CommunityImagegithub.com

Game Asset Pipeline

Local AI game asset generation pipeline for sprites, textures, 3D props, and video. Covers model selection, workflows, quality, and licensing for indie game dev.

What is Game Asset Pipeline?

Game Asset Pipeline is a Claude Code agent skill that local AI game asset generation pipeline for sprites, textures, 3D props, and video. Covers model selection, workflows, quality, and licensing for indie game dev.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/konqiDAM/void-skills/tree/HEAD/game-asset-pipeline

Installed? Explore more Image skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Game Asset Pipeline — Local AI

Machine

  • Windows 10, RTX 3090 24 GB, 28 GB RAM (→40 GB), Xeon E5-2696 v4
  • ComfyUI 0.44.0 at D:\AI\ComfyUI, models at D:\AI\models\
  • Docs: D:\AI\SETUP_DOCUMENTATION.md, D:\AI\HANDOFF.md, D:\AI\PROJECTS.md

Task → Model mapping

TaskModelWorkflowNotes
Fast general imagesZ-Image Turbo (int8/FP8)image_z_image_turbo_int8.json8-9 steps, CFG 1.0, 1024-1344px
Anime illustrationNova Anime XL v19 / Prefect Pony XL v6nova_anime_xl_v19.json / prefect_pony_xl_v6.json28 steps, CFG 5-6, CLIP skip 2
Structure-guided (pose/depth/canny)Z-Image Turbo + ControlNet Unionimage_z_image_turbo_fun_union_controlnet_int8.jsonInput image drives structure
Sprites (pixel art)SDXL + Pixel-Art-XL LoRA (not installed yet)To be createdDownscale nearest-neighbor, palette-limit
Tileable texturesZ-Image Turbo or SDXL + tileable LoRATo be created+ TextureAlchemy PBR extraction
3D propsPixal3D / TRELLIS.2 (native)3d_pixal3d_trellis2_image_to_model.jsonGLB + PBR, 1024-1536px
Video clipsMiniMax H3 (Ref2VA)video_minimax_h3_r2v_safe.json5s 864x480, 4-step turbo; 15s ~23 min
Concept art / skyboxesZ-Image Turbot2i workflowEquirectangular LoRA for 360 skies

Sprite pipeline

  1. Generate at 1024 with SDXL + Pixel-Art-XL LoRA (or Z-Image + pixel style).
  2. Downscale with nearest-neighbor to 32/48/64/96/128 px.
  3. Palette-limit to 16-32 colors (Aseprite / Pixelorama).
  4. Manual cleanup (fix stray pixels, align silhouette).
  5. Consistency: lock seed, ControlNet OpenPose for poses, or train a character LoRA.
  6. Animation: generate key poses with ControlNet; hand-clean; pack sprite sheet.

Honest limits: AI makes "pixel-art-like" images, not true pixel grids. Walk cycles need hand-cleaning. Cloud tools (PixelLab, Retro Diffusion, Sprite AI) are more turnkey for animation, but local wins on privacy/cost/style consistency.

Texture pipeline

  1. Tileable albedo: SDXL + tileable LoRA or Z-Image Turbo, 1024/2048, top-down prompt.
  2. Seamless fix: TextureAlchemy "Seamless Tiling Maker" + inpaint seam.
  3. PBR extraction: TextureAlchemy (Marigold/Lotus) → normal, roughness, metallic, AO, height, curvature.
    • Alternative: CHORD (Ubisoft, research-only — not for commercial).
  4. Post: Texture Equalizer (remove baked lighting), channel-pack ORM for Unity/Unreal.
  5. Upscale to 2K/4K with SeedVR2 (conservative, open source) or ESRGAN (fast).

Honest limits: organic/stylized materials are great; precise parametric architecture (brick patterns) still belongs in Substance Designer. CHORD is research-only.

3D pipeline

  1. Concept image (Z-Image Turbo) — clean background, front view. Optional multi-view.
  2. Image-to-3D: ComfyUI template "Pixal3D & TRELLIS.2" → GLB + PBR.
    • Boolean off = Pixal3D (better input fidelity), on = TRELLIS.2 (complex topology).
  3. Post-process in ComfyUI (remesh, decimate, fill holes, smooth normals) or Blender.
  4. Retopo/UV/LOD/collision in Blender; game-ready pass.
  5. Rig: SkinTokens (MIT, auto-rig, ~6 GB GGML) or Mesh2Motion (free, local, Mixamo-like).
  6. Export FBX/GLB to engine.

Honest limits: static props are usable after cleanup; characters need manual rigging/weight painting; animation is the hard part. Closed-source cloud (Meshy, Tripo, Rodin) still better for characters.

Consistency and automation

  • Workflow JSONs live in the project repo. Commit them; same workflow + seed = reproducible output.
  • Staging folder discipline: output → staging/, human review, then move to engine project.
  • ComfyUI API: POST workflow JSON to /prompt; poll /history or use websocket.
  • LoRA training: Kohya sd-scripts. SDXL 12-16 GB, FLUX 16-24 GB. 10-30 images, 1024px, 1000-2500 steps. This is the key to a coherent art style.

Licensing (personal use = no restrictions; for commercial:)

CategoryModelsCommercial?
Apache 2.0 / MITZ-Image/Turbo, FLUX.2 klein 4B, FLUX.1 schnell, Qwen-Image/2512, ERNIE, HiDream (MIT), GLM (MIT), LongCat, Pixal3D, TRELLIS.2 (MIT), SkinTokens (MIT), Mesh2MotionYes
Revenue-cappedFLUX 3 Klein (<$5M + filters/review), SD 3.5 (<$1M), Krea 2 (<$1M), Stable Fast 3D (<$1M)Under threshold
Non-commercialFLUX.1 dev, FLUX.2 dev/klein 9B, Qwen-Image-2.1, Ideogram 4, HunyuanImage-3.0 (territorial)No
Research-onlyCHORD (Ubisoft PBR), Marigold/Lotus (check)Prototype only

Also: Steam requires AI disclosure for shipped games. Civitai LoRAs have individual licenses. US copyright requires human authorship.

What's installed vs. not

Installed: Z-Image Turbo, Nova Anime XL, Prefect Pony XL, Pixal3D, TRELLIS.2, MiniMax H3, ControlNet Union, BiRefNet, MoGe, DINOv3.

NOT installed (available on request): SDXL base, FLUX, pixel-art LoRAs, SDXL ControlNet, H3 FL2VA, upscale models (ESRGAN/SeedVR2), texture LoRAs, Kohya training tools, Krita AI Diffusion, Aseprite/Pixelorama.

References

  • D:\AI\SETUP_DOCUMENTATION.md — full 13-section reference
  • D:\AI\HANDOFF.md — agent quick reference (install procedures)
  • D:\AI\PROJECTS.md — project tracker
  • D:\AI\README.txt — user quick reference
  • Prompt repos: booru-prompt-gallery, sd-akashic, SupaGruen cheat sheet, Dalabad templates, roblaughter style-reference, zsky prompt library

Related Skills