"description":"Nodes: ModelSamplerTonemapNoiseTest, ReferenceOnlySimple, RescaleClassifierFreeGuidanceTest, ModelMergeBlockNumber, ModelMergeSDXL, ModelMergeSDXLTransformers, ModelMergeSDXLDetailedTransformers.<p style='background-color: black; color: red;'>This is a consolidation of the previously separate custom nodes. Please delete the sampler_tonemap.py, sampler_rescalecfg.py, advanced_model_merging.py, sdxl_model_merging.py, and reference_only.py files installed in custom_nodes before.</p>"
"description":"ComfyUI nodes based on the paper '<a href='https://arxiv.org/abs/2307.10159'/>FABRIC: Personalizing Diffusion Models with Iterative Feedback</a>' (Feedback via Attention-Based Reference Image Conditioning)"
"description":"A collection of custom nodes for ComfyUI. Includes a quick canny edge detection node with unconventional settings, simple LoRA stack nodes for workflow efficiency, and a customizable aspect ratio node."
"description":"Nodes: Load Image (Base64), Load Mask (Base64), Send Image (WebSocket), Crop Image, Apply Mask to Image. Provides nodes geared towards using ComfyUI as a backend for external tools."
"description":"Nodes:LatentGarbageCollector. This ComfyUI custom node flushes the GPU cache and empty cuda interprocess memory. It's helpfull for low memory environment such as the free Google Colab, especially when the workflow VAE decode latents of the size above 1500x1500."
"description":"Nodes:Attention couple. This is a custom node that manipulates region-specific prompts. While vanilla ComfyUI employs an area specification method based on latent couples, this node divides regions using attention layers within UNet."
"description":"A custom ComfyUI node designed for rapid latent upscaling using a compact neural network, eliminating the need for VAE-based decoding and encoding."
"description":"Nodes: QRNG Node CSV. A node that takes in an array of random numbers from the ANU QRNG API and stores them locally for generating quantum random number noise_seeds in ComfyUI"
},
{
"author":"Lerc",
"title":"Canvas Tab",
"reference":"https://github.com/Lerc/canvas_tab",
"files":[
"https://github.com/Lerc/canvas_tab"
],
"install_type":"git-clone",
"description":"This extension provides a full page image editor with mask support. There are two nodes, one to receive images from the editor and one to send images to the editor."
"description":"A collection of nodes which can be useful for animation in ComfyUI. The main focus of this extension is implementing a mechanism called loopchain. A loopchain in this case is the chain of nodes only executed repeatly in the workflow. If a node chain contains a loop node from this extension, it will become a loop chain."
"description":"This extension consists of auxiliary nodes for automatic calculation of latent sizes, an all-in-one node for SDXL's t2i, i2i, and scaling/hiresfix, and nodes capable of loading the Pixelbuster library.<p style='background-color: black; color: red;'>NOTE:Currently, the Pixelbuster library includes libraries for Windows and Linux environments by default. For other environments such as OSX, you will need to build and use Pixelbuster directly from <a href='https://github.com/Beinsezii/pixelbuster' target='blank'>here</a>.</P>"
Dr.Lt.Data
1 year ago