Node packVerifiedExternal

Comfyui_TTP_Toolset

for tile the image for advanced control or modification

Sourcegithub.com/TTPlanetPig/Comfyui_TTP_Toolset

Maintainer@TTPlanetPigBgrade

Package profile

Status: Verified
Publisher: @TTPlanetPig
Source: GitHub
Stars: 1K

README

ComfyUI TTP Toolset

ComfyUI TTP Toolset is a collection of tiled upscale, Smart Tile, video sampler, coordinate, and conditioning helper nodes. The current main feature is Smart Tile 2.0, an object-aware tiled img2img workflow with automatic layout, per-tile prompts, loop processing, semantic priority, mask-aware assembly, and final-only saving.

ComfyUI TTP Toolset 是一组围绕分块放大、Smart Tile、视频采样、坐标处理和条件处理的 ComfyUI 节点集合。当前主推功能是 Smart Tile 2.0：它支持语义自动分块、逐 tile 提示词、循环采样、语义层级、蒙版拼合和只保存最终结果。

Feature Blocks / 功能模块

Feature block / 功能块	Status / 状态	What it is for / 用途
Smart Tile 2.0	Current main feature / 当前主推	Object-aware variable-size tile workflow for detail img2img upscale. / 面向细节重绘放大的语义可变尺寸分块流程。
TTP Tile 1.0	Legacy workflow / 旧版流程	Fixed-grid image tiling and assembly for classic upscale workflows. / 传统固定网格切图、批处理和拼回流程。
Coordinate and conditioning utilities	Helper nodes / 辅助节点	Coordinate splitting, condition batching, and condition merging. / 坐标拆分、条件批处理和条件合并。
LTX workflow examples	Example workflows / 示例工作流	First/last frame and middle-frame control examples. / 首尾帧与中间帧控制示例。
TeaCache for Hunyuan Video	Extra tool / 额外工具	Faster Hunyuan Video sampling with TeaCache. / 使用 TeaCache 加速 Hunyuan Video 采样。

Smart Tile 2.0: Object-Aware Tile Loop / 语义分块循环

Smart Tile is an object-aware tiled img2img workflow for ComfyUI. Instead of cutting every image into equal squares, it lets you build variable-size tiles around visual structure: face, eyes, hands, text, subject, clothing, foreground details, and background/context regions.

Smart Tile pipeline

Smart Tile is designed for workflows where small areas need more detail than the full image. You can draw or auto-detect tiles, process one tile at a time through your sampler, then assemble the final image with feathering, masks, semantic priority, color correction, and optional pixel alignment.

What It Solves

Avoids cutting important objects through the middle when a simple grid would split a face, hand, or text.
Allows different tile sizes, so a face tile can be small and high detail while the background stays large.
Sends one tile at a time through img2img, so the number of tiles can be 4, 8, 16, or anything produced by the editor.
Keeps high-detail focus tiles visible during assembly with priority, layer, and semantic ranking.
Supports mask-aware pasteback, soft detail overlay, final-only assembly, and black-base canvas mode.

Visual Tile Editor

Smart Tile editor controls

TTP Smart Tile Interactive Crop is the recommended starting point. It can load an image like ComfyUI's official Load Image, or receive a connected source_image. The editor stores the current layout in a hidden layout_json widget, so your workflow keeps the tile plan.

Useful editor actions:

Replace grid: replace the whole layout with an even grid.
Grid in T#: subdivide the selected tile without rebuilding the whole layout.
Show masks / Hide masks: toggle a colored overlay for tile object masks in the editor.
Stitch mask / Raw masks: preview the hardened and feathered replace-paste mask shape without changing saved masks.
Mask to Tile: turn painted regions into object tiles.
Merge masks: Shift/Cmd/Ctrl-select multiple tiles, then union their cropped object masks back onto the selected tiles.
Merge tiles: Shift/Cmd/Ctrl-select multiple tiles, then replace them with one larger tile; existing masks are unioned into the merged tile when available.
Refresh masks: after manually moving sub-tiles from a masked tile, re-crop the inherited masks to the current tile boxes.
Fill gaps: add background tiles for uncovered areas.
Auto Tile: run SAM3.1 or QwenVL3 detection and write the detected layout back into the editor.
Auto SAM: run SAM3.1 detection and keep