Krea2 Projector Tuner for ComfyUI ⚡
The ultimate in-memory projector tuning tool designed to patch and customize txtfusion.projector layers of Krea2 models in real-time.
Enables instant censorship/NSFW bypass and prompt-following enhancements with zero permanent changes to your model files!
💡 Ultimate Quality:
You can also pair this tuner with our companion node FLSampler (BSS) to perfectly restore any lost micro-details!
🔗 GitHub Repository (Full Guide & Docs): https://github.com/BlackSnowSkill/ComfyUI-Krea2-Projector-Tuner
🌟 Key Features (v2.0.0)
🧠 In-Memory Dynamic Patching: Patches model weights temporarily in VRAM during execution using ComfyUI's native patching pipeline. Zero disk writes, zero model file corruption risk.
📂 Dynamic JSON Presets & Easy Sharing: All configurations are stored in the local
presets/folder as simple.jsonfiles. This allows the community to easily share, import, or back up their favorite tuning setups! Just copy any community preset.jsonto yourpresets/folder and it will load instantly.🎛️ Interactive Web UI & On-Node Buttons: Save and manage your custom configurations directly from the node interface:
Save Preset (BSS): Prompt-saves your manual sliders setup as a new JSON preset on the fly.Delete Selected Preset (BSS): Instantly deletes the current preset file from your disk.Open Presets Folder (BSS): Opens the presets folder in your OS file explorer.All sliders update dynamically on your canvas when choosing a preset!
🔥 Premium Default Presets:
Strongx3_wl7(Default & Best): The absolute best bypass configuration. Applies a 3x suppression on safety layers 8–10, plus a targeted-0.7shift on layer 7 to lock down the last safety peak.Strong 2.5: Standard decensoring patch.Clean Bypass: Clean safety filter bypass.
🎚️ 12-Layer Slider Control: Custom sliders mapped directly to the 12 CLIP text encoder layers, giving you full manual control over style, details, layout, and censorship with a comfortable
0.01dragging step.
📂 Quick Installation
Method 1 (Recommended):
Open ComfyUI Manager -> click Install Custom Nodes.
Search for
Krea2 Projector Tuner.Click Install and restart ComfyUI.
Method 2 (Fallback via Git URL):
Open ComfyUI Manager -> click Install via Git URL.
Paste this URL:
https://github.com/BlackSnowSkill/ComfyUI-Krea2-Projector-TunerClick Install and restart ComfyUI.
For detailed parameters, portable environment wheels, and manual installation, please refer to the GitHub README.
☕ Support & License
Support Development: Support me and get exclusive models on Boosty!
License & Usage: © 2026 blacksnowskill (BSS). All rights reserved. This project is protected by copyright. Copying, distribution, merging, or use on other websites/repositories without explicit written permission is strictly prohibited.
Description
### What's New in Version 2.0.0 ⚡
* Interactive On-Node Buttons: Save, delete, and browse your custom weights configurations directly from the node:
* Save Preset (BSS): Prompt-saves current manual slider values as a new JSON preset in your presets/ folder. The dropdown list refreshes instantly!
* Delete Selected Preset (BSS): Deletes the currently selected preset file from disk.
* Open Presets Folder (BSS): Instantly opens the presets directory in your OS file explorer.
* Dynamic JSON Presets Folder: All presets are now loaded dynamically from individual .json files in the presets/ directory. You can easily share, edit, or delete them!
* Dynamic Web UI Sync: Sliders update automatically on your canvas when a preset is selected. Manual slider adjustments automatically switch the dropdown back to custom.
* Standard Step Size (0.01): Restored the comfortable 0.01 step size (like the standard LoRA Loader) for smooth manual dragging, while fully preserving high-precision float inputs (up to 6 decimals) when typed or loaded from presets.
FAQ
Comments (5)
From testing, it's the current best unfiltering method among all.
could you share your testings with me?
Great, thanks for this. Can I suggest a small change which would much improve the utility? Add an overall weight multiplier. All knobs are multiplied by that value.
Consider the 2 and 3 vector lora settings from another author that many use - they are often applied at 5x or 10x.
Your 'strongx3_wl7' is very similar ratio of knobs 8/9/10 (plus -0.7 on 'knob 7') to the 3 vector. I find I apply your lora at weight 3 to 5.
yet I find i use loras instead of your node, as it is quicker to weight your 'strongx3_wl7' at 3x, than have to calculate 3x knob 7 value, 3 times knob 8 value, etc.
if you add multiplier, it would be a quick as loras for big changes (multipliers), but allow individual knob tweaking.
done
Fast work there! Thank you! This will help many.