Node pack designed to save images with metadata supported by Civitai.
A collection of enhanced nodes for ComfyUI with metadata handling for Civitai and streamlined model loading.
Now the Image Saver keeps the workflow data in the image! Just drag and drop the image to open the workflow it was created with!
π LoRA Metadata Exporter β Extracts trigger words from LoRA metadata (local & online).
π Prompt Formatters β Organizes quality tags, descriptions, and prompt structure.
π Smart Model Loader β Loads models and LoRAs with automatic metadata extraction.
π Enhanced KSampler β Improved metadata tracking with LoRA and checkpoint integration.
π Diffusion Model Loader β Like SDXL/PONY version, it loads model along with clips and LoRAs, extracting metadata and and passing them as string.
π FLUX Sampler β Metadata tracking with LoRA and checkpoint integration.
π FLUX Guidance β The very same FLUX Guidance as ComfyUI original, but with guidance extraction to save as metadata.
π Advanced Image Saver β Saves images with embedded metadata, filenames, and auto-numbering.
π Custom Latent Generator β Predefined resolutions for common aspect ratios.
π Prompt Saver β Don't lose your prompts ever again, by saving their copy in the output folder (or specified subfolder).
π Prompt Loader β Load saved prompts easily from the dropdown list, and connect to the Positive/Negative nodes.
Known issue: Occasionally, not every LoRA will be visible on Civitai as the hash will not be recognized correctly. It's most likely caused by models' updates on Civitai, and re-downloading the model solves the issue.
pip install safetensors
Find Mango Node Pack in the ComfyUI Manager!
OR
git clone https://github.com/mang01010/MangoNodePack.git
MangoNodePack
folder into ComfyUIβs custom_nodes
directory.π‘ Category: Metadata
π‘ Category: Metadata
π‘ Category: Metadata
π‘ Category: Loaders
π‘ Category: Sampling
π‘ Category: Metadata
π‘ Category: Loaders
π‘ Category: Metadata
Once installed, find the MangoNodePack nodes inside ComfyUI.
Example Workflow:
This project is licensed under the MIT License β see the LICENSE file for details.