PH-CU-S

EN | RU

Buy License

Get a license key instantly after paying by card. 1 year of technical support included.

Key is saved permanently, used for all future updates. 1 year of technical support is included in this English version of the license.

Download latest version

Enter your license key to get the latest version.

Latest version: PH-CU-S_3.60.15

3.60.09

Added

  • Batch for series of generations

3.53.20

Added

  • Custom field in the Snap menu
  • Automatic format conversion for additional images (.psd .tiff .png .webp .jpg)

Fixed

  • Random display of the snap list instead of the workflow list

PH-CU-S

Work with Photoshop's familiar toolset — layers, selections, masks — while generation is performed by ComfyUI, running locally or remotely.

Demo

About the plugin

PH-CU-S is a panel for Adobe Photoshop (UXP plugin) that turns ComfyUI into an image generation engine within your Photoshop workflow.

The plugin sends the current canvas (or active selection), prompt and parameters to ComfyUI, runs a selected workflow and returns the result back to Photoshop as a new layer.

Main capabilities

License & Activation (Up to 3 Devices)

Each license key allows you to bind the plugin to 3 independent computers (devices) simultaneously. A maximum of 15 lifetime activations (device registrations) is allowed per license.

How does it work?

  • Automatic Activation: Your license key is embedded into the archive when you download the plugin from the site. Upon the first launch in Photoshop, it automatically generates a hardware identifier (HWID) and registers your computer.
  • Device Management: If you reach the 3-device limit and want to install the plugin on a new computer, you must unlink an old device. You can do this by visiting the Manage Devices page. Please note that each license key supports a lifetime limit of 15 total activations.
  • Local Cache: After a successful activation, the license status is cached locally, allowing the plugin to launch instantly without any network delays.

Interface features

Full tab

Complete control with all available settings:

  • Prompt and Negative Prompt input
  • Fixed Seed or random seed
  • 30 slots for storing prompts
  • Workflow list with nested folders
  • Selection alignment to model multiples (FLUX 64, Qwen 112, Personal)
  • Add to content (+ to selection for better model understanding)
  • Custom Step & CFG parameters
  • Progress and status in real time
  • Loading up to 3 additional images

Simple tab

Minimal mode for quick workflows:

  • Prompt input
  • Negative prompt
  • Workflow selection
  • Run button

Ideal for quick work when advanced settings are not required.

Can be fully changed, add / remove any tabs (in settings)

Config tab

Connection settings and history management:

  • Workflow folder configuration
  • ComfyUI server URL settings
  • Saved prompts history (ON/OFF)
  • All runs history (ON/OFF)
  • History export (TXT & HTML)

Additional features

  • Automatic history cleanup (configurable)
  • Connection status indicator
  • Generation progress in real time
  • Seed tracking and display
  • Generation statistics

Installation and setup

System requirements

  • Adobe Photoshop 2025 (26.00) and above
  • ComfyUI with installed custom node ComfyUI_PH-CU-S
  • Common exchange folder accessible to both plugin and ComfyUI
  • Minimum recommended hardware: NVIDIA RTX 3060 (6GB VRAM), 32GB RAM minimum, from 30GB for files (preferably SSD)

📋 Manual installation

1. Unzip the archive

2. Photoshop plugin installation. Copy PH-CU-S folder to "C:\Program Files\Adobe\Adobe Photoshop <Version>\Plug-ins\PH-CU-S" (depends on Photoshop version), then open panel: Window → Extensions → PH-CU-S

3. ComfyUI custom node installation. Copy ComfyUI_PH-CU-S folder to ComfyUI/custom_nodes/, launch ComfyUI — nodes appear in category PH-CU-S

4. Copy Workflow to ComfyUI. Copy Photoshop folder into ComfyUI\user\default\workflows\Photoshop, reload browser, photoshop folder visible in workflow.

5. Check Workflow in ComfyUI. Launch Workflows you plan to work with, fix all "red" errors, connect models if needed — once the process works properly, you can launch it from plugin in Photoshop.

6. Configuration. File config.txt on first launch is copied from plugin folder depending on Photoshop version and username: %AppData%\Adobe\UXP\PluginsStorage\PHSP\<Version>\External\com.ph-cu-s\PluginData To change: Tools → Edit config.txt

  • WORKFLOWS_FOLDER - path to folder with .json workflows
  • PS_INPUTS_DIR - path to exchange folder (shared with ComfyUI)
  • COMFYUI_URL - server address (default: http://localhost:8188)

🤖 Automatic installation

1. Unzip archive contents to root of drive where ComfyUI will be installed. Preferably SSD, minimum size including Flux 2 klein model - about 30 GB. If drive name is Z:\, path to unzipped folder will be: Z:\PH-CU-S_install

2. In folder Z:\PH-CU-S_install launch 1_ComfyUI-Easy-Install.bat - wait for installation completion.

3. In folder Z:\PH-CU-S_install launch 2_Install.bat. Choose 1. for minimal Flux 2 Klein model install, or 2. if you also plan to install Qwen Image Edit 2511. Models will download and be placed at correct paths automatically. Wait for installation completion.

4. If you want to install Qwen Image Edit 2511 after Flux 2 Klein install or during download if the install process was interrupted - run 2_Install.bat again and choose 2 (or 1 if you need to continue). Models already downloaded will be skipped, models not fully downloaded will be re-downloaded and placed at correct paths automatically. Wait for installation completion.
During install a folder "downloads_temp" is created on drive root. Script checks if model already exists there and uses it from there. Also checks system "downloads" folder - if model was downloaded via browser, script copies model from "downloads".

5. config.txt file will be changed automatically, you can open Photoshop, then open panel: Window → Extensions → PH-CU-S

Detailed interface description

Adaptation to Photoshop color scheme

Plugin element colors change together with Photoshop color scheme changes

Prompt and Negative Prompt

Text areas for your AI prompts. Sent directly to ComfyUI via prompt.txt and negative.txt files.

Fixed Seed / Random seed

Seed behavior control:

  • Fixed: Use specific seed value for reproducible results
  • Random: ComfyUI generates new seed each run
  • Actual used seed displayed after generation completes

Additional image support

Upload up to 3 additional images for:

  • Inpainting workflows
  • Image-to-image generation
  • Multi-input image scenarios

Images saved as extra1.png, extra2.png, extra3.png to exchange folder. By default active mode is resize and convert when exceeding 1 megapixel (button "↓1Mp" - green). If button pressed ("↓1Mp" - red), additional images will be sent to workflow unchanged.

Prompt Slots (SAVE & LOAD)

5 color sections, 6 numbered slots for parameter presets:

  • Loading mode (default): Loads saved set with all parameters
  • Saving mode: Saves current settings to slot (buttons highlight red)
  • Automatically restored when plugin launches
  • Customizable colors in settings - PROMPT_SET_COLORS=#ffb0b0,#388e3c,#1565c0,#f9a825,#7b1fa2

Snap to Grid

Automatic size alignment for different models:

  • FLUX x64: Sizes rounded to 64px (for FLUX models, can change in settings - sm_flux = 64)
  • Qwen x112: Sizes rounded to 112px (for Qwen models, can change in settings - sm_qwen = 112)
  • Personal x8: Sizes rounded to 8px (configurable any size - sm_personal = 8)
  • Auto-selected based on workflow name for Flux and Qwen

Workflows

When plugin loads, folder <ComfyUI>\user\<User>\workflows\Photoshop is scanned. All nested folders at 1 level are added to plugin interface. If you change workflows during work, add new ones or modify and save existing - you can re-scan the folder by pressing "↻ Update Workflows". Several workflows supplied with plugin:

  • Base - all Workflow for working with selected area. If no selection, you will see error when launching. Number of steps in name - more = better quality. For Flux 2 klein usually 8 steps is enough. For Qwen 2511 - 4 and 8 steps using Qwen-Image-Edit-2511-Lightning-4 (8)steps-V1.0-bf16.safetensors, usually this is enough. If you need to increase quality - choose CUSTOM step / CFG and configure your parameters.
  • Canvas - workflows for working with entire artboard. Entire artboard sent to workflow. Numbers mean what is transferred, e.g. "F2-Klein 1+1" - 1+1 - for processing artboard + can connect 1 additional image. "Qwen 0+3" - artboard not transferred, work only with 3 loaded images (can load fewer - 1 or 2). "F2-Klein Restore&Colorise" - prompt needed here as it built into workflow. "Qwen 1+2" - artboard transferred + up to 2 loaded images
  • Txt-Img - Image generation from text prompt.
  • Zoom - Image enlargement. Connected scheme with fast upscale model. By default configured for minimum configuration. If you have 10-12 Vram or modern card (tested on 5060 / VRAM) - try changing SeedVR2_up_to 4096.json in GUI ComfyUI and select bigger model (e.g. seedvr2_ema_7b_fp8_e4m3fn_mixed_block35_fp16.safetensors). How enlargement works: to enlarge document size along with selected size press "Expand" button. If not pressed, process completes and image is enlarged but fits into current document. Zoom in by double-click to see real size.
    If your scheme has enlargement - e.g. as in "Qwen 2512 + Upscale", for Photoshop document enlargement need to press "Expand" button in "Zoom" block.
  • Note #1 - If your scheme has enlargement - e.g. as in "Qwen 2512 + Upscale", for Photoshop document enlargement need to press "Expand" button in "Zoom" block.
  • Note #2 - Button "↑1 Mp" in "Zoom" block - enlarges selection to 1 megapixel. Needed when selection is very small and some models start distorting image heavily. Enlargement can be built into workflow or press this button.
  • Note #3 When exceeding configured image size (MAX_IMAGE_MP=4), warning appears during generation send. If agree - image sent unchanged to ComfyUI, and for sizes above 4 megapixels possible slowdown and sometimes hanging. This block offers reducing image to 2/3/4 megapixels. Green buttons - with step from Snap menu (64 for Flux, 112 for Qwen). Blue - without step binding.

Guide

Adds guides with selected step from selection. Parameter configurable: GUIDE_PRESETS=100,200,300,500

Add to content

Block for expanding selection area before sending to ComfyUI. Adds padding around selection — useful for inpainting tasks when model needs additional context around edited area.

  • Input field - padding values in pixels in `top/right/bottom/left` format (or shortened: one value for all sides, two — top-bottom and left-right).
  • Preset buttons (default: 64, 128, 256, 112, 224, 336 px) — press sets equal padding from all sides.

    • Custom Step & CFG

    Send custom parameters to workflow nodes:

    • Custom Step: Integer (up to 4 digits)
    • CFG: Guidance scale (up to 2 decimal places)

    Tools Tab

    Language

    Interface translation into 8 languages: English, Spanish, Japanese, German, Chinese, Portuguese, French, Russian

    • Save - apply language selection

    Workflow folder

    Displays current path to .json workflow folder (from config.txt). Path can be changed in field — when changed, workflow list reloads automatically. Button **↻ Update Workflows** for manual update.

    ComfyUI Server URL

    Field for ComfyUI server address (default `http://localhost:8188`). Buttons:

    • TEST — checks server availability (timeout 5 seconds)
    • SAVE — saves URL to `ui_prefs.json` for restore on next launch

    Saved prompts history

    Each time prompt saved to slot, record added to `prompts_old.txt`. Buttons:

    • Open .txt — opens file in text editor
    • Open .html — generates and opens HTML version of history with readable formatting

    Status **ON / OFF** shows recording enabled (managed by `SAVE_PROMPTS_HISTORY` in config.txt). Open method controlled by `OPEN_LOGS_METHOD`: `auto`, `mac` or `pc`.

    All prompts history

    Each generation run recorded in `all_prompts.txt`. Same buttons Open .txt / Open .html. Status **ON / OFF** controlled by `SAVE_ALL_PROMPTS` in config.txt.

    Clear all prompts

    Button **🗑 Clear all prompts** — clears history files (`all_prompts.txt`, `prompts_old.txt`) and resets all 30 prompt slots. Request confirmation before execution.

    View images (Canvas / Mask)

    Thumbnails of recently sent files from `exchange` folder:

    • Canvas — `canvas.png` (image sent to ComfyUI on last run)
    • Mask — `mask.png` (mask, if used)

    Below each thumbnail displayed dimensions in pixels and size in megapixels. Button **↻** updates preview manually.

    Add bleed

    Expands document canvas uniformly from all sides by specified value.

    • Preset buttons — press immediately applies expansion. After operation displays row with new canvas size in selected units.

    Unit of measurement and preset set in config.txt via `BLEED_UNIT` (`mm` / `inches` / `pixel`) and `BLEED_PRESETS`. Default: mm, presets 2 / 3 / 5.

    Guides for bleed

    Places guide lines from document edges — for trim zone layout and safe area.

    • Preset buttons — each button sets pair values `inner+outer` (e.g. `3+7`: inner guide 3 mm from edge, outer — 7 mm). If outer value equals 0, only one guide drawn from each side.
    • Center canvas — draws guides through center of canvas
    • Center select — draws guides through center of active selection
    • Clear — removes all guides in document

    Unit and presets set in config.txt via `ADD_GUIDE_UNIT` (`mm` / `inches` / `pixel`) and `ADD_GUIDE_PRESETS`. Default: mm, presets `3+7` / `2+5` / `2+0`.

    Integration with ComfyUI

    How it works (data flow)

    1. Select canvas or area in Photoshop
    2. Enter prompt and configure parameters
    3. Press "Run Workflow"
    4. Plugin saves canvas and parameters to exchange folder
    5. ComfyUI processes workflow
    6. Result returned as new Photoshop layer

    Custom ComfyUI nodes

    PH-CU-S Input

    Reads all input data from exchange folder: canvas, mask, prompts, seed, parameters, image sizes, 3 additional images

    PH-CU-S Save Seed

    Accepts seed, writes to exchange folder, passes value forward. Returns actual used seed back to plugin.

    PH-CU-S Output

    Extends SaveImage. Saves result and sends HTTP notification to plugin on completion.

    History and auto-cleanup

    Automatic history management:

    • Prompts saved to slots logged in prompts_old.txt
    • All generation runs logged in all_prompts.txt
    • Automatic cleanup on plugin launch (configurable storage days)
    • History export as .txt or .html

    Frequently asked questions

    Works with all Photoshop versions?

    Yes, compatible with Photoshop 2025 (26.00) and newer. Early versions may not work due to UXP API restrictions.

    Is it subscription or one-time purchase?

    One-time purchase. No subscriptions, no recurring payments, no functionality restrictions over time.

    Can use remote ComfyUI server?

    Yes! Settings in config.txt file. Supports local servers.

    What AI models supported?

    Works with any ComfyUI workflow: FLUX.2, Qwen, Flux 2 Klein, Stable Diffusion and custom models. No model restrictions.

    Need GPU for Photoshop plugin?

    No. GPU required only for machine running ComfyUI models. Photoshop plugin works on any system.

    What about image privacy?

    Images exchanged via local folder. Use local ComfyUI server for maximum privacy or configure secure network setup.

    Ready to improve your workflow?

    Join thousands of creatives using AI in Photoshop.