Skip to content

Refresh README value proposition and processing architecture #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
PlevanTem merged 1 commit into from
Oct 14, 2026
Merged

Refresh README value proposition and processing architecture #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion ARCHITECTURE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ The core package is provider-neutral. A multimodal host such as Codex or Claude

## Processing model

<img src="docs/assets/architecture.svg" alt="UltraSplitter agent-native processing architecture" width="100%">
<img src="docs/assets/architecture.svg" alt="Processing pipeline from irregular source sheet through scanning, semantic planning, source-pixel routing, primary review, optional transparency review, and PNG plus layered PSD delivery" width="100%">

### Scan

Expand Down
6 changes: 4 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,9 @@

<sub>Illustrated workflow · <a href="docs/assets/banner-static.png">Static view</a></sub>

**Turn AIGC sheets into individual assets your production pipeline can actually use.**
**Split irregular asset sheets into reviewable, traceable assets.**

AI identifies subjects; deterministic code splits original pixels into individual images and a layered PSD.

Image models are good at presenting a family of ideas in one image: a UI icon set, weapon collection, character turnaround, building elevation sheet, furniture board, or product-variant grid. The sheet may look finished, but the assets inside it are still trapped in one bitmap. Uneven spacing, mixed scale, labels, touching silhouettes, and edge-clipped subjects make equal slicing unreliable.

Expand Down Expand Up @@ -127,7 +129,7 @@ ultrasplit evaluate output/task/manifest.json --visual-verdict pass

## Architecture

<img src="docs/assets/architecture.svg" alt="UltraSplitter agent-native processing architecture" width="100%">
<img src="docs/assets/architecture.svg" alt="Processing pipeline from irregular source sheet through scanning, semantic planning, source-pixel routing, primary review, optional transparency review, and PNG plus layered PSD delivery" width="100%">

Every run writes a schema-v3 manifest with exact source coordinates, route evidence, provenance, approval state, bounded repair attempts, evaluation status, and absolute delivery paths. See [ARCHITECTURE.md](ARCHITECTURE.md).

Expand Down
6 changes: 4 additions & 2 deletions README.zh-CN.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,9 @@

<sub>直观流程插画 · <a href="docs/assets/banner-static.png">查看静态版</a></sub>

**把 AIGC 生成的整张方案图，变成生产流程真正能用的独立资产。**
**把不规则素材图拆成可审核、可追溯的独立资产。**

AI 识别主体，代码按原图像素拆分，输出图片与分层 PSD。

图片模型很擅长在一张图里展示一组创意：UI 图标、武器合集、角色多视图、建筑立面、家具方案、产品变体。整图看起来已经完成，但里面的素材仍被锁在一个位图文件中。间距不均、尺寸混杂、文字边框、轮廓相接和主体截断，都会让均匀切图失效。

Expand Down Expand Up @@ -127,7 +129,7 @@ ultrasplit evaluate output/task/manifest.json --visual-verdict pass

## 架构

<img src="docs/assets/architecture.svg" alt="UltraSplitter AI 原生处理架构" width="100%">
<img src="docs/assets/architecture.svg" alt="不规则素材图经过扫描、语义规划、原像素路由和主视觉审核后，交付图片与分层 PSD；另含可选的透明版本审阅和重建路径" width="100%">

每次运行都会写入 schema v3 的 `manifest.json`，记录准确的源图坐标、路由依据、来源追踪、批准状态、有界修复次数、评估结果和绝对访问路径。完整设计见 [ARCHITECTURE.md](ARCHITECTURE.md)。

Expand Down
Loading
Loading