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:
@@ -34,11 +34,11 @@ Cutout 提供四种结果:
|
||||
| Depth Balloon | `O Image Depth Balloon` | MoGe-2 高度 |
|
||||
| Depth Surface | `O Image Depth Surface` | MoGe-2 相机点 |
|
||||
|
||||
四种 Shape 共用 `O Image Cutout` 修改器、规则三角基础面、UV 和 `o_balloon` 属性。Shape 菜单选择内部几何分支,Cleanup 在分支前执行,Smooth 在分支后执行;Point Spacing 控制网格密度,Normal 与 Refine Selection 按需启用 MoGe-2 和 BEN2。
|
||||
四种 Shape 共用 `O Image Cutout` 修改器、规则三角基础面、UV 和 `o_balloon` 属性。Shape 菜单选择内部几何分支,Cleanup 在分支前执行且使用便于调节的百倍显示值,Smooth 在分支后执行;Depth Shape 根据 Region 透明比例选择固定或自适应 Base Plane Depth,Normal 可选 None、Tangent 或 Object,Refine Selection 按需启用 BEN2。
|
||||
|
||||
### 图片结果
|
||||
|
||||
Image Mask 和 Perspective 直接更新当前 Empty 的图片并 Pack。Remove Background 输出透明颜色图或序列。Upscale 通过三档 ONNX 模型输出 4× RGBA,并保存原图引用,重复执行时从原图重新生成。
|
||||
Image Mask 和 Perspective 直接更新当前 Empty 的图片并 Pack。Remove Background 输出透明颜色图或序列。Upscale 通过三档 ONNX 模型把当前 Image 输出为 4× RGBA;当前长边达到全局输入上限时不可执行。
|
||||
|
||||
## 模型
|
||||
|
||||
|
||||
Reference in New Issue
Block a user