset | Generate, code or premade, with a tradeoff table |
| 3. The reference lock method | Perfect one, lock it, attach it to every request, ask for deltas only |
| 4. STYLE.md | A style file template with palette, line, light, camera and forbidden list |
| 5. PROMPTS.json | A saved prompt library so good prompts are reused, not retyped |
| 6. Assets as code | Script-built props, asset description files and the annotate loop |
| 7. The review sheet | One image of the whole set, plus a ten-point check |
| 8. 3D as a camera guide | Use a rough 3D model to steer generated video and stills |
| 9. Cost and rights ledgers | Track spend per stage and the license on every asset |
| 10. Client brand sets | Turn a brand guide into STYLE.md and an approval flow |
| 11. Rules block | A paragraph for CLAUDE.md, AGENTS.md or a project |
| 12. The set-reviewer skill | A SKILL.md that checks a batch against the reference |
| 13. Prompts | 12 prompts |
| 14. Sources | What we used and how we used it |
````

## Worth knowing

- Model behavior changes between versions. Date your prompt notes.
- No method makes generated sets perfectly consistent. The review sheet catches what slips.
- Real brands, crests and people need permission for commercial use. Not legal advice.

## Questions

**Which image or 3D tools does it work with?** Any that accept a reference image or file. The method is tool-neutral; the scripts use Blender and Python.

**Is this only for games?** No. The same method works for card sets, social campaigns, product renders and client brand images. Section 10 covers client brand sets.

**Do I need to code?** No for the reference method, STYLE.md and review. The assets-as-code and review sheet scripts are written by your coding agent from the prompts.

**Is there a free sample?** Yes. The reference lock method and the delta request prompt are free on their own listing.

**Is any of it copied?** No. We read 9 public build reports and wrote everything in our own words. Sources are linked and credited inside.

## How to buy

$24 one time at https://paperchasewebb.ai/bots/marketplace/items/consistent-asset-sets-reference-lock-style-files-review-sheets/. Stripe checkout, then an instant download page; the download link is also in your emailed receipt.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com