feat: Implement cutout tool and depth generation features

- Added a new cutout tool for selecting regions in images, allowing users to choose mesh shapes based on selected areas.
- Introduced depth generation capabilities for rasterized images, including normal data extraction.
- Created jobs for generating depth planes and region data, enhancing the AI data generation workflow.
- Developed a selection refinement process for cutout regions, improving accuracy in generated outputs.
- Established a new region module for handling rasterized image regions and their associated AI generation tasks.
- Enhanced node graph builders for asset generation, facilitating smoother integration of new features.
This commit is contained in:
2026-08-30 23:09:13 +08:00
parent 32bcd45d7b
commit 08309f719d
88 changed files with 4145 additions and 5639 deletions

View File

@@ -20,7 +20,7 @@ AnyImage 把运行环境、模型和任务结果放在 Blender 之外,多个 B
## 全局 AI 输入尺寸
Environment 区的 **Maximum AI Input Size** 控制 Upscale、Depth 与 Normal 分析输入的最大长边,默认 `2048 px`,可在 `256–8192 px` 之间调整。超过上限的输入会保持宽高比缩小;颜色贴图仍使用原始分辨率。Cutout 在完成套索裁切后再应用上限,因此整张原图很大但选区较小时不会被无谓缩小。
Environment 区的 **Maximum AI Input Size** 默认 `2048 px`,可在 `256–8192 px` 之间调整。它既是允许执行 Upscale 的当前图片长边上限,也是 Depth 与 Normal 分析输入的最大长边;Upscale 在达到上限时置灰,Depth 与 Normal 则保持宽高比缩小分析输入。颜色贴图仍使用当前图片的原始分辨率。Cutout 在完成套索裁切后再应用上限,因此整张图片很大但选区较小时不会被无谓缩小。
## Device
扩展偏好设置中的 **Device** 控制 Depth Plane、Cutout 的 AI 增强、Remove Background 和 Upscale 等正式任务。