Video to 3d
Turn a single-character A-pose orbit video or an approved whole multi-view character sheet into an editable Blender model using local MiniMax H3 MAIN/H3 IR generation when needed, measured 8-72 angle evidence, calibrated Blender overlays, detailed per-angle visual modeling, and final topology/beauty review. Use for fixed-subject character turntables and Blender reconstruction; do not use for action footage, moving subjects, direct neural-mesh generation, or photogrammetry capture.
Install
npx skills add enwong93-sketch/video-to-3d --skill video-to-3dgit clone --depth 1 https://github.com/enwong93-sketch/video-to-3d.git /tmp/video-to-3d
mkdir -p ~/.claude/skills
cp -r /tmp/video-to-3d/. ~/.claude/skills/video-to-3dPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Video to 3D Build an editable Blender character from source-backed angle evidence. Treat the video as a measured view set, not as a magical multi-view reconstruction input. The finished `.blend`, calibrated cameras, reference images, model parts, and review evidence remain inspectable and reproducible. ## Non-negotiable outcome - Use 8-72 independently decoded real source angles, divisible by four; default to 24. Use more only when the video has enough sharp, identity-stable frames. - Establish true view angles from observed timecodes. A prompt that asks for constant speed is not proof that the resulting video is constant-speed. - Import every admitted view into Blender on its matching calibrated orthographic camera. One global model scale and origin must serve every camera. - At every retained geometry milestone, compare silhouette, scale, proportions, and visible design against the corresponding reference at every admitted angle. - At every admitted angle, superimpose the calibrated full-resolution reference over the shared model and inspect the actual visible form in Blender. Use reference-only, model-only, clay/wireframe, and adjustable-alpha overlay views; add close-ups wherever a part cannot be judged at full-body scale. - Detailed visual judgment drives modeling. Pixel counts, IoU, XOR, scanline deltas, bounding-box ratios, or automated edge corrections must never prescribe vertex movement, replace artistic
Details
- Skill name
video-to-3d- Repository
- enwong93-sketch/video-to-3d
- License
- MIT
- Repo updated
- 8 September 2026
FAQ
What does the Video to 3d skill do?
Turn a single-character A-pose orbit video or an approved whole multi-view character sheet into an editable Blender model using local MiniMax H3 MAIN/H3 IR generation when needed, measured 8-72 angle evidence, calibrated Blender overlays, detailed per-angle visual modeling, and final topology/beauty review. Use for fixed-subject character turntables and Blender reconstruction; do not use for action footage, moving subjects, direct neural-mesh generation, or photogrammetry capture.
How do I install the Video to 3d skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add enwong93-sketch/video-to-3d --skill video-to-3d. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Video to 3d popular?
It lives in enwong93-sketch/video-to-3d, which has 12 GitHub stars and 0 forks.
Related skills
Ecom Adds
8Samin12/ecom-adds
Generate 4 scroll-stopping e-commerce ad creatives for a product using deep customer research, competitor ad analysis via Facebook Ads Library, reference image sourcing via Tavily, and image generation via Nano Banana 2 (Gemini). Use when the user asks to create ads, ad creatives, DTC ads, Facebook/Instagram ads, or generate advertising images for a product.
Image Audit
12xiaowu89/skill-function
对图片进行鉴黄、政治、暴恐内容审核。先将图片压缩到 500px/JPEG 后直传 NX API 审核，以表格汇总结果。适用于用户提到图片审核、内容检查、鉴黄、政治识别、暴恐识别、违规扫描、图片安全、JPG/PNG/WebP 审核的场景。
Podcast From Research
9Easternguy/podcast-from-research
Research-to-podcast pipeline for learning new topics: 20-angle full-coverage research (with blind-spot discovery) → steered NotebookLM audio overview → MP3 delivered to you, with everything ingested into a local GBrain knowledge base for permanent recall. When the user says "create a podcast on X", this handles it end-to-end. Installs its own dependencies (notebooklm-py, GBrain) if missing.
Gpt Images
12lukasersil/gpt-images
Turns a plain-language brief into a production-ready prompt for OpenAI GPT Image models (ChatGPT Images 2.5, gpt-image-2.5-flare, gpt-image-2.5-sunburst, gpt-image-2). Returns a seven-block prompt, a settings block for the chosen surface, and three concrete levers for the next iteration. Covers text inside the image, reference binding, edits that do not drift, transparent backgrounds, and the hard API limits on size, quality and input images. Triggers: 'write an image prompt', 'gpt image prompt', 'chatgpt images 2.5', 'make me a poster', 'product shot prompt', 'article cover image', 'edit this
Layered Holo Card
10JamesonZGJ/layered-holo-card-skill
Turn an existing photo or artwork into a layered 2.5D holographic collectible card while preserving its composition and subject pixels. Use for floating subjects, layered photo cards, or 把照片做成主体浮起的全息闪卡; not for redesigning the image or flat whole-card tilt alone.
Genpark Snap Sell
12alphaparkinc/genpark-snap-sell
Sell anything with a single photo. An autonomous creator monetization agent that turns an image into a live, zero-fee Stripe checkout page in seconds.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.