image-to-sculpt — скилл для Claude Code: что делает и как установить
Скилл image-to-sculpt для Claude Code превращает изображение в трёхмерную скульптуру и сверяет её с оригиналом. Агент включает его для создания модели по картинке, записи процесса в Blender или проверки готовой модели по референсу.
MIT ★ 306 обновлён 2026-11-08
/plugin marketplace add gokayfem/image-to-sculpt
/plugin install image-to-sculpt@image-to-sculptЧто делает image-to-sculpt
Скилл собирает по одному изображению замкнутую 3D-скульптуру и записывает этапы работы для воспроизведения в Blender. Он строит карты маски, глубины и нормалей для исходного ракурса, создаёт виды скрытых сторон, отбирает согласованные изображения и формирует визуальную оболочку. Затем скульптура проходит этапы подгонки по силуэту, нормалям и глубине оригинала.
В комплекте есть CLI scripts/i2s.py: он запускает подготовку проекта, построение и проверку модели, подгонку отдельных областей, экспорт и создание таймлапса или вращения модели. Результаты можно выгрузить в GLB, OBJ и STL; отчёт включает сравнение с референсом. Для генерации видов CLI вызывает fal. Если API-ключа нет, можно работать с PNG на прозрачном фоне и собственными видами; при одном виде глубина невидимой стороны остаётся предположительной.
Скилл не предназначен для сцен и помещений, создания 3D по одному текстовому описанию, риггинга, анимации, PBR-текстур и деталей с точностью CAD.
Какие задачи решает
- создать скульптуру персонажа по одному изображению
- собрать трёхмерную модель фигурки или предмета
- сопоставить готовую модель с референсом
- записать процесс скульптинга в таймлапс
Примеры запросов агенту
- Создай 3D-скульптуру этого персонажа по изображению.
- Собери модель фигурки по этой фотографии и сохрани этапы в Blender.
- Сравни эту модель с референсом и покажи, где расходятся силуэт и поверхности.
Как установить image-to-sculpt
1Через маркетплейс плагинов
/plugin marketplace add gokayfem/image-to-sculpt/plugin install image-to-sculpt@image-to-sculptКоманда ставит плагин image-to-sculpt целиком, со всеми его скиллами
2Через Skills CLI (Vercel)
npx skills add gokayfem/image-to-sculpt --skill image-to-sculpt -a claude-code3Вручную: положить файлы
~/.claude/skills/image-to-sculpt/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/image-to-sculpt/
1Через Skills CLI (Vercel)
npx skills add gokayfem/image-to-sculpt --skill image-to-sculpt -a codex2Вручную: положить файлы
.agents/skills/image-to-sculpt/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add gokayfem/image-to-sculpt --skill image-to-sculpt -a cursor2Вручную: положить файлы
.cursor/skills/image-to-sculpt/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install gokayfem/image-to-sculpt skills/image-to-sculpt2Вручную: положить файлы
.github/skills/image-to-sculpt/SKILL.md1Через Skills CLI (Vercel)
npx skills add gokayfem/image-to-sculpt --skill image-to-sculpt -a gemini-cli2Командой платформы
gemini skills install https://github.com/gokayfem/image-to-sculpt --path skills/image-to-sculptВручную: положить файлы
.devin/skills/image-to-sculpt/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Claude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы об image-to-sculpt
Как установить image-to-sculpt в Claude Code?
Добавь маркетплейс командой /plugin marketplace add gokayfem/image-to-sculpt, затем установи скилл командой /plugin install image-to-sculpt@image-to-sculpt.
Что делает image-to-sculpt?
Создаёт замкнутую 3D-скульптуру по изображению, подгоняет видимые поверхности под референс и записывает этапы работы для Blender. Поддерживает экспорт в GLB, OBJ и STL.
Какие изображения подходят для image-to-sculpt?
Можно начать с рендера, фото предмета, рисунка или PNG с прозрачностью. Для невидимых сторон скилл использует сгенерированные виды; вместо них можно импортировать собственные фотографии.
Исходный текст
SKILL.md · MIT
---
name: image-to-sculpt
description: >-
Turns one image of any subject (an AI image, a render, a photo of a figurine or product, a drawing, or an idea
turned into an image first) into a watertight 3D sculpt that is measured against the image and recorded step by
step in Blender: front maps (mask, metric depth and focal length, normals), generated views of the unseen sides
(registered over the whole circle and screened), a visual hull, then many recorded fit passes against every
normal map, silhouette and the photo's depth, with symmetry, focus regions, gap cuts and smoothing. Ships a CLI
(`scripts/i2s.py`) for case scaffolding, fal calls with a budget, registration, carving, fitting, map checks,
Blender replay, timelapse and turntable films, exports (GLB, OBJ, STL) and a report. Use when the user wants a
3D model or sculpt "from this image", a figurine or character turned into a mesh, a sculpting timelapse, or a
check of a 3D model against a reference image. Not for scenes or rooms, text-to-3D without any image, rigging
or animation, PBR texturing, or CAD-accurate parts.
license: MIT
metadata:
hermes:
tags:
- 3d
- sculpting
- blender
- image-to-3d
- normal-maps
- photogrammetry
category: graphics
---
# Image 2 Sculpt
One image in, a sculpt out that you can prove: every surface the image shows is fitted to that image's own
normals, outline and depth in its own camera, every hidden surface comes from generated views that had to agree
with each other first, and every step of the build is recorded and replayed in Blender.
## Input routing
Any input ends in the same case layout (`i2s.py new CASE --input ...`). Details: `references/inputs.md`.
| Input | Do this | Notes |
|---|---|---|
| A character/creature/object render or AI image | `new` → `run` | the main path |
| A photo of a real object (figurine, toy, product, statue) | `new --kind photo` → `run` | MoGe gives real focal length and depth |
| A cut-out PNG with transparency | `new` → `run` | the alpha channel is the mask; no mask call |
| A busy image with several things in it | `prep --select "the red dragon"` | SAM-3 picks the subject |
| A drawing, sketch or flat illustration | `prep --restyle` | nano banana turns it into a 3D render first, keeping the pose |
| Several photos of the same object | `views --import DIR` | your photos replace generated views; angles found by registration |
| Only an idea | `imagine OUT.png "idea"` → `new` | a clean full-figure render to start from |
| No API key | a cut-out PNG (+ your own views) | front-only works too: the silhouette is inflated, depth behind is a guess |
## Workflow
Post a labelled visual at every checkpoint (`checks/sheet_*.png`, the views sheet, a turntable frame): images
first, numbers second. Fix rounds add steps; nothing recorded is ever edited.
1. **Scaffold.** `i2s.py new CASE --input IMG --subject "short noun phrase"`. Look at the image and write the
subject phrase yourself ("stocky cartoon troll", "ceramic owl figurine"): it goes into every view prompt. The
input is copied with its sha256 and padded to the nearest generator aspect ratio, so every view shares one lens.
2. **Front maps.** `i2s.py prep CASE` (mask, MoGe-3 depth + focal length, Marigold normals; units normalised to
the subject). Check `ref/front_mask.png` and `ref/front_normals.png` before going on. Wrong subject picked →
`--select`. Drawing → `--restyle`.
3. **Views.** `i2s.py views CASE` (9 views + 1 held out, ~$2 estimated; `--set minimal` for 5). Look at every
generated image: a changed pose, an extra limb or a cropped subject is a bad view. Registration will reject
views that disagree (IoU < 0.80 against the hull of the others), but say what you saw. Regions no view sees
need new views at angles that look into them (`--angles "-30:25"`), not more smoothing
(`references/views.md`).
4. **Hull.** `i2s.py hull CASE`: registration of every view (the asked-for angle is only a prior: left/right
swaps are found, front/back is kept), re-centring, screening, the recorded carve, symmetry detection. Read the
registered angles in `case.json`; `i2s.py symmetry CASE on|off` overrides the detected mirror plane.
5. **Fit.** `i2s.py fit CASE --stage all` (forms → surface → detail, 38 recorded passes), then `cut` (opens gaps
between fingers, legs, arm and body that the photo shows), `smooth` (removes webs and specks), `fit --stage
polish`. `i2s.py run CASE` does steps 2-8 in order with this default plan (`references/fitting.md`).
6. **Check and iterate.** `i2s.py check CASE` writes a sheet per view: reference, reference normals, sculpt,
normal error, silhouette difference. Look for lumps, webs, missing gaps, flattened features. Target them:
`parts CASE --prompt "hands"` then `fit --stage focus --region hands`, `cut --region hands`,
`smooth --region box:...` (`references/checking.md`). Never claim a fix without the before/after sheet.
7. **Finish, Blender, films.** `finish` (facet smoothing, OBJ/STL), `blender` (every step replayed from the photo's
camera, 360° turntable, each view, `sculpt.blend`, GLB), `film` (two-panel timelapse that ends in the 360°
turn, turntable, views sheet, hero image) (`references/blender-and-delivery.md`).
8. **Report and stop.** `report` writes `out/REPORT.md`, `out/index.html` and the per-step chart. Present the
timelapse, the views sheet and the measured table, say what is weak, and stop. The user decides what next.
## Hard rules
- **The photo governs what it sees.** Generated views only fill in where the photo does not see; their depth is
never used (it disagrees by centimetres between views). Never average a generated view's normals over the photo's.
- **Register every view; never trust the requested angle.** Generated views were off by 20–155° on the troll,
mostly left/right swaps. The search allows those but keeps front views in front and back views behind (a
symmetric subject's back outlines like its front). Read the registered angles in `case.json`.
- **Screen before you carve.** A view that disagrees with the others is a different subject or pose: reject it
(and say so) rather than cutting the sculpt with it.
- **Hold one view out.** It never moves the surface; its camera is frozen before fitting. Report it separately
from the views used to fit. It is generated too, so it measures consistency, not truth.
- **Measure, don't eyeball alone.** IoU, outline distance, normal angle, roughness against the reference's own
roughness, the photo's depth. One number never stands for "quality": report them side by side.
- **Distance fields stay exact.** Every operation re-distances the grid (exact triangle distances in a band, EDT
beyond). Offsetting an inexact field, mirroring the field itself, or blurring normal targets made staircases,
moiré rings and flattened noses in the case this was built from (`references/lessons.md`).
- **Record everything.** Every carve, pass, cut and smoothing is a step in `build/steps/` and `build/log.jsonl`,
replayed in Blender and shown in the timelapse. Never edit a recorded step; add a new one.
- **Paid calls:** every fal call goes through the case budget (`settings.budget_usd`), its request id is saved in
`case.json` before waiting, and nothing is resubmitted blindly. `FAL_KEY` is never printed or written.
- **Visual feedback at every checkpoint**, and frame 0 of every film is a finished thumbnail.
- **Say what is invented.** The back of a subject seen only from the front is the generator's guess.
## References
| File | Read when |
|---|---|
| `references/inputs.md` | routing an unusual input; masks, restyle, select, imported photos, idea-only |
| `references/views.md` | generating, judging, registering, screening and adding views |
| `references/fitting.md` | what a pass does, stages, parameters, cut / smooth / focus, the default plan |
| `references/checking.md` | reading map sheets and metrics, the held-out view, what to fix next |
| `references/blender-and-delivery.md` | Blender replay, films, exports, the report, the review page |
| `references/conventions.md` | world frame, cameras, units, file formats (for writing new tools) |
| `references/lessons.md` | what went wrong on the first cases and why the rules above exist |
Templates: `templates/CONTRACT.md` (copied into every case), `templates/acceptance.json` (targets).
© gokayfem · MIT · gokayfem/image-to-sculpt