Not in the top 1,000 by GitHub stars

LaurentiuGabriel/unreal-game-assets-creation-skill

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

bd5858064d9c → bd5858064d9c

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit bd5858064d9c0c09b1b8a17afc394e2759e60e0c

148GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days

Heat

0.3
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Oct 25, 2026148

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

text-to-3d-asset

When your agent uses it

Generate a game-ready 3D asset by running the local AI pipeline sequentially: Fooocus (SDXL text-to-image) -> Hunyuan3D-2 (image-to-textured-GLB) -> optional Blender FBX convert + Unreal import. Use when the user wants to create/generate a 3D model, mesh, or racer for the Unreal train-racer project from a text prompt or a photo. Covers launching both local Gradio services, generating, and wiring the result into Unreal.

What it loads into context

Frontmatter

128 tokens

Always available to the agent

SKILL.md

2,577 tokens

When the skill is activated

Reference documents

1,214 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. ⚠<U+FE0F> Hardware rule (RTX 4070 Laptop, 8 GB VRAM / 32 GB RAM) — STRICT
  2. Key paths
  3. Stage 1 — Generate the image (Fooocus SDXL)
  4. Stage 2 — Image -> textured GLB (Hunyuan3D-2) [core, validated]
  5. Stage 3 — Import into Unreal (optional; needs the editor + unreal-mcp running)
  6. Troubleshooting

Scripts executed separately

  • scripts/fooocus_gen.py
  • scripts/glb_to_fbx.py
  • scripts/hunyuan_gen.py

Files

  • .gitignoreasset45 bytes
  • README.mddoc4,214 bytes
  • SKILL.mdcore8,584 bytes
  • SKILL.mdcore8,584 bytes
  • SKILL.mdcore8,584 bytes
  • SKILL.mdcore8,584 bytes
  • docs/demo.gifasset831,917 bytes
  • scripts/fooocus_gen.pyruns2,425 bytes
  • scripts/glb_to_fbx.pyruns1,181 bytes
  • scripts/hunyuan_gen.pyruns3,041 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

  • text-to-3d-asset

Repository facts

License
No license detected
Created
Jul 24, 2026
Last pushed
Jul 24, 2026
Forks
3
Open issues
0
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 3 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 48 signals by file

README.md

  • Network accessline 3
    A [Claude Code](https://claude.com/claude-code) **skill** that turns a text prompt or a photo into a
  • Network accessline 30
    | Stage | Tool | Output | |-------|------|--------| | 1. Text → image *(optional)* | [Fooocus](https://github.com/lllyasviel/Fooocus) SDXL, driven headlessly via the [Fooocus-API](https://github.com/mrhan1993/Fooocus-API) REST wrapper | `.p
  • Network accessline 31
    |-------|------|--------| | 1. Text → image *(optional)* | [Fooocus](https://github.com/lllyasviel/Fooocus) SDXL, driven headlessly via the [Fooocus-API](https://github.com/mrhan1993/Fooocus-API) REST wrapper | `.png` | | 2. Image → 3D | [H
  • Network accessline 32
    | 1. Text → image *(optional)* | [Fooocus](https://github.com/lllyasviel/Fooocus) SDXL, driven headlessly via the [Fooocus-API](https://github.com/mrhan1993/Fooocus-API) REST wrapper | `.png` |
  • Network accessline 33
    | 2. Image → 3D | [Hunyuan3D‑2](https://github.com/Tencent-Hunyuan/Hunyuan3D-2) (image‑to‑textured‑mesh) | textured `.glb` |
  • Network accessline 34
    | 3. Convert | [Blender](https://www.blender.org/) headless (`glTF → FBX`, embedded textures) | `.fbx` |
  • Network accessline 50
    - **Windows** with an **NVIDIA GPU (8 GB VRAM works; more is better)** and recent drivers. - [Hunyuan3D‑2](https://github.com/Tencent-Hunyuan/Hunyuan3D-2) running locally (this skill was set up
  • Network accessline 51
    - [Hunyuan3D‑2](https://github.com/Tencent-Hunyuan/Hunyuan3D-2) running locally (this skill was set up
  • Network accessline 52
    with the [WinPortable build](https://github.com/YanWenKun/Hunyuan3D-2-WinPortable)); its texture
  • Network accessline 53
    extensions (`custom_rasterizer`, `differentiable_renderer`) compiled against a CUDA toolkit matching   its PyTorch build. - [Fooocus](https://github.com/lllyasviel/Fooocus) + the [Fooocus-API](https://github.com/mrhan1993/Fooocus-API)
  • Network accessline 54
    its PyTorch build. - [Fooocus](https://github.com/lllyasviel/Fooocus) + the [Fooocus-API](https://github.com/mrhan1993/Fooocus-API)   wrapper (only needed for Stage 1 text‑to‑image).
  • Network accessline 55
    - [Fooocus](https://github.com/lllyasviel/Fooocus) + the [Fooocus-API](https://github.com/mrhan1993/Fooocus-API)
  • Network accessline 56
    wrapper (only needed for Stage 1 text‑to‑image). - [Blender 4.x](https://www.blender.org/) (only for Stage 3 FBX conversion). - An Unreal project with the `unreal-mcp` server (only for Stage 4 import).
  • Network accessline 57
    - [Blender 4.x](https://www.blender.org/) (only for Stage 3 FBX conversion).
  • Network accessline 88
    Built with [Claude Code](https://claude.com/claude-code). Wraps the excellent open‑source projects

SKILL.md

  • Network accessline 40
    |---|---| | Fooocus | `C:\projects\unreal-game\Fooocus_win64_2-5-0` (launch `run.bat`) | | Fooocus UI | http://localhost:7865 |
  • Network accessline 41
    | Fooocus | `C:\projects\unreal-game\Fooocus_win64_2-5-0` (launch `run.bat`) | | Fooocus UI | http://localhost:7865 | | Fooocus outputs | `C:\projects\unreal-game\Fooocus_win64_2-5-0\Fooocus\outputs\<YYYY-MM-DD>\` |
  • Network accessline 42
    | Fooocus UI | http://localhost:7865 |
  • Network accessline 43
    | Fooocus outputs | `C:\projects\unreal-game\Fooocus_win64_2-5-0\Fooocus\outputs\<YYYY-MM-DD>\` | | **Fooocus-API (REST)** | `C:\AI\Fooocus-API` — isolated `python_embeded`; `config.txt` reuses models | | Fooocus-API endpoint | http://127.0
  • Network accessline 44
    | **Fooocus-API (REST)** | `C:\AI\Fooocus-API` — isolated `python_embeded`; `config.txt` reuses models | | Fooocus-API endpoint | http://127.0.0.1:8888 — `POST /v1/generation/text-to-image` | | Hunyuan3D | `C:\AI\HY3D2\Hunyuan3D2_WinPortabl
  • Network accessline 45
    | Fooocus-API endpoint | http://127.0.0.1:8888 — `POST /v1/generation/text-to-image` |
  • Network accessline 46
    | Hunyuan3D | `C:\AI\HY3D2\Hunyuan3D2_WinPortable` (launch `launch_server.bat`) | | Hunyuan3D UI/API | http://localhost:8080 | | Bundle python (has gradio_client) | `C:\AI\HY3D2\Hunyuan3D2_WinPortable\python_standalone\python.exe` |
  • Network accessline 47
    | Hunyuan3D UI/API | http://localhost:8080 |
  • Network accessline 71
    2. Launch if port 8888 isn't up (run from its dir so `./config.txt` is found):    `cmd /c "cd /d C:\AI\Fooocus-API && python_embeded\python.exe -s main.py --skip-pip --disable-preset-download --port 8888 --host 127.0.0.1 > C:\AI\Fooocus-API
  • Network accessline 72
    `cmd /c "cd /d C:\AI\Fooocus-API && python_embeded\python.exe -s main.py --skip-pip --disable-preset-download --port 8888 --host 127.0.0.1 > C:\AI\Fooocus-API\api.log 2>&1"`    Wait for `Uvicorn running on http://127.0.0.1:8888` in `api.log
  • Network accessline 73
    Wait for `Uvicorn running on http://127.0.0.1:8888` in `api.log` (loads SDXL, ~20–40 s).
  • Network accessline 78
    ### Method B — Fooocus UI (fallback, manual click) Launch `cmd /c "cd /d C:\projects\unreal-game\Fooocus_win64_2-5-0 && run.bat"` (cold start ~5–6 min; poll **port 7865**, the log doesn't flush). Open http://localhost:7865, enter prompt, cl
  • Network accessline 79
    Launch `cmd /c "cd /d C:\projects\unreal-game\Fooocus_win64_2-5-0 && run.bat"` (cold start ~5–6 min; poll **port 7865**, the log doesn't flush). Open http://localhost:7865, enter prompt, click Generate, grab the newest PNG from `Fooocus\out
  • Network accessline 80
    poll **port 7865**, the log doesn't flush). Open http://localhost:7865, enter prompt, click Generate,
  • Network accessline 89
    1. Ensure the server is up (it does **not** persist across sessions):    `Invoke-WebRequest http://localhost:8080 -UseBasicParsing`. If down, launch in background:
  • Network accessline 90
    `Invoke-WebRequest http://localhost:8080 -UseBasicParsing`. If down, launch in background:
  • Network accessline 91
    `cmd /c "C:\AI\HY3D2\Hunyuan3D2_WinPortable\launch_server.bat > C:\AI\HY3D2\server.log 2>&1"`    then watch `C:\AI\HY3D2\server.log` for `Uvicorn running on http://0.0.0.0:8080` (~1–2 min; models cached). 2. Generate (uses the running serve
  • Network accessline 92
    then watch `C:\AI\HY3D2\server.log` for `Uvicorn running on http://0.0.0.0:8080` (~1–2 min; models cached).

scripts/fooocus_gen.py

  • Executable scriptline 1
    Executable file
  • Network accessline 17
    ap.add_argument("--negative", default="blurry, multiple objects, cluttered background, text, watermark")     ap.add_argument("--out", required=True, help="output PNG path")     ap.add_argument("--url", default="http://127.0.0.1:8888")
  • Network accessline 18
    ap.add_argument("--out", required=True, help="output PNG path")     ap.add_argument("--url", default="http://127.0.0.1:8888")     ap.add_argument("--performance", default="Speed",
  • Network accessline 19
    ap.add_argument("--url", default="http://127.0.0.1:8888")
  • Network accessline 36
    print(f"[fooocus] generating: {args.prompt!r}", flush=True)     t0 = time.time()     r = requests.post(args.url + "/v1/generation/text-to-image", json=payload, timeout=1800)
  • Network accessline 37
    t0 = time.time()     r = requests.post(args.url + "/v1/generation/text-to-image", json=payload, timeout=1800)     r.raise_for_status()
  • Network accessline 38
    r = requests.post(args.url + "/v1/generation/text-to-image", json=payload, timeout=1800)
  • Network accessline 45
    if u.startswith("/"):         u = args.url + u     png = requests.get(u, timeout=120).content
  • Network accessline 46
    u = args.url + u     png = requests.get(u, timeout=120).content     os.makedirs(os.path.dirname(os.path.abspath(args.out)), exist_ok=True)
  • Network accessline 47
    png = requests.get(u, timeout=120).content

scripts/glb_to_fbx.py

  • Executable scriptline 1
    Executable file

scripts/hunyuan_gen.py

  • Executable scriptline 1
    Executable file
  • Network accessline 18
    ap.add_argument("--name", default=None, help="basename for output (defaults to image name)")     ap.add_argument("--mode", choices=["textured", "shape"], default="textured")     ap.add_argument("--url", default="http://localhost:8080")
  • Network accessline 19
    ap.add_argument("--mode", choices=["textured", "shape"], default="textured")     ap.add_argument("--url", default="http://localhost:8080")     ap.add_argument("--seed", type=int, default=1234)
  • Network accessline 20
    ap.add_argument("--url", default="http://localhost:8080")

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 48 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.