Nougan Nodes
Nougan's Nodes: loaders, LoRA tooling, masks, bounding boxes, smart image/video saving, dataset captioning, remote Set/Get, Prompt Relay and an LM Studio bridge for ComfyUI.
Nodes (60)
Point it at a directory and press Run once
Caption a folder of clips without hitting Queue 200 times
Two Krea 2 characters in one image without the blend — this is how
Nougan Album Cover Maker
Bounding Boxes without Nodes 2.0 — draw the layout, hand the model a map
SillyTavern cards inside ComfyUI — chatting with the LLM you already loaded
Why your 5-second clip is 107 frames — duration to frames, without the math node
Stop retyping 'preserve the composition' — template your edit prompts
The receiver half of wireless data — grab a Set node's value from anywhere
Grab any in-workflow image and get IMAGE + MASK, no disk detour
GIFs that don't look like mud — two-pass palette, and where Discord's 10MB bites
MiniMax H3 image editing in one node — conditioning, sampling, decode, done
Nougan Image Converter
The one-toggle uncensor for Krea 2, with LoRAs shipped in the pack
One uncensor stack, five Krea 2 models — the multi-model version
Nougan Layout LLM Prompt
Chat with a local LLM from inside ComfyUI — vision, audio, video included
A live, editable reader for whatever your local LLM just said
Point at any LoRA and it tells you who it is — live from Civitai
A LoRA stack editor that doesn't make you squint at text menus
Make one image match another's dimensions — without the resize math
Nougan Model Preview Mirror
Six Load Image nodes? One node with a plus button instead
H3 refmods applied in place
Bake a character — portraits and a voice — into one MiniMax H3 reference file
Baking chat characters into safetensors
Four characters, one H3 graph — loading baked refmods with separate face and voice strength
The node that frees your VRAM mid-graph — and how to wire it so it doesn't backfire
Two characters, no identity soup
One node for aspect ratios that survive snapping
Save video with the workflow inside it — codecs, CRF and the NVENC trap
Beam any value across your graph without the wire spaghetti
Nougan Tail Capture
Nougan Tail Load
Nougan Tail RefMod
A no-frills text box that emits a clean STRING
Skip the CLIPTextEncode → ConditioningZeroOut two-node dance
Styled title banners that stay readable at any zoom
Nougan Ultimate KSampler
The Nougan V2 PNG Baker
Nougan Video Save
The Nougan Workflow PNG Baker
Tuning the segment boundaries kijai's node draws
Give a video different prompts for different moments
Drag your scene changes instead of typing frame numbers
The Nougan Regional Character LoRA
The node that gets .txt files into your dataset folder
🌀 Winnougan (Nougan's Nodes)
<img width="1672" height="941" alt="Nougan poster" src="https://github.com/user-attachments/assets/20f56fbe-e2cf-4094-94c2-1b14dce04e5f" /> <br>Custom nodes and canvas tools for ComfyUI
Thirty-plus nodes across thirteen families, plus three frontend extensions that change how you work on the canvas. Loaders, LoRA tooling, masking, layout boxes, smart image saving, dataset captioning, remote data, temporal video prompts, a local LLM bridge, character cards, MiniMax H3 references and GIF making. Every node has its own themed, live UI.
</div>✨ Overview
Nodes
- 🚀 Loaders: a folder-aware Diffusers Loader and the one-toggle Krea 2 · Uncensored stage with three bundled LoRAs.
- 📁 LoRA tooling: a themed LoRA stack editor with favourites, folder filters and a randomizer, plus the Lora Inspector that identifies any LoRA live from Civitai.
- 🎨 Image & masks: Get Image for in-graph grabs, a full Mask Editor and Mask Composite.
- 🔲 Layout: Bounding Boxes to draw a layout on a canvas (with layers and a right-click menu), plus a Layout LLM Prompt that lets a local LLM draw the boxes for you.
- 💎 Smart image saving: the Image Converter / Saver saves or converts to PNG, WebP, JPEG and more, and Smart Squeeze finds the smallest file that still looks right.
- 📂 Dataset captioning: folder batch loaders and a caption saver that names each
.txtafter its image, with whole-folder auto-run. - 📡 Remote data: Set / Get nodes pass data across your graph without wires.
- 🎭 Characters & video: Regional Character LoRA for two identities without blend, and Prompt Relay for per-segment prompts in LTX video.
- 🧠 Local LLMs: the LM Studio Bridge streams chat, vision, audio and video through any model in LM Studio, with a live on-node console.
- 🃏 PNG Bakers: the Character Card V2 Baker and Workflow PNG Baker bake data into PNGs, with a holographic preview.
- 💬 Character Chat: chat with V1 / V2 / V3 character cards on Qwen3.5, with a chat panel, lorebooks and sampling settings.
- 🧬 RefMod: MiniMax H3 character references. Bake portraits and audio into one file, then load and apply it for video generation.
- 🎞️ GIF Maker: video to GIF / WebP / MP4 with a visual timeline trim, on-video crop, social presets and a live size estimate.
Frontend extensions (not nodes, they appear on their own when ComfyUI loads)
- 🖱️ Canvas Tools: Zip Ties, Bypass Slash, Smart Guides with tidy-by-dependency, Subgraph Box, Group Box and hold-a-key gestures.
- 🪟 Automagic 2222: Live Panel: a floating, dockable panel that edits your checkpoint, CLIP, VAE, resolution, samplers, seeds and LoRAs live. Drag any node onto it to pin its widgets, compare two images with a slider, run from the panel, and pick from 32 themes.
- 📋 Automagic 2222: Paste Stack: a floating clipboard history. One click saves the text, image or file you copied (prompts, screenshots, files from Explorer). Click a saved card to copy it back, or drag an image card onto a Load Image node. Your stack survives reloads, and the panel minimizes to a small chip.
The pack also includes a global Tab-cycler quality-of-life extension that works on every node in your graph.
📦 Node index
| Node | What it does | Docs |
|---|---|---|
| Nougan Diffusers Loader 🚀 | Loads a Diffusers folder/file → MODEL · CLIP · VAE, auto-precision, optional Sage/Flash attention | core |
| Nougan Krea 2 · Uncensored 🌀 | Bakes in 1–3 bundled uncensor LoRAs with per-LoRA toggle + uncapped strength | core |
| Nougan Get Image 🖼️ | Grabs an in-workflow image → IMAGE + MASK, live previews | core |
| Nougan Text Encode + Zero Neg 🎯 | Encodes positive and builds the negative (zero-out / empty-string) in one node | core |
| Nougan Text Box 📝 | Reusable prompt card emitting a STRING, with counts + copy/clear | core |
| Nougan Title Font 🌈 | Zoom-proof styled title banner with glow, animations, gradient presets, web link | core |
| Nougan Lora Loader 📁 | Themed LoRA stack editor: chooser, ☆ favourites, folder filter, 🎲 randomizer | core |
| Nougan Lora Loader (Multi) 📁 | Same editor, sharing one stack across up to 5 models | core |
| Nougan Lora Inspector 🔍 | Point at a LoRA → trigger words, base model, samples, stats, live from Civitai | docs |
| Nougan Mask Editor 🎨 | Paint and edit masks on-node | core |
| Nougan Mask Composite 🎭 | Combine masks for edit-then-composite workflows | core |
| Nougan Bounding Boxes 🔲 | Draw layout boxes on a canvas → preview, BOUNDING_BOX and prompt elements. Layers, snap, right-click menu, paste/import JSON | docs |
| Nougan Layout LLM Prompt 🧭 | Writes the instructions that make an LLM answer with box JSON, so a local LLM can draw your layout | docs |
| Nougan Image Converter / Saver 💎 | Save or convert to PNG · WebP · JPEG · AVIF · TIFF · BMP · GIF. Smart Squeeze + a 5–10 quality scale find the smallest file that still looks right | docs |
| Nougan Load Image Batch From Folder 📂 | One image per run from a folder, with live preview and whole-folder auto-run | docs |
| Nougan Load Video Batch From Folder 🎞️ | The video counterpart of the folder loader | docs |
| Nougan Save Caption (Match Image/Video Name) 💾 | Saves a caption as a .txt named after the file just loaded | docs |
| Nougan Set (Remote) 📡 | Sends data under a key, no wire needed | docs |
| Nougan Get (Remote) 📥 | Receives data by key from anywhere in the graph | docs |
| Nougan Regional Character LoRA 🎭 | Two character LoRAs, one image, each masked to its own region, no blend | docs |
| Nougan Prompt Relay Encode 🎬 | Per-segment temporal prompts for LTX · LTX2 · LTXAV | docs |
| Nougan Prompt Relay Timeline 🎞️ | Same pipeline + a draggable WYSIWYG timeline editor | docs |
| Nougan Prompt Relay Options ⚙️ | Per-stream epsilon / strength / window tuning | docs |
| Nougan LM Studio 🧠 | Streaming LLM chat + vision + audio + video via LM Studio, live DOM console | docs |
| Nougan LM Studio Prompt Box 💬 | Live on-node reader/editor for LLM output | docs |
| PNG Bakers 🃏 | Character Card V2 Baker and Workflow PNG Baker: bake a character card or a workflow into a PNG, with a holographic preview | docs |
| Character Chat 💬 | Chat with V1 / V2 / V3 character cards on Qwen3.5, with a chat panel, lorebooks and sampling settings | docs |
| RefMod 🧬 | MiniMax H3 character references: Bake (portraits + audio → one file), Loader and Apply, with a card UI, curves and scramble | docs |
| GIF Maker 🎞️ | Video to GIF / WebP / MP4 with a visual timeline trim, on-video crop, social presets, live size estimate and a frames output | docs |
Frontend extensions
| Extension | What it does | Docs | |---|---|---| | Canvas Tools 🖱️ | Zip Ties, Bypass Slash, Smart Guides + tidy by dependency, Subgraph Box, Group Box and hold-a-key gestures | docs | | Automagic 2222: Live Panel 🪟 | Floating, dockable panel that live-edits checkpoint / CLIP / VAE / resolution / duration / samplers / seeds / LoRAs. Drag a node on to pin it, image compare, subgraph cards, run bar with VRAM meter, 32 themes | docs | | Automagic 2222: Paste Stack 📋 | Floating clipboard history. One click saves copied text, images and files; click a card to copy it back; drag an image card onto Load Image. Survives reloads, minimizes to a chip, WebGPU backdrop | docs |
🧭 Which node do I need?
| I want to… | Use | |---|---| | Load a Diffusers model folder | Diffusers Loader 🚀 | | Uncensor Krea 2 in one toggle | Krea 2 · Uncensored 🌀 | | Stack style/character LoRAs with favourites + a randomizer | Lora Loader 📁 | | Find out what an unknown LoRA actually is | Lora Inspector 🔍 | | Encode positive + negative without the two-node dance | Text Encode + Zero Neg 🎯 | | Place subjects and text exactly where I want them | Bounding Boxes 🔲 | | Let a local LLM plan the layout for me | Layout LLM Prompt 🧭 | | Save images as small as possible without visible loss | Image Converter / Saver 💎 | | Convert a whole folder of images to WebP or PNG | Image Converter / Saver 💎 | | Caption a whole dataset folder in one run | Dataset Captioning 📂 | | Pass data across the graph without wires | Set / Get 📡 | | Put two characters in one image without identity blend | Regional Character LoRA 🎭 | | Give different video segments different prompts | Prompt Relay 🎬 | | Chat with / analyze images via a local LLM | LM Studio Bridge 🧠 | | Bake a character card or a workflow into a PNG | PNG Bakers 🃏 | | Chat with a V1 / V2 / V3 character card | Character Chat 💬 | | Use a character's portraits and voice as MiniMax H3 references | RefMod 🧬 | | Turn a video into a GIF, WebP or MP4 for socials | GIF Maker 🎞️ | | Tidy a messy graph and move around it faster | Canvas Tools 🖱️ | | Change my model, sampler, seed and LoRAs without hunting through the graph | Live Panel 🪟 | | See the difference between two outputs with a slider | Live Panel 🪟 (Compare) | | Keep my old prompts and images handy to reuse | Paste Stack 📋 | | Drop an image I just copied straight into a Load Image node | Paste Stack 📋 (drag a card onto the node) |
⚡ Install
cd ComfyUI/custom_nodes
git clone <your-repo-url>
# restart ComfyUI, then hard-refresh the browser tab (Ctrl+F5)
Each node family announces itself on boot, and each loads in its own try/except, so a problem in one can never take down the others:
[Nougan] ✅ Lora Inspector loaded.
[Nougan] ✅ Bounding Boxes loaded.
[Nougan] ✅ Image Converter loaded.
[Nougan] ✅ Prompt Relay loaded (3 nodes).
[Nougan] ✅ LM Studio Bridge loaded (2 nodes).
The frontend extensions announce themselves in the browser console instead, for example:
✔ Automagic 2222: Live Panel (web extension)
✔ Automagic 2222: Paste Stack (web extension)
Paste Stack also has a small server helper (it reads files you copied in Explorer / Finder, which browsers can't) that reports as Paste Stack clipboard helper (0 nodes) on boot. After updating, restart ComfyUI so the helper loads, not just the browser tab.
Or install via ComfyUI Manager: search Nougan.
Optional: pip install pyoxipng adds an extra lossless pass to PNG saving in the Image Converter.
📚 Documentation
Every node family has its own page in docs/:
| Page | Covers | |---|---| | Core nodes | Diffusers Loader · Krea 2 · Get Image · Text Encode + Zero Neg · Text Box · Title Font · Lora Loaders · Mask Editor · Mask Composite | | Remote Data Nodes | Wireless data passing, auto-color sync, dynamic key management | | Lora Inspector | Civitai lookup, sample strip, caching, HTTP endpoint | | Regional Character LoRA | Token-space masking, regions, recon tool, debugging | | Prompt Relay | Timeline editor, epsilon tuning, technical deep dives | | LM Studio Bridge | Dev-server setup, vision/audio/video, Krea 2 prompt director | | Dataset Captioning | Folder Batch Loader · Save Caption (Match Image Name) · whole-folder auto-run · LoRA dataset prep | | Bounding Boxes | Box editor · layers and right-click menu · LLM layout prompt · MOSS-Image layouts | | Image Converter / Saver | Save and convert · Smart Squeeze · quality scale · lossless PNG/WebP · batch convert a folder | | PNG Bakers | Character Card V2 Baker · Workflow PNG Baker · accepted JSON shapes · holographic preview · troubleshooting | | Character Chat | Chat with V1/V2/V3 character cards · Qwen3.5 · chat panel · lorebooks · sampling settings · outputs · troubleshooting | | RefMod | MiniMax H3 character references · Bake (portraits + audio → one file) · Loader · Apply · card UI · curves and scramble · credits | | GIF Maker | Video to GIF / WebP / MP4 · visual timeline trim · on-video crop · social presets · live size estimate · frames output · HTTP endpoints · troubleshooting | | Canvas Tools | Zip Ties · Bypass Slash · Smart Guides + tidy by dependency · Subgraph Box · Group Box · hold-a-key gestures · key map · troubleshooting | | Automagic 2222: Live Panel | Floating dockable panel · live-edit checkpoint / CLIP / VAE / resolution / duration / samplers / LoRAs · drag a node on to pin it · image compare · subgraph cards · rename, hide, reorder · Reload (R) · 32 visual themes · troubleshooting | | Automagic 2222: Paste Stack | Floating clipboard history · one-click paste of text, images and copied files · click a card to copy it back · drag an image onto Load Image · minimize to a chip · WebGPU backdrop · storage and limits · troubleshooting |
📄 License
MIT. Take it, ship it, remix it.
<div align="center">
Nougan's Nodes · if something here saves you a render, ⭐ the repo.
</div>