Skip to content

elithril/blender-kiln / plugin

Makes and fixes 3D assets in Blender, for games, the web and AR. Use when the user wants a 3D model, prop, character or GLB/glTF/FBX/USDZ file made — from a text brief, a reference image, a free marketplace (PolyHaven, Sketchfab) or AI generation — AND when they bring an existing 3D file to fix: too heavy or too many polygons (optimize, compress, LODs), broken normals, scale or origin, materials lost on glTF export, conversion between GLB, FBX and USDZ, texturing, rigging for animation, animating it (walk and idle cycles, text-to-motion, looping clips, articulated props), or inspection. Drives Blender through a Blender MCP server (ahujasid's or the official Blender Lab one). Batch mode produces many consistent assets unattended. Kiln Studio (`/kiln studio`) opens the project's models in the browser, where the user reviews them and pins notes for Claude to act on.

FileKindSize
.claude-plugin/plugin.jsonconfig1.2 KB
.mcp.jsonconfig236 B
LICENSEother1.0 KB
NOTICEother2.5 KB
SKILL.mdskill md29.0 KB
references/ai-generation.mdmarkdown21.0 KB
references/animation.mdmarkdown21.6 KB
references/batch-mode.mdmarkdown19.5 KB
references/blender-mcp.mdmarkdown9.4 KB
references/characters.mdmarkdown52.8 KB
references/cli-tools.mdmarkdown6.5 KB
references/commands.mdmarkdown10.7 KB
references/export-targets.mdmarkdown14.3 KB
references/log-format.mdmarkdown2.2 KB
references/naming-conventions.mdmarkdown5.8 KB
references/photo-projection.mdmarkdown6.3 KB
references/pipeline-brief.mdmarkdown4.2 KB
references/pipeline-import-cleanup.mdmarkdown6.3 KB
references/pipeline-optimize-export.mdmarkdown6.4 KB
references/pipeline-rig-animate.mdmarkdown5.8 KB
references/pipeline-source.mdmarkdown9.7 KB
references/print.mdmarkdown41.5 KB
references/reference-fidelity.mdmarkdown31.8 KB
references/review-rounds.mdmarkdown10.4 KB
references/setup-install.mdmarkdown2.8 KB
references/setup.mdmarkdown9.2 KB
references/sourcing-strategy.mdmarkdown6.1 KB
references/studio.mdmarkdown38.9 KB
references/texturing-strategy.mdmarkdown14.4 KB
references/topology-rules.mdmarkdown3.9 KB
references/uv-materials.mdmarkdown6.8 KB
references/validation-checklist.mdmarkdown10.5 KB
studio/approval_hook.pyscript14.2 KB
studio/blender_live.pyscript2.3 KB
studio/checks.pyscript38.1 KB
studio/estimate.pyscript4.2 KB
studio/example/barrel/barrel_final.glbbinary111.9 KB
studio/example/barrel/barrel_log.mdmarkdown445 B
studio/handoff.pyscript17.8 KB
studio/mcp_server.pyscript32.7 KB
studio/phoneshare.pyscript17.1 KB
studio/server.pyscript47.9 KB
studio/setup_status.pyscript7.5 KB
studio/static/app.jsscript241.4 KB
studio/static/apple-touch-icon.pngbinary20.6 KB
studio/static/fonts/OFL-JetBrainsMono.txtmarkdown4.3 KB
studio/static/fonts/OFL-Sora.txtmarkdown4.3 KB
studio/static/fonts/jetbrains-mono-latin-ext.woff2binary11.3 KB
studio/static/fonts/jetbrains-mono-latin.woff2binary30.6 KB
studio/static/fonts/sora-latin-ext.woff2binary11.8 KB
studio/static/fonts/sora-latin.woff2binary24.6 KB
studio/static/i18n.jsscript6.2 KB
studio/static/i18n/fr.jsonconfig101.2 KB
studio/static/icon-32.pngbinary2.6 KB
studio/static/icon-64.pngbinary6.6 KB
studio/static/icon-96.pngbinary12.8 KB
studio/static/index.htmlother39.5 KB
studio/static/style.cssother114.5 KB
studio/static/tutorial.jsscript49.0 KB
studio/static/tutorial/barrel_after.glbbinary117.3 KB
studio/static/tutorial/barrel_before.glbbinary111.9 KB
studio/static/tutorial/fixtures.jsonconfig13.5 KB
studio/static/tutorial/lantern_1_blockout.glbbinary83.1 KB
studio/static/tutorial/lantern_2_details.glbbinary101.8 KB
studio/static/tutorial/lantern_3_materials.glbbinary102.0 KB
studio/static/tutorial/lantern_4_final.glbbinary141.1 KB
studio/static/tutorial/make_tutorial.pyscript4.9 KB
studio/static/viewer.jsscript41.4 KB
studio/studio.pyscript29.2 KB
studio/studiolib.pyscript77.8 KB
studio/test_studio.pyscript90.2 KB
studio/test_worker.pyscript31.5 KB
studio/worker.pyscript56.8 KB
studio/worker_blender.pyscript2.7 KB
tools/autorig.pyscript44.1 KB
tools/bind_rigid_parts.pyscript3.6 KB
tools/blender_mcp_start.pyscript1.5 KB
tools/check_usdz.pyscript1004 B
tools/cutout.swiftscript2.0 KB
tools/export_outputs.pyscript5.2 KB
tools/fidelity_check.pyscript39.0 KB
tools/fit_coupon.pyscript11.3 KB
tools/fixtures/skintokens_raw_child.glbbinary88.8 KB
tools/fixtures/skintokens_skeletons.jsonconfig6.5 KB
tools/flatten.pyscript14.9 KB
tools/glb_to_fbx.pyscript2.1 KB
tools/glb_to_usdz.pyscript6.2 KB
tools/motion_loop.pyscript5.9 KB
tools/motion_measure.pyscript15.2 KB
tools/motions/LICENSE-image-to-3dlab.txtmarkdown11.1 KB
tools/motions/cheer.npzbinary48.4 KB
tools/motions/cheer_b.npzbinary48.1 KB
tools/motions/dance.npzbinary78.2 KB
tools/motions/dance_b.npzbinary78.9 KB
tools/motions/death.npzbinary45.9 KB
tools/motions/death_b.npzbinary46.5 KB
tools/motions/fight_stance.npzbinary60.3 KB
tools/motions/fight_stance_b.npzbinary61.3 KB
tools/motions/flying_kick.npzbinary39.7 KB
tools/motions/flying_kick_b.npzbinary39.9 KB
tools/motions/hit_react.npzbinary31.9 KB
tools/motions/hit_react_b.npzbinary31.8 KB
tools/motions/idle.npzbinary51.8 KB
tools/motions/idle_b.npzbinary57.7 KB
tools/motions/jump.npzbinary39.8 KB
tools/motions/jump_b.npzbinary39.9 KB
tools/motions/kata.npzbinary77.4 KB
tools/motions/kata_b.npzbinary75.3 KB
tools/motions/kick.npzbinary32.4 KB
tools/motions/kick_b.npzbinary32.5 KB
tools/motions/presets.jsonconfig9.6 KB
tools/motions/punch.npzbinary32.0 KB
tools/motions/punch_b.npzbinary32.1 KB
tools/motions/punch_combo.npzbinary47.4 KB
tools/motions/punch_combo_b.npzbinary47.5 KB
tools/motions/roll.npzbinary46.7 KB
tools/motions/roll_b.npzbinary47.5 KB
tools/motions/roundhouse.npzbinary39.7 KB
tools/motions/roundhouse_b.npzbinary39.9 KB
tools/motions/run.npzbinary47.2 KB
tools/motions/run_b.npzbinary47.7 KB
tools/motions/sit.npzbinary47.2 KB
tools/motions/sit_b.npzbinary47.2 KB
tools/motions/sneak.npzbinary61.6 KB
tools/motions/sneak_b.npzbinary61.8 KB
tools/motions/strafe_left.npzbinary45.9 KB
tools/motions/strafe_left_b.npzbinary47.1 KB
tools/motions/sword_swing.npzbinary39.7 KB
tools/motions/sword_swing_b.npzbinary39.4 KB
tools/motions/walk.npzbinary62.8 KB
tools/motions/walk_b.npzbinary62.6 KB
tools/motions/walk_woman.npzbinary62.9 KB
tools/motions/wave.npzbinary46.3 KB
tools/motions/wave_b.npzbinary46.3 KB
tools/open_blender.pyscript5.0 KB
tools/photo_project.pyscript37.8 KB
tools/presets.pyscript16.3 KB
tools/print_check.pyscript47.2 KB
tools/quadruped.pyscript19.4 KB
tools/retarget.pyscript46.9 KB
tools/review_renders.pyscript13.8 KB
tools/review_sheet.pyscript11.0 KB
tools/skintokens-requirements.txtmarkdown2.4 KB
tools/skintokens.patchother9.2 KB
tools/template_profile.pyscript5.8 KB
tools/test_autorig.pyscript15.9 KB
tools/test_fidelity_check.pyscript20.7 KB
tools/test_fit_coupon.pyscript6.4 KB
tools/test_flatten.pyscript15.0 KB
tools/test_open_blender.pyscript1.3 KB
tools/test_photo_project.pyscript12.6 KB
tools/test_presets.pyscript17.6 KB
tools/test_print_check.pyscript33.1 KB
tools/test_review_renders.pyscript11.4 KB
tools/test_review_sheet.pyscript4.0 KB
tools/test_template_profile.pyscript3.6 KB
tools/test_uv_check.pyscript5.0 KB
tools/test_verify_docs.pyexecutablescript7.9 KB
tools/unimate.patchother3.5 KB
tools/unimate.pyscript17.5 KB
tools/uv_check.pyscript8.4 KB
tools/verify_blender.pyexecutablescript29.2 KB
tools/verify_docs.pyexecutablescript16.6 KB

references/photo-projection.md

View on GitHub
# Photo projection — the photo's own markings on the model (optional)

A script copies text, a logo or precise wear as a lookalike: the ammo box's stencil came
out in the right font, a few millimetres off and worn in the wrong places. The photo holds
the right answer for every surface it sees squarely. `tools/photo_project.py` puts those
pixels back on the model's base-colour textures, and nowhere else. The method is
AssetFurnace's Pixel Match (image-to-3dlab, Apache-2.0 — `plugin/NOTICE`), on kiln's cameras.

**Optional, never the default, never silent.** It runs after the last fidelity_check round
(`reference-fidelity.md` § 5), and only when all three hold:

- the photo carries **text, a logo or precise wear** the script did not get right;
- the **fitted camera's silhouette IoU is ≥ 0.95** (the tool refuses below);
- **the user said yes** — propose it with what it changes and the two other angles (rule 6:
  it repaints the textures the user already saw; the input is never overwritten).

## Run it

```bash
# --view / --azimuth / --elevation: the same as the fidelity_check calls (read before modelling).
# --exclude: parts placed differently from the photo (a handle folded the other way, a lever).
# --erase-stencil: the scripted marking's colour (sRGB), erased where the photo is used.
blender -b --factory-startup --python-exit-code 1 --python <skill>/tools/photo_project.py -- \
  --reference ref.png --model asset_final.glb --hdri studio_small_09_1k.hdr --out review/project/ \
  --view front --azimuth 50 --elevation 20 \
  --exclude SM_AmmoBox_Handle SM_AmmoBox_LatchLever --erase-stencil '#443A14'
```

It writes `{model}_projected.glb` (Draco and WebP kept when the input had them),
`textures/`, `confidence/` (white: the photo is used), `photo_view.png` (photo | before |
after | confidence), `other_angles.png` (before above after) and `photo_project.json`.

1. **The camera.** fidelity_check's (orthographic, scaled to the photo's height), then
   azimuth, elevation, roll and distance fitted to the photo's silhouette — bounded to 10°
   from it, 5° of roll. Unbounded, a box 40 % too long fitted 0.955 by turning 30° away.
2. **Each texel's confidence**, multiplied: seen (depth), facing the camera (full at
   `--facing`, 0.6 by default and never less, fading in from 0.35 below), away from the
   model's outline, from inner depth edges and from the matte's edge, inside the matte. A
   texel two surfaces share in the UVs gets nothing.
3. **The photo at the model's exposure**: one gain in linear luminance, the median ratio
   over the trusted texels (≥ 0.9). Never the photo's raw pixels: they carry its light — on
   the ammo box, the photo's near-black lighting pasted into the base colour. A mean ratio
   is pulled by what the model lacks: a white letter on 11 % of a face set it at 1.25 and left
   the face 18 % dark, letter included; the median (2.07) keeps it within 15 % of the model's.
4. **Blend**: photo × confidence + texture × (1 − confidence), the change grown 4 texels
   into the UV gutter. Excluded parts receive nothing but still hide what is behind them.

## Read it

- **Look at `other_angles.png` first.** It is the only view not measured against the photo.
  The SSIM and ΔE76 from the photo's view are **partly circular** — the photo compared with
  itself where it was pasted: they say the projection landed, not that the model is better.
- **fidelity_check's numbers are not the judge either**: on the ammo box its saturation gap
  grew (0.131 → 0.183, prototype) while the stencil became the photo's.
- **Look for the defects seen on the ammo box**: a **double marking** (the photo's text beside
  the script's, half-blended) — pass `--erase-stencil`; **a highlight or part pasted where
  the model has another part** (a lid highlight on a handle placed differently) — `--exclude`
  that part; **an opening painted on a flat plate** (the lever's hole) — exclude it, or model
  the hole; **text faded at the trust's edge** (the "7" of "7.62", near the face's outline) —
  a limit, said to the user.
- Refusals exit 1: fitted IoU under `--min-iou`, `--facing` under 0.6, an `--exclude` that
  matches no object or material, no textured part, fewer than 50 trusted texels.

## Measured

The ammo box (bench `ref-kiln-v15gen`, scripted, 3,856 tris, two 1024 textures), azimuth
50 / elevation 20 as its session read them. Camera: IoU **0.918 → 0.963** after the fit
(az 51.9, el 15.7, 0.92 m). From the photo's view, Cycles under `studio_small_09`:

| Run | Gain | SSIM | ΔE76 | GLB |
|---|---|---|---|---|
| Before (the session's `_final.glb`) | — | 0.551 | 17.46 | 186.6 kB |
| Prototype, raw pixels | — | 0.655 | 12.90 | — |
| Prototype, mean-ratio gain | 2.05 | 0.619 | 15.42 | 171.8 kB |
| `photo_project.py`, median-ratio gain | 2.71 | 0.597 | 16.84 | 175.4 kB |
| + `--exclude` handle and lever, `--erase-stencil '#443A14'` | 2.97 | 0.589 | 17.27 | 174.3 kB |

The tool scores below the prototype's mean gain on this one photo, and is right on the
seeded box where the mean left the face 18 % dark: the brighter median lifts the dark photo further from
itself, which is the circularity above. Raw scores highest and is refused — it is the
photo's lighting. The erase removed 19,273 stencil texels where the photo is used, kept
67,206 where it is not; the double "7.62" is gone by eye. 14 % of the texels trusted, 25 %
touched. 83 s headless (Apple Silicon CPU, 64 samples, six renders).

`tools/test_photo_project.py` (Blender workflow): a box with an "E" printed on its front,
photographed 1⅓ stops darker from az 25 / el 15 at 0.9 m, the tool started at 30 / 12 —
IoU 0.917 → 0.992, SSIM 0.771 → 0.847, ΔE76 16.9 → 14.5, gain 2.07, the front's correlation
with the truth 0.17 → 0.95, the back's texture unchanged, an excluded plate kept, a yellow
mark erased in view and kept on the back, a 40 % longer box refused at 0.859.

## Limits

- **One object tested** (the ammo box, one photo), plus the seeded box. No organic shape, no
  glossy material, no second photo.
- One photo, one camera: the sides it does not face keep the scripted texture, and the seam
  between them is only as good as the gain. No local colour match (AssetFurnace's).
- The photo's exposure is matched, not its light: shading and highlights in the photo stay
  in the base colour where it is trusted.
- The model's shape must match: a misplaced part gets the photo of what is in front of it.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall