If you encounter unsuccessful uploading of the image, please check: LAN or cloud service, please use https, port 8189 (Thanks to @Damien for feedback on the issue)
If you encounter difficulties in uploading images, please check the following: for local network or cloud services, please use HTTPS and the service on port 8189. (Thanks to @Damien for reporting the issue.)
??? Real-time Design
ScreenShareNode & FloatingVideoNode. Now comfyui supports capturing screen pixel streams from any software and can be used for LCM-Lora integration. Let's get started with implementation and design!
Voice + Real-time Face Swap Workflow
Preview Audio
text-to-audio
GPT
Support for calling multiple GPTs.Local LLM , ChatGPT, ChatGLM3 , ChatGLM4 , Some code provided by rui. If you are using OpenAI's service, fill in https://api.openai.com/v1 . If you are using a local LLM service, fill in http://127.0.0.1:xxxx/v1 . Azure OpenAI:https://xxxx.openai.azure.com
LLM_base_workflow
SiliconflowLLM
ChatGPTOpenAI
Prompt
PromptSlide
Layers
A new layer class node has been added, allowing you to separate the image into layers. After merging the images, you can input the controlnet for further processing.
The composite images node overlays a foreground image onto a background image at specified positions and scales, with optional blending modes and masking capabilities. position : 'overall',"center_center","left_bottom","right_bottom","left_top","center_top","right_top"
3D
workflow-4
LoadImagesFromURL
Conveniently load images from a fixed address on the internet to ensure that default images in the workflow can be executed.
TextImage
Download the font in custom_nodes/comfyui-mixlab-nodes/assets/fonts
MiniCPM-VQA Simple
This is the int4 quantized version of MiniCPM-V 2.6. Running with int4 version would use lower GPU memory (about 7GB).
Model
workflow-1
TransparentImage
FeatheredMask, SmoothMask
Add edges to an image.
LaMaInpainting (requires manual installation)
The pillow in simple-lama-inpainting causes a conflict and is temporarily removed from the dependency. If simple-lama-inpainting is installed, the node will be automatically added, and if there is no, it will not be automatically added.
_ briarmbg _ model was developed by BRlA Al and can be used as an open-source model for non-commercial purposes
Enhancement
Direct "Help" option accessible through node context menu.
"Nodes Map" feature added to global context menu.
An improvement has been made to directly redirect to GitHub to search for missing nodes when loading the graph.
*** If not needed, you can comment out app.showMissingNodesError in the ui_mixlab.js file.
Right-click shortcut
The right-click menu supports text-to-text, which is convenient for completing the word propt, and supports cloud LLM or local LLM. The right-click menu supports text-to-text conversion, facilitating prompt word completion, and supports cloud LLMs or local LLMs.
Local LLM API example: http://localhost:1234/v1
Models
Download TripoSR and place it in models/triposr
Download facebook/dino-vitb16 and place it in models/triposr/facebook/dino-vitb16
Download rembg Models, move to: models/rembg
Download lama, move to : models/lama
Download Salesforce/blip-image-captioning-base, move to : models/clip_interrogator/Salesforce/blip-image-captioning-base
Download succinctly/text2image-prompt-generator,moving to: models/prompt_generator/text2image-prompt-generator
Download Helsinki-NLP/opus-mt-zh-en,move to: models/prompt_generator/opus-mt-zh-en
Installation
manually install, simply clone the repo into the custom_nodes directory with this command:
cd ComfyUI/custom_nodes
git clone https://github.com/shadowcz007/comfyui-mixlab-nodes.git
Install the requirements:
run directly:
cd ComfyUI/custom_nodes/comfyui-mixlab-nodes
install.bat
