neilsonnn

⭐ image-blaster ⭐ neilsonnn/image-blaster 1. 사진 한 장으로 3D 공간을 만들어주는 클로드 스킬 모음이 나옴 2. 이미지 한 장만 넣으면 5분 안에 3D 환경까지 뽑아줌. 3D 작업 초반 밑그림 잡을 때 쓰라고 만든 도구 3. 움직이는 물체는 3D 모델(.glb, .obj), 안 움직이는 배경은 둘러볼 수 있는 3D 장면(.spz), 거기에 배경 소리와 물체별 효과음(.mp3)까지 만들어줌. "단계마다 나한테 확인받으면서 해줘"라고 시킬 수도 있음 4. 게임 레벨 콘셉트, 어릴 적 내 방, 로봇용 환경, 영화 촬영지 헌팅, 건축 렌더링 같은 데 쓰라고 소개함. Unity·Unreal·Godot·Blender·Three.js에도 넣어 쓸 수 있음 5. MIT 무료, 스타 1.2만 개. 클로드 코드와 World Labs·FAL API 키 필요 설치: git clone neilsonnn/image-blaster 사진 한 장으로 게임 배경이랑 효과음까지 뚝딱 뽑는 시대인 듯. ━━━━━━━━━━ 🇺🇸 1. A set of Claude skills that turns a single photo into a 3D world 2. Drop in one image and get a 3D environment in under 5 minutes. Built to jumpstart 3D work 3. Moving objects come out as 3D models (.glb, .obj), the static background as an explorable 3D scene (.spz), plus ambient sound and per-object sound effects (.mp3). You can also tell it "confirm each step with me" 4. Pitched for game level concepts, your childhood bedroom, robot environments, film location scouting, and architectural renders. Works with Unity, Unreal, Godot, Blender, and Three.js 5. Free under MIT, 11.9k stars. Needs Claude Code plus World Labs and FAL API keys Install: git clone neilsonnn/image-blaster Feels like we can now turn one photo into a game scene with sound effects in minutes. #AI #ClaudeCode #3D #GameDev #OpenSource

image-blaster: the real cost of one image 3D world One image in, a walkable 3D environment out in under five minutes. That is the pitch on neilsonnn/image-blaster — 11.8k stars, MIT, front page of Hacker News in May 2026. Built by a World Labs team member (not an official World Labs product), it chains Marble, Hunyuan 3D, nano-banana and ElevenLabs behind a Claude Code skill. Two questions decide whether you can use it, and the eight English write-ups I could find answer neither: 1. What does one run actually cost? (Short answer: the world is fixed at ~$1.34; every dynamic object adds ~$0.46.) 2. Can you drop the outputs into an engine? (Short answer: not before you apply a scale correction the CLI never applies for you.) Both answers are below, with code references and prices as of 2026-10-21. What it actually is Not an app — a skill pack for Claude Code. You clone the repo, run claude inside it, hand Claude two API keys (World Labs + FAL), drop an image into input/, and say blast it and confirm each step with me. | | | |---|---| | Repo | neilsonnn/image-blaster, MIT | | Timeline | created 2026-04-21, last push 2026-05-15; 11,794 ★ (snapshot 2026-10-21) | | Form | .claude/skills/* + Node scripts | | Requires | Claude Code CLI + World Labs key + FAL key | | Outputs | dynamic objects .glb/.obj; static environment .spz; SFX .mp3 | The three outputs are not the same kind of thing, and that is where every downstream problem starts: | Output | Format | What it is | What it is not | |---|---|---|---| | Static environment | .spz | a Gaussian-splat scene you can walk through | not a mesh — no faces, no UVs; needs splat render support | | Dynamic objects | .glb / .obj | one real mesh per object | not a scene — you place them yourself | | SFX | .mp3 | ambient loop + per-object impact | not a mixed audio system | The pipeline, as it actually executes (read from the scripts, not the README): input/ image ├─① clean plate / object cut-outs fal-ai/nano-banana-2/edit $0.08/img ├─② static environment World Labs marble-1.1 1,500 credits │ └→ .spz (full_res + 500k + 100k + 150k downloaded) │ └→ collider mesh .glb (100–200k triangles) ├─③ each dynamic object fal-ai/hunyuan-3d/v3.1/pro/... $0.375/call │ (or .../rapid $0.225, fal-ai/meshy/v6 $0.80) └─④ SFX fal-ai/elevenlabs/sound-effects/v2 $0.002/sec Two details that matter and are easy to miss: - Every object costs one image edit before the 3D call. The image-blast-3d skill instructs Claude to first write a cut-out prompt ("Isolate the <object> … white background, centered, tight crop"). So an object is edit + 3D, not 3D. - SFX go through FAL, not ElevenLabs directly (fal-ai/elevenlabs/sound-effects/v2). If you price this off ElevenLabs credit tables you will be off by an order of magnitude. The skill's defaults: ambient --loop --count 2 --duration-seconds 10, per object --count 4 --duration-seconds 1. The bill Prices below are the vendors' own pages, checked 2026-10-21. | Item | Price | Source | |---|---|---| | World Labs credits | $1.00 = 1,250 credits; minimum purchase $5 | docs.worldlabs.ai/api/pricing | | World generation marble-1.1 | 1,500 credits = $1.20 | same | | Pano generation (non-pano image) | +80 credits = $0.064 | same | | HQ mesh export | 3,500 credits = $2.80 | same (this pipeline never calls it) | | Image edit nano-banana-2/edit | $0.08 / image (2K/4K ×1.5) | FAL model page | | Object 3D hunyuan-3d/v3.1/pro | $0.375 / generation | FAL model page | | Object 3D .../rapid | $0.225 / generation | FAL model page | | Object 3D meshy/v6 | $0.80 / generation | FAL model page | | SFX elevenlabs/sound-effects/v2 | $0.002 / second | FAL model page | Which reduces to a very simple structure: fixed per run = world 1.264 (1,500 + 80 credits) + one plate edit 0.08 ≈ $1.34 per object = cut-out edit 0.08 + 3D 0.375 + impact SFX 4s × 0.002 ≈ $0.46 | Scene | Math | Total | |---|---|---:| | 1 object | 1.34 + 0.46 | ≈ $1.81 | | 5 objects (one room) | 1.34 + 5 × 0.46 | ≈ $3.66 | | 20 objects (street / level) | 1.34 + 20 × 0.46 | ≈ $10.60 | | 20 objects on rapid | 1.34 + 20 × (0.08 + 0.225 + 0.008) | ≈ $7.62 | | 20 objects on meshy v6 | 1.34 + 20 × (0.08 + 0.80 + 0.008) | ≈ $19.10 | Three non-obvious consequences: 1. The world is the cheap part. Marble renders an entire environment for $1.26; five small props cost twice that. Your budget is a function of object count, not canvas size. 2. The $2.80 HQ mesh export is not in the loop. generate-world.mjs only pulls assets.mesh.collider_mesh_url — the 100–200k-triangle collision mesh. If you want a static mesh you can actually look at, you have to go back to Marble and export the HQ version separately: ~600k triangles with textures (or ~1M with vertex colors), up to an hour, rate-limited to 4/hour, Pro plan. 3. Failures are billable. Unhappy with face count? Re-run: another $0.375. Bad cut-out? Another $0.08. This is exactly why the skill's default posture is confirm each step with me. > Scope: these are estimates derived from the pipeline structure and public unit prices, not our own invoice. No retries, no plan differences (Free can generate worlds but cannot export; Standard covers splat/collider exports; Pro adds HQ mesh + commercial rights). The part nobody writes about: the .spz is not in metric space World Labs documents this in api/rendering-spz: > Marble SPZ files are exported in the generated asset coordinate frame. When you render them outside Marble, use assets.splats.semantics_metadata to convert Gaussian centers and Gaussian sizes into metric, ground-aligned coordinates. | Field | Job | |---|---| | metric_scale_factor | raw generated units → meters | | ground_plane_offset | puts the metric ground plane at y = 0 | | flip_y (optional) | Y-axis orientation (SPZ defaults to RUB, Unreal is Z-up) | So: is it handled? I grepped the whole repo (2026-10-21, main): | Location | Reads semantics_metadata? | |---|---| | app/src/components/WorldViewer.tsx (bundled React viewer) | Yes — metric_scale_factor, ground_plane_offset, flip_y, defaults 1 / 0 | | .claude/scripts/** (the CLI pipeline that hands you the files) | No — downloads spz_urls and collider_mesh_url, nothing else | Which means: it looks right in the bundled viewer because the viewer applies the correction, and it is wrong in Unity / Unreal / Blender / three.js because the exported files don't carry it. Symptoms: a door 30+ units tall, everything floating above or sunk into the floor, and props misaligned against the splat they were generated from. // three.js: the loader reads the file, it does not fix the frame const world = await new SPZLoader().loadAsync(url); const m = semantics.metric_scale_factor; world.scale.setScalar(m); world.position.y -= semantics.ground_plane_offset; Apply the same factor to the collider mesh (inference — the docs only spell this out for splats, but both come from the same generated frame). What the outputs really are | Output | Official spec | Who reads it natively | |---|---|---| | Splat .spz (full res) | ~2M splats | three.js (SPZLoader in addons); Unity / Unreal / Blender / Houdini need community splat plugins | | Splat .spz (low res) | ~500k / 100k / 150k | same; lower res is what you actually want in-engine | | Splat .ply | ~2M / ~500k | widest compatibility, much bigger — SPZ is roughly 10× smaller than the equivalent PLY | | Collider .glb | 100–200k triangles | any engine; it is a physics proxy, not a render mesh | | HQ .glb (Pro) | ~600k textured / ~1M vertex-color | any engine; not produced by this pipeline | Ten-minute acceptance checklist | # | Check | How | If it fails | |---|---|---|---| | 1 | Units are meters | measure a known reference (2 m door) | apply metric_scale_factor | | 2 | Ground at y = 0 | splat floor on the zero plane | subtract ground_plane_offset | | 3 | Orientation | upside down → flip_y; rotated → world yaw | flip / rotate | | 4 | Splat and mesh share scale | overlay the same chair twice | use one factor for both | | 5 | Face count holds up close | zoom to player distance | re-run with --face-count (billed again) | | 6 | Collider ≠ render mesh | 100–200k tri file is the collider | keep both, don't swap | | 7 | File size | prefer low-res .spz in-engine | see the payload comparison link below | | 8 | Licensing | code is MIT; assets are generated by third-party APIs | Marble commercial rights sit on Pro; check each vendor | Four things that will bite you 1. Static/dynamic split errors → ghosting. The splat already contains the chair; generate a mesh of the chair and now you have two. Wrong split = double image, and an extra object you didn't want costs $0.46. 2. The splat/mesh boundary leaks. Splats have no geometry, cast no shadows, don't receive light like meshes. Contact shadows and occlusion at the seam won't match. (Inference: add AO blob decals under meshes, or cover the contact band with mesh.) 3. The 50k default is the skill's, not the API's. Hunyuan's own default is 500,000 faces. Background props are fine; hero objects look generated up close. 4. SFX are materials, not an audio system. Two 10-second ambient loops, four 1-second impacts per object. No rolling, no sustained sounds, no material variation. Non-loop output gets trimmed and loudness-normalized by ffmpeg; loop output is left raw for seamlessness. When not to use it | You want | Why not | Instead | |---|---|---| | One model, no scene | the $1.34 world is wasted | call the FAL model directly | | Precise dimensions | generation isn't dimension-driven | parametric CAD workflow | | Editable topology / clean UVs | you get "scanned" topology | rebuild from the form (Mesh2CAD route) | | Offline / on-prem | the whole chain is two cloud APIs | local text-to-3D (e.g. TRELLIS.2 in-browser) | | Team doesn't use Claude Code | it's a skill pack, not a GUI app | drive the scripts yourself | | Clean commercial rights | assets come from multiple vendors | verify each license | The one thing it is genuinely good at: you have an image — concept art, a film still, a photo of a room — and you need a prototype you can walk around in within five minutes to align the space, test framing, or show a client. For that, it beats hand-building the scene by a wide margin. --- Scope and sources: repo README, .claude/skills/* and .claude/scripts/* (2026-10-21, main); World Labs docs (api/pricing, marble/export/specs, marble/export/gaussian-splat, api/rendering-spz); FAL model pages; Niantic spz format notes and three.js SPZLoader. No end-to-end run was performed — costs are structural estimates from public unit prices, and mesh/engine/license constraints come from documentation rather than our own tests. The author is a World Labs team member; this is their project, not an official World Labs product. More from us: the full Chinese write-up with the same billing breakdown · AI × 3D guides on BimAnt

@digi_the_robot You should check out image blaster neilsonnn/image-blaster it does something similar. While I am sure there are a lot of people who hate stuff like this exists I am also aware that there are a lot more people who do not make worlds and could use this if its made easier.

A single photo turned into a 3D world you can explore? Pretty wild 👀 It’s called image-blaster. It uses Claude, World Labs, and fal.ai to generate: • 3D models of objects in the image • An explorable background environment • Ambient audio and sound effects The repo says it can do this in under five minutes. Imagine taking a picture of a cabin or a concept for a game level and using it as the starting point for a 3D scene. That’s a pretty exciting shortcut from “I have an idea” to something you can move around in. GitHub 👇 neilsonnn/image-blaster #AI #3D #OpenSource

Из картинки в 3D-сцену за пять минут На GitHub появился Image Blaster — инструмент, который превращает обычное изображение в полноценную 3D-сцену. Загружаешь картинку, а Claude разбирает её на части: объекты конвертирует в 3D-модели, фон собирает... neilsonnn/image-blaster

Claude har fått ögon. Image-blaster förvandlar varje skärmbild till en strukturerad världskarta som din agent kan läsa och agera på. Vad skulle du låta en agent göra på din skärm först? neilsonnn/image-blaster Följ mig på Insta också: instagram.com

Esto pero en local y con imágenes 360. neilsonnn/image-blaster

メモ: Creates 3D environments, SFX, and meshes from a single image using Claude skills, World Labs, and FAL. neilsonnn/image-blaster

This Open Source Toolkit Turns a Single Image into an Interactive 3D World Image Blaster is a set of Claude Code skills that turns a single image into an explorable 3D scene. It separates objects from the background, generates individual 3D assets, and builds the environment with ambient audio. The workflow combines World Labs for the environment, Hunyuan 3D for objects, Nano Banana for image cleanup, and ElevenLabs for sound. What you get: - Gaussian Splat environments with collision geometry. - Separate 3D meshes you can grab and move around with physics in the included viewer. - PBR materials and adjustable polycounts, including a LowPoly option. - Ambient audio and object-specific sound effects. - GLB / OBJ assets for further work in Blender or game engines. Could be useful for turning concept art into explorable level prototypes or quickly building a scene from a reference photo. The code is open source under MIT. Generation runs through external APIs and requires your own keys. GitHub

有人在GitHub上新放了一个仓库image-blaster。 随便上传一张照片，就能生成可漫游的3D场景。 带物理网格、背景splat、环境音效，一套配齐。 一张图输入，五分钟，直接产出一个可探索世界。 那些苦练十年Blender的大佬，今天都在默默围观这个项目。 仓库链接放下面。 neilsonnn/image-blaster