Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
docs(forge): document the Pixal3D fidelity lane and ship its changelog entry
nirholas192c01233f50
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 973ba0b8f..66a3e1967 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -37,6 +37,7 @@ Public history for [three.ws](https://three.ws), newest first. New pages come fr- **Browse every feature by goal**: A new /everything page groups all 340 product pages under twelve goals (make, animate, build an agent, embed, earn, launch, trade, on-chain, worlds, discover, developer tools, account) with search, pins, recents and a new-this-month feed. The nav leads with it, the command palette labels every result with its goal, and tool pages like Forge, Create and Widgets now end with a what-next strip. (`/everything`) `[feature]`- **Choose which @-mentions your agent answers, right from its editor**: An agent's Social tab now has an "Answer mentions" section: turn it on, keep it in dry run while you watch what it would say, cap it at a daily reply count, and pick exactly which kinds of mentions it may act on. A new decisions list on the same page shows the agent's own recent calls, what it decided and why, so the owner never has to ask an admin to check a console on their behalf. (`/agents`) `[feature]`- **Every 3D generation now writes a signed run receipt**: Each Studio run (avatars, rigged avatars, meshes, rigs, refinements) records stage by stage what was expected, what was observed, and a verdict: met, recovered by a named fallback, missed with its cause, or skipped. The rig is verified by reading the delivered file back, not by trusting the rigger. Receipts are ed25519-signed, linked from every result, browsable at /runs with stage-by-stage rates, and verifiable offline with one command. (`/runs`) `[feature]`+- **Forge gets a fidelity lane: match your photo instead of guessing it**: A new Forge engine, "Match my photo", fuses 1 to 4 photos of the same object into one pixel-aligned 3D model instead of generating a plausible guess from a single view. Drop photos into the existing view slots and label each one Front, Back, Left or Right; the model is pixel-aligned to every photo you give it, and more photos narrow the result further. Only one photo on hand? Toggle "fill in the other sides" and the worker synthesizes the missing angles before reconstructing. Built on TencentARC's Pixal3D (MIT) running on Microsoft TRELLIS.2's backbone, with MV-Adapter (Apache-2.0) for the view synthesis step. Every input photo is recorded against the finished model, and single-photo requests on every other engine are unaffected. (`/forge`) `[feature]`- **Live widgets and an assistant on the desktop, and the desktop is back at /**: The homepage is the web desktop again, and the Field moves to /?view=field. The desktop gains eleven live widgets: the $THREE price with a 24 hour chart, weather where you are, clock, calendar, the newest agents, Pulse wallet moves, coins launched through three.ws, platform stats, headlines from the news desk, your device's battery, network and storage, and sticky notes. Pin them to the desktop in small, medium or large, drag them on a snap grid, or keep them on the widgets board beside a news column. The new assistant pane answers questions about three.ws, opens the right app from its reply, and lets you switch to any public agent and talk to it instead. Nothing is sample data: a source that is down says so and offers a retry. (`/docs/desktop-widgets`) `[feature, desktop]`- **Menu bar panel for the desktop app**: Click the three.ws icon in your menu bar or tray and a small panel shows your agent alive in 3D, its Solana wallet balance, a start and stop button, anything waiting on your approval, unread alerts and a box to ask the agent something. Approvals still open the native confirmation window, so what you approve is exactly what you were shown. (`/desktop`) `[feature]`- **Real agents live on the campus: a greeter meets you at the gate and every agent you walk up to talks back**: The campus is now populated by the ten most talked-to public agents on three.ws, each wearing its own avatar from its public record (five on a phone). The most popular one stands beside the gate path, turns to you as you walk in, waves and says hello through its own brain. Every agent idles, wanders a step, faces you when you come near and carries a name tag; walk up (or tap the tag) and press E to open a conversation that streams the agent's real reply, shows it as a speech bubble and can read it aloud. The panel opens the agent's profile as a window and hands you the one-tag embed that puts that exact agent, body and brain, on any web page. GET /api/agents/public now returns avatar_model_url for public and unlisted avatars. (`/?world=1`) `[feature, desktop]`diff --git a/STRUCTURE.md b/STRUCTURE.mdindex 19b519a9f..cd38b6fe6 100644--- a/STRUCTURE.md+++ b/STRUCTURE.md@@ -193,7 +193,7 @@ bottom.| Agent-native 3D + embeddable distribution | MCP tool [api/_mcp/tools/agents.js](api/_mcp/tools/agents.js) (`attach_avatar_to_agent`); shared oEmbed provider [api/agent-oembed.js](api/agent-oembed.js) `→ /api/oembed` + builder [api/_lib/embed.js](api/_lib/embed.js) (`forgeEmbedTarget`, shared by `get_embed_code` in [api/_mcp/tools/embed.js](api/_mcp/tools/embed.js)); Forge share page oEmbed discovery [api/forge-share.js](api/forge-share.js) `→ /forge/share/:id`; distribution snippet builders [src/forge-embed-snippets.js](src/forge-embed-snippets.js) + panel [src/forge-embed-panel.js](src/forge-embed-panel.js); autonomous demo [examples/agent-native-3d/](examples/agent-native-3d) | In-repo | Closes the loop: create → own → discover/remix → **use everywhere**. `attach_avatar_to_agent` gives a registered agent identity a persistent body (chains into `register_agent` for on-chain identity + `anchor_provenance` for a signed authenticity credential). Any Forge creation now unfurls via real oEmbed (paste `/forge/share/:id` into Notion/Discord/Slack) with the same `type:rich` iframe payload `get_embed_code` returns via MCP. The Forge "Embed this model" panel hands out five real distribution flavours from one GLB — iframe, `<model-viewer>`, `<agent-3d>`, a `@three-ws/page-agent` talking guide, and a `@three-ws/walk` companion — all built from one shared, pure snippet module so every surface stays byte-identical. `examples/agent-native-3d/run.mjs` drives the full agent-native chain live against `/api/mcp-studio` (mesh_forge → rig_mesh → create_agent_persona → persona_say → get_agent_persona → every distribution snippet) with zero mocks and a documented, logged fallback if the shared free-tier generation lane is rate-limited at run time. Spec: [specs/EMBED_SPEC.md](specs/EMBED_SPEC.md#share-routes-on-chain-agents). Docs: [docs/mcp.md#attach_avatar_to_agent](docs/mcp.md#attach_avatar_to_agent). Roadmap prompt 10 (closes the roadmap campaign). || Animation pipeline | [public/animations/](public/animations) + [scripts/build-animations.mjs](scripts/build-animations.mjs) | In-repo | Mixamo source FBX + GLB retargeting pipeline · see [docs/3d-asset-pipeline.md](docs/3d-asset-pipeline.md) || Procedural animation (runtime IK layers) | [src/procedural/](src/procedural) — analytic two-bone IK [two-bone-ik.js](src/procedural/two-bone-ik.js), gaze [look-at.js](src/procedural/look-at.js), terrain foot planting [foot-plant.js](src/procedural/foot-plant.js), drift-free re-application [pose-baseline.js](src/procedural/pose-baseline.js) | Live | Post-mixer layers that do what no baked clip can: the chest/neck/head chain turns toward a world point, and each foot lands on its own patch of uneven ground. Rig-agnostic via `canonicalNodeMapFromObject`; an unsupported rig reports `enabled === false` and no-ops. Wired into the corner companion ([walk-sdk/src/companion.js](walk-sdk/src/companion.js) `_updateGaze`), the walkaround world ([src/walk.js](src/walk.js) `rebuildFootPlant`), and agent avatars ([src/agent-avatar.js](src/agent-avatar.js) `_applyLookTarget` — which is what finally makes `setLookTarget()` and the `LOOK_AT` action move the rig). Ambient idle motion (breathing/blink/saccade/weight-shift) stays in [src/idle-animation.js](src/idle-animation.js). Docs: [docs/procedural-animation.md](docs/procedural-animation.md). Tests: [tests/procedural-anim.test.js](tests/procedural-anim.test.js), [tests/agent-avatar-look-target.test.js](tests/agent-avatar-look-target.test.js) |-| Self-hosted 3D GPU fleet (the engines behind the Forge) | [workers/model-trellis2/](workers/model-trellis2) (TRELLIS.2, MIT, the default image-to-3D lane `trellis2`: PBR GLB with alpha, `resolution` 512/1024/1536; built and tested, deploy owner-gated), territory router [api/_lib/forge-territory.js](api/_lib/forge-territory.js) (EU, UK and KR never reach a Tencent-model lane; unknown country fails closed), [workers/model-trellis/](workers/model-trellis), [workers/model-hunyuan3d/](workers/model-hunyuan3d) (2.0 + 2.1 PBR + 2.1 RTX), [workers/model-triposg/](workers/model-triposg), [workers/modly/](workers/modly) (Modly v0.4.3 running its TripoSG and Hunyuan3D 2 Mini Turbo extensions as the untextured Forge lanes `modly` and `modly_hunyuan`, behind `MODEL_MODLY_URL`; weights staged, built and tested, deploy owner-gated), [workers/model-triposr/](workers/model-triposr), [workers/model-text2motion/](workers/model-text2motion), [workers/rig/](workers/rig) (auto-rigging, deployed as `model-rig`), [workers/avatar-reconstruction/](workers/avatar-reconstruction), CPU stages [workers/rembg/](workers/rembg) · [workers/remesh/](workers/remesh) · [workers/segment/](workers/segment) · [workers/stylize/](workers/stylize), talking-avatar video [workers/longcat/](workers/longcat) (LongCat-Video-Avatar-1.5, gates the `/create/video` lane via `LONGCAT_WORKER_URL`; the one fleet member that is not a Cloud Run service, because its ~45 GB resident weight set needs an 80 GB GPU, so it is built and tested but undeployed), streaming video→3D [workers/model-video2scene/](workers/model-video2scene), selfie-pipeline CPU orchestrator [workers/avatar-pipeline-controller/](workers/avatar-pipeline-controller) | Live · Cloud Run GPU (us-central1, plus us-east4 where trellis/hunyuan/triposr hold standbys and `model-text2motion` runs as its production lane) | Every generation engine the Forge dispatches to, each with its own `cloudbuild.yaml`. The L4 quota is **per region** and both us-central1 and us-east4 are granted 3, so a warm pin in one region only starves lanes in that same region (increase to 16 filed 2026-07-16, still reconciling); the Hunyuan3D-2.1 PBR realism lane also ships an RTX PRO 6000 build (`model-hunyuan3d-21-rtx`, quota granted 1000) as the warm primary. `model-text2motion` (MDM, MIT) is the text→motion lane behind `GCP_TEXT2MOTION_URL`, the `text_to_animation` MCP tool, and `POST /api/forge-motion`: prompt in, a retargetable three.js `AnimationClip` out, applied with the same engine (`src/animation-retarget.js`) as the curated animation library. It is the one GPU service whose production URL points at us-east4, and its `cloudbuild.yaml` deploys both regions from one image so the standby never lags. Ops map: [docs/ops/gcp-credits-plan.md](docs/ops/gcp-credits-plan.md) |+| Self-hosted 3D GPU fleet (the engines behind the Forge) | [workers/model-trellis2/](workers/model-trellis2) (TRELLIS.2, MIT, the default image-to-3D lane `trellis2`: PBR GLB with alpha, `resolution` 512/1024/1536; built and tested, deploy owner-gated), [workers/model-pixal3d/](workers/model-pixal3d) (TencentARC Pixal3D, MIT, on TRELLIS.2's backbone: the `pixal3d` fidelity lane labeled "Match my photo", 1 to 4 pixel-aligned input photos with optional `view_labels` and one-photo `fill_other_sides` view synthesis via MV-Adapter (Apache-2.0); built and tested, deploy owner-gated), territory router [api/_lib/forge-territory.js](api/_lib/forge-territory.js) (EU, UK and KR never reach a Tencent-model lane; unknown country fails closed), [workers/model-trellis/](workers/model-trellis), [workers/model-hunyuan3d/](workers/model-hunyuan3d) (2.0 + 2.1 PBR + 2.1 RTX), [workers/model-triposg/](workers/model-triposg), [workers/modly/](workers/modly) (Modly v0.4.3 running its TripoSG and Hunyuan3D 2 Mini Turbo extensions as the untextured Forge lanes `modly` and `modly_hunyuan`, behind `MODEL_MODLY_URL`; weights staged, built and tested, deploy owner-gated), [workers/model-triposr/](workers/model-triposr), [workers/model-text2motion/](workers/model-text2motion), [workers/rig/](workers/rig) (auto-rigging, deployed as `model-rig`), [workers/avatar-reconstruction/](workers/avatar-reconstruction), CPU stages [workers/rembg/](workers/rembg) · [workers/remesh/](workers/remesh) · [workers/segment/](workers/segment) · [workers/stylize/](workers/stylize), talking-avatar video [workers/longcat/](workers/longcat) (LongCat-Video-Avatar-1.5, gates the `/create/video` lane via `LONGCAT_WORKER_URL`; the one fleet member that is not a Cloud Run service, because its ~45 GB resident weight set needs an 80 GB GPU, so it is built and tested but undeployed), streaming video→3D [workers/model-video2scene/](workers/model-video2scene), selfie-pipeline CPU orchestrator [workers/avatar-pipeline-controller/](workers/avatar-pipeline-controller) | Live · Cloud Run GPU (us-central1, plus us-east4 where trellis/hunyuan/triposr hold standbys and `model-text2motion` runs as its production lane) | Every generation engine the Forge dispatches to, each with its own `cloudbuild.yaml`. The L4 quota is **per region** and both us-central1 and us-east4 are granted 3, so a warm pin in one region only starves lanes in that same region (increase to 16 filed 2026-07-16, still reconciling); the Hunyuan3D-2.1 PBR realism lane also ships an RTX PRO 6000 build (`model-hunyuan3d-21-rtx`, quota granted 1000) as the warm primary. `model-text2motion` (MDM, MIT) is the text→motion lane behind `GCP_TEXT2MOTION_URL`, the `text_to_animation` MCP tool, and `POST /api/forge-motion`: prompt in, a retargetable three.js `AnimationClip` out, applied with the same engine (`src/animation-retarget.js`) as the curated animation library. It is the one GPU service whose production URL points at us-east4, and its `cloudbuild.yaml` deploys both regions from one image so the standby never lags. Ops map: [docs/ops/gcp-credits-plan.md](docs/ops/gcp-credits-plan.md) || Self-hosted Granite Guardian (governance lane behind watsonx) | [workers/granite-guardian/](workers/granite-guardian/README.md) (Cloud Run `granite-guardian`, europe-west4, vLLM on one L4), client lane in [api/_lib/granite-guardian.js](api/_lib/granite-guardian.js) | Live · Cloud Run GPU (europe-west4) | IBM's open-weight `ibm-granite/granite-guardian-3.3-8b` served by the stock vLLM OpenAI image, so `/api/guardian/assess`, the identity integrity check, and the Granite Twin/Oracle/Attest/IRL screens return real Granite Guardian verdicts on a deployment with no IBM Cloud account. watsonx.ai stays the lead lane when configured; every verdict names the `model` and `provider` that produced it. Placed in europe-west4 because that region's L4 grant is otherwise unused, so its warm pin never starves the 3D lanes. Tests: [tests/api-guardian.test.js](tests/api-guardian.test.js), [tests/api/identity-integrity.test.js](tests/api/identity-integrity.test.js) || Reconstruct completion backstop (abandoned selfie jobs) | [api/cron/reconstruct-sweep.js](api/cron/reconstruct-sweep.js), every 5 min via `vercel.json` crons → Cloud Scheduler | Live 2026-07-25 | A reconstruct job used to be advanced **only by the user's browser**: `/create/selfie` polls `regenerate-status`, and each poll runs the finalize stages. Close the tab and the worker still finished the GLB and stored it durably, but nothing ever collected it — 26 jobs were stranded that way, oldest from 2026-05-31, invisible to `db-retention` (which prunes only terminal rows). This sweep is the server-side driver: it picks up reconstruct jobs quiet >3 min and runs **the same shared stages** in [reconstruct-finalize.js](api/_lib/reconstruct-finalize.js), so an abandoned job still lands in the user's library. 30-day rescue window (the worker's GCS blobs + Firestore job state are durable, so a weeks-old job is still deliverable); past that, or when a job's provider is no longer pollable from platform credentials, rows fail out with an honest reason so the open set can't grow unbounded. BYOK (meshy/tripo) jobs stay browser-driven — a cron has no user context to resolve their keys. Sibling of [auto-rig-sweep.js](api/cron/auto-rig-sweep.js), which plays the same role for the rerig lane. Docs: [docs/avatar-reconstruction.md](docs/avatar-reconstruction.md#who-finishes-the-job) || Avatar fidelity evaluation (selfie → avatar, scored) | [workers/avatar-reconstruction/eval/](workers/avatar-reconstruction/eval) | In-repo · gates every reconstruction change | **Identity Shape Error (ISE)** — does the reconstructed avatar have *this person's* face shape? Texture-blind, pose- and scale-invariant, dimensionless: MediaPipe's 468 landmarks and the avatar's corresponding head vertices are both Umeyama-aligned onto the neutral canonical face over a stable identity subset (no eyes/lips, so a smile is not scored as identity), then compared. A pipeline cannot score better by resizing or tilting the head — only by matching shape, a property pinned in [eval/test_identity_eval.py](workers/avatar-reconstruction/eval/test_identity_eval.py) alongside monotonicity. [`run_eval.py`](workers/avatar-reconstruction/eval/run_eval.py) scores a whole reference set against a live worker and diffs two revisions, surfacing per-face regressions a mean would hide; [`tune_morph.py`](workers/avatar-reconstruction/eval/tune_morph.py) sweeps the morph parameters against ISE offline; [`robustness.py`](workers/avatar-reconstruction/eval/robustness.py) measures the opposing axis (does a blurred / turned / occluded / dim / low-res photo of the same person still yield the same head?), and the shipped `max_displacement_frac` is the knee of those two curves. The 40-face reference set is **synthesised** by [`make_refs.py`](workers/avatar-reconstruction/eval/make_refs.py) over a deterministic grid of the platform's diversity matrix — no real biometrics, no licence terms, rebuildable by any agent — gitignored and mirrored to `gs://three-ws-avatar-reconstructions/eval-refs/`. Docs: [eval/README.md](workers/avatar-reconstruction/eval/README.md), program plan [docs/avatar-fidelity-program.md](docs/avatar-fidelity-program.md) |diff --git a/data/changelog.json b/data/changelog.jsonindex 4afe7adfc..40d71edee 100644--- a/data/changelog.json+++ b/data/changelog.json@@ -1,6 +1,15 @@{"$comment": "Curated changelog entries for three.ws, the editorial layer of the public changelog. New PAGE launches are tracked automatically via the `added` field in data/pages.json; this file is for everything else holders care about: improvements, fixes, SDK releases, trading/payments capabilities, security work. scripts/build-page-index.mjs merges both sources into CHANGELOG.md, public/changelog.json, and public/changelog.xml. Newest first. Allowed tags: feature, improvement, fix, sdk, infra, docs, security, desktop (desktop entries become the desktop app's release notes). `link` is optional and must be a live three.ws path.","entries": [+ {+ "date": "2026-10-11",+ "title": "Forge gets a fidelity lane: match your photo instead of guessing it",+ "link": "/forge",+ "summary": "A new Forge engine, \"Match my photo\", fuses 1 to 4 photos of the same object into one pixel-aligned 3D model instead of generating a plausible guess from a single view. Drop photos into the existing view slots and label each one Front, Back, Left or Right; the model is pixel-aligned to every photo you give it, and more photos narrow the result further. Only one photo on hand? Toggle \"fill in the other sides\" and the worker synthesizes the missing angles before reconstructing. Built on TencentARC's Pixal3D (MIT) running on Microsoft TRELLIS.2's backbone, with MV-Adapter (Apache-2.0) for the view synthesis step. Every input photo is recorded against the finished model, and single-photo requests on every other engine are unaffected.",+ "tags": [+ "feature"+ ]+ },{"date": "2026-10-11","title": "A stuck background job now fails fast instead of hanging for 15 minutes",diff --git a/docs/forge.md b/docs/forge.mdindex ca612e07d..20f5b6927 100644--- a/docs/forge.md+++ b/docs/forge.md@@ -36,6 +36,7 @@ Each backend declares which paths it serves, whether it needs a bring-your-own-k- **Hunyuan3D / TRELLIS (free)** on Hugging Face Spaces. The free photo-to-3D lane and a High-tier engine, with automatic failover across Hunyuan3D 2.1, Hunyuan3D 2, TRELLIS, and TripoSR. Queue waits vary.- **TRELLIS (self-host)** and **Hunyuan3D (self-host)**, our own scale-to-zero Cloud Run GPU workers, and the named defaults: TRELLIS at Draft and Standard, Hunyuan3D at High. Zero vendor cost, so free-first routing prefers them first. Self-host TRELLIS is a native single-hop image-to-3D lane; Hunyuan3D leads on people and organic subjects.- **TripoSG (self-host)**, the sketch-only scribble worker. Untextured geometry from a drawing. It also serves photos as the last automatic failover rung: when every textured photo lane has failed mid-job, the job continues on TripoSG's photo pipeline and returns the shape without textures rather than failing.+- **Pixal3D (self-host)**, the fidelity lane, labeled **"Match my photo"** in the UI. Built on [TencentARC Pixal3D](https://github.com/TencentARC/Pixal3D) (MIT), pixel-aligned image-to-3D on [Microsoft TRELLIS.2](https://github.com/microsoft/TRELLIS.2)'s backbone. Where the other photo lanes read one view and generate a plausible result, Pixal3D fuses every photo you give it (1 to 4), so the result matches your photos rather than guessing. Never a named default or a failover target (a down Pixal3D must not silently drop the 2nd/3rd photo on a lane that only reads the first view) and only selectable explicitly. With exactly one photo, the optional `fill_other_sides` flag first synthesizes the other three angles with [MV-Adapter](https://github.com/huanngzh/MV-Adapter) (Apache-2.0) before reconstructing.- **TRELLIS** on Replicate, a paid platform lane. Selectable explicitly and used as the last-resort fallback only on deployments with no free engine configured.- **Meshy 6**, **Tripo v3.1**, **Rodin (Hyper3D)**, BYOK geometry-first engines with quad topology and a real poly target. You supply your own key.- **Stable Fast 3D** (Stability, BYOK) and **Replicate (your account)** (BYOK), single-image reconstruction lanes.@@ -334,6 +335,32 @@ curl -X POST 'https://three.ws/api/forge' \-d '{"image_urls":["https://…/front.jpg","https://…/side.jpg"],"tier":"standard"}'```+Pin the Pixal3D fidelity lane (1 to 4 photos, pixel-aligned to every one of+them) with `backend`, and optionally label each photo's angle with+`view_labels` (`"front"`, `"back"`, `"left"`, `"right"`, same order as+`image_urls`) so the worker doesn't have to guess:++```bash+curl -X POST 'https://three.ws/api/forge' \+ -H 'content-type: application/json' \+ -d '{+ "image_urls": ["https://…/front.jpg","https://…/back.jpg","https://…/left.jpg"],+ "view_labels": ["front","back","left"],+ "backend": "pixal3d",+ "tier": "standard"+ }'+```++With exactly one photo, add `"fill_other_sides": true` to synthesize the+other three angles with MV-Adapter before reconstructing, instead of+reconstructing from the single view alone:++```bash+curl -X POST 'https://three.ws/api/forge' \+ -H 'content-type: application/json' \+ -d '{"image_urls":["https://…/front.jpg"],"fill_other_sides":true,"backend":"pixal3d","tier":"standard"}'+```+A minimal poll-until-done loop in JavaScript:```javascriptdiff --git a/public/changelog-recent.json b/public/changelog-recent.jsonindex 377c3fe3f..4ddb6b716 100644--- a/public/changelog-recent.json+++ b/public/changelog-recent.json@@ -1,11 +1,11 @@{- "generated_at": "2026-10-11T13:47:51.450Z",+ "generated_at": "2026-10-11T18:53:40.209Z","generated_by": "scripts/build-page-index.mjs from data/pages.json + data/changelog.json","site": {"name": "three.ws","url": "https://three.ws"},- "total": 4029,+ "total": 4030,"complete": false,"full_feed": "/changelog.json","entries": [@@ -290,6 +290,16 @@"feature"]},+ {+ "date": "2026-10-11",+ "type": "update",+ "title": "Forge gets a fidelity lane: match your photo instead of guessing it",+ "summary": "A new Forge engine, \"Match my photo\", fuses 1 to 4 photos of the same object into one pixel-aligned 3D model instead of generating a plausible guess from a single view. Drop photos into the existing view slots and label each one Front, Back, Left or Right; the model is pixel-aligned to every photo you give it, and more photos narrow the result further. Only one photo on hand? Toggle \"fill in the other sides\" and the worker synthesizes the missing angles before reconstructing. Built on TencentARC's Pixal3D (MIT) running on Microsoft TRELLIS.2's backbone, with MV-Adapter (Apache-2.0) for the view synthesis step. Every input photo is recorded against the finished model, and single-photo requests on every other engine are unaffected.",+ "link": "/forge",+ "tags": [+ "feature"+ ]+ },{"date": "2026-10-11","type": "update",@@ -1536,16 +1546,6 @@"tags": ["fix"]- },- {- "date": "2026-10-09",- "type": "update",- "title": "Claim the 3D models the bot made for you on X",- "summary": "Anything @trythreews makes for you from a post now waits for you. Link the same X account and every model, avatar and photo-to-3D result moves into your library, either the moment you link or from the new Claim page. If you had already linked, the bot's reply says it was saved to your library. If not, the reply carries a link to claim it.",- "link": "/x/claim",- "tags": [- "feature"- ]}]}diff --git a/public/changelog.json b/public/changelog.jsonindex 7432ef58d..21f36b589 100644--- a/public/changelog.json+++ b/public/changelog.json@@ -1,5 +1,5 @@{- "generated_at": "2026-10-11T13:47:51.428Z",+ "generated_at": "2026-10-11T18:53:40.187Z","generated_by": "scripts/build-page-index.mjs from data/pages.json + data/changelog.json","site": {"name": "three.ws",@@ -287,6 +287,16 @@"feature"]},+ {+ "date": "2026-10-11",+ "type": "update",+ "title": "Forge gets a fidelity lane: match your photo instead of guessing it",+ "summary": "A new Forge engine, \"Match my photo\", fuses 1 to 4 photos of the same object into one pixel-aligned 3D model instead of generating a plausible guess from a single view. Drop photos into the existing view slots and label each one Front, Back, Left or Right; the model is pixel-aligned to every photo you give it, and more photos narrow the result further. Only one photo on hand? Toggle \"fill in the other sides\" and the worker synthesizes the missing angles before reconstructing. Built on TencentARC's Pixal3D (MIT) running on Microsoft TRELLIS.2's backbone, with MV-Adapter (Apache-2.0) for the view synthesis step. Every input photo is recorded against the finished model, and single-photo requests on every other engine are unaffected.",+ "link": "/forge",+ "tags": [+ "feature"+ ]+ },{"date": "2026-10-11","type": "update",diff --git a/public/changelog.xml b/public/changelog.xmlindex 73b346e1f..36abfc20f 100644--- a/public/changelog.xml+++ b/public/changelog.xml@@ -230,6 +230,14 @@<category>feature</category><description>Each Studio run (avatars, rigged avatars, meshes, rigs, refinements) records stage by stage what was expected, what was observed, and a verdict: met, recovered by a named fallback, missed with its cause, or skipped. The rig is verified by reading the delivered file back, not by trusting the rigger. Receipts are ed25519-signed, linked from every result, browsable at /runs with stage-by-stage rates, and verifiable offline with one command.</description></item>+ <item>+ <title>Forge gets a fidelity lane: match your photo instead of guessing it</title>+ <link>https://three.ws/forge</link>+ <guid isPermaLink="false">2026-10-11:Forge gets a fidelity lane: match your photo instead of guessing it</guid>+ <pubDate>Sun, 11 Oct 2026 12:00:00 GMT</pubDate>+ <category>feature</category>+ <description>A new Forge engine, "Match my photo", fuses 1 to 4 photos of the same object into one pixel-aligned 3D model instead of generating a plausible guess from a single view. Drop photos into the existing view slots and label each one Front, Back, Left or Right; the model is pixel-aligned to every photo you give it, and more photos narrow the result further. Only one photo on hand? Toggle "fill in the other sides" and the worker synthesizes the missing angles before reconstructing. Built on TencentARC's Pixal3D (MIT) running on Microsoft TRELLIS.2's backbone, with MV-Adapter (Apache-2.0) for the view synthesis step. Every input photo is recorded against the finished model, and single-photo requests on every other engine are unaffected.</description>+ </item><item><title>Live widgets and an assistant on the desktop, and the desktop is back at /</title><link>https://three.ws/docs/desktop-widgets</link>diff --git a/public/features.json b/public/features.jsonindex 98e6a906e..f34e82e01 100644--- a/public/features.json+++ b/public/features.json@@ -1,5 +1,5 @@{- "generated_at": "2026-10-11T13:47:51.415Z",+ "generated_at": "2026-10-11T18:53:40.173Z","generated_by": "scripts/build-page-index.mjs from data/pages.json","site": {"name": "three.ws",