4b727015dd67367ade797f1c60b26bdea1f4d7cf
ComfyUI Jake Upgrade
A ComfyUI workflow customization by Jake.
Installation
git clone https://github.com/jakechai/ComfyUI-JakeUpgradeinto thecustom_nodesfolder- e.g.
custom_nodes\ComfyUI-JakeUpgradeOR: Install using ComfyUI Manager.
- e.g.
- Open a Command Prompt/Terminal/etc.
- Change to the
custom_nodes\ComfyUI-JakeUpgradefolder you just created- e.g.
cd C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-JakeUpgrade
- e.g.
- Install python packages
- Windows Standalone installation (embedded python):
run install.bat
OR:
../../../python_embeded/python.exe -s -m pip install -r requirements.txt - Manual/non-Windows installation
pip install -r requirements.txt
- Windows Standalone installation (embedded python):
run install.bat
OR:
Video Introduction
Youtube Bilibili
JakeUpgrade Workflow
Main:
- JK_workflow_tex2img_img2img_SDXL
- JK_workflow_tex2img_img2img_SD15
- JK_workflow_Seamless Texture
- JK_workflow_img2mesh_single
- JK_workflow_img2mesh_single_Unique3D
- JK_workflow_img2mesh_multi
(Tips: ComfyUI-3D-Pack needs pytorch 2.2+cu121, but the latest ComfyUI_windows_portable version uses pytorch 2.3+cu121, you should separate those two ComfyUI.)
Other:
- JK_workflow_Concept
- JK_workflow_Detailer
- JK_workflow_Inpaint
- JK_workflow_tex2img_Simple
- JK_workflow_Upscale
Required Custom Nodes
To use JK_workflow, you need to install:
- rgthree
- Comfyroll
- pythongosssss
- ControlNet AUX
- Impact Pack
- Inspire Pack
- WD14 Tagger
- ComfyUI Noise
- IP Adapter Plus
- Face Analysis
- StyleAligned
- NNLatentUpscale
- Dynamic Prompts
- One Button Prompt
- ComfyUI ELLA
- Essentials
- WAS Node Suite
- Ultimate SD Upscale
- ComfyUI 3D Pack
- Seamless tiling
- Portrait Master
- JakeUpgrade
Install and copy | replace files (see in replacement folder):
- ComfyUI Manager : Copy _JK.pack in the replacement folder to `custom_nodes\ComfyUI-Manager\component'.
- Prompt Stylers : Copy new styles (optional).
JK_workflow : tex2img_img2img_Complete : Introduction
Hotkey:
0: usage guide
\`: overall workflow
1: base, image selection, & noise injection
2: embedding, fine tune string, auto prompts, & adv conditioning parameters
3: lora, controlnet parameters, & adv model parameters
4: refine parameters
5: detailer parameters
6: upscale parameters
7: In/Out Paint parameters
Workflow Control:
All switches in any Workflow panel take effect in realtime.
All switches in any Select panel also affect sub workflow, but don't take effect in realtime, which needs preprocessing.
All switches in Parameters panel that affect sub workflow don't take effect in realtime, which needs preprocessing.
Suggested method:
Preprocessing needs to be executed before actural generation for switches in Select or Parameters panels to control the sub workflow.
Pre-Queue Prompt: It's recommended to disable all processes in the Overall Workflow panel and adjust all sub-workflow-related switches before running Queue Prompt. The state of corresponding switches in Pre-process panels will be changed automatically after the preprocessing.
Pre-process Pannel: Alternatively, you can preprocess manually by setting the corresponding switches in the Pre-process Pannel to the same state as in the Parameters Pannel, which does not need a Pre-Queue Prompt.
Metadata:
All parameters including sub-workflow-related switches will affect the generation result and also the content of Metadata saved with the image.
In Refine image saving, remove noise_jinection_metadata link if not refining any noise injection process.
In Upscale image saving, remove noise_jinection_metadata or refine_metadata link if not using Noise Injection or refine process.
In Detailer image saving, remove noise_jinection_metadata, refine_metadata or upscale_metadata link if not using Noise Injection or refine process.
SDXL switches:
Load SDXL Ckpt for Base | Refine | Upscale | Detailer | In/Out Paint
Load SDXL Vae for Base | Detailer
FreeU SDXL settings
Auto Variation SDXL settings
Disable SD15 ELLA Text Encode (in Base Model Sub Workflow JK🐉)
Enable SDXL Text Ecode (in Base Model Sub Workflow JK🐉) (Optional)
Enable SDXL Refine Text Encode (in Refine Sub Workflow JK🐉) (optional)
Disable IPAdapter 2 - faceid (in Refine Sub Workflow JK🐉)
Switch plus and plus-face ipadapter to sdxl_vit-h version
Switch Image Upscale ControlNet Tile to sdxl version (in Upscale Sub Workflow JK🐉)
Switch NNLatentUpscale version to SDXL
(If it is SD15, choose the opposite)
Other:
1. Nodes State JK🐉 uses target nodes' id to control their active | mute | bypass mode. Need to update node_id_list if you make a copy.
2. The order of Detailer Progress and Upscale Progress can be swapped. Please avoid to form loops.
JK_workflow : tex2img_img2img_Complete : Explanation
- Overall Workflow
- Project Setting
- Base Model Parameters
- TI Parameters
- Auto Variation Prompt Parameters
- Advanced Conditioning Parameters
- Lora Parameters
- Control Net Parameters
- Advanced Model Parameters
- Refine Process Parameters
- Upscale Process Parameters
- Detailer Process Parameters
- In/Out Paint Process Parameters
JakeUpgrade Custom Nodes
Misc Nodes
SD1.5 Aspect Ratio JK🐉
SDXL Aspect Ratio JK🐉
Reroute Nodes
Reroute List JK🐉
Reroute Ckpt JK🐉
Reroute Vae JK🐉
Reroute Sampler JK🐉
Reroute Upscale JK🐉
Reroute Resize JK🐉
ControlNet Nodes
Apply ControlNet JK🐉
Multi-ControlNet Stack JK🐉
Apply Multi-ControlNet JK🐉
LoRA Nodes
Load LoRA JK🐉
LoRA Stack JK🐉
Embedding Nodes
Embedding Picker JK🐉
Embedding Picker Multi JK🐉
Loader Nodes
Ckpt Loader JK🐉
Vae Loader JK🐉
Sampler Loader JK🐉
Upscale Model Loader JK🐉
Pipe Nodes
Nodes State JK🐉
Ksampler Parameters JK🐉
Project Setting JK🐉
Base Model Parameters JK🐉
Base Model Parameters Extract JK🐉
Base Image Parameters Extract JK🐉
Base Model Pipe JK🐉
Base Model Pipe Extract JK🐉
Refine Pipe JK🐉
Refine Pipe Extract JK🐉
Noise Injection Parameters JK🐉
Refine Model Parameters JK🐉
Refine 1 Parameters Extract JK🐉
Refine 2 Parameters Extract JK🐉
Upscale Model Parameters JK🐉
Image Upscale Parameters Extract JK🐉
Latent Upscale Parameters Extract JK🐉
Upscale Model Parameters Extract JK🐉
Detailer Parameters JK🐉
Pipe End JK🐉
Metadata Pipe JK🐉
Metadata Pipe Extract JK🐉
Image Nodes
Save Image With Metadata JK🐉
Save Image With Metadata Flow JK🐉
Load Image With Metadata JK🐉
Enchance And Resize Hint Images JK🐉
Animation Nodes
Animation Prompt JK🐉
Animation Value JK🐉
Logic switches Nodes
Boolean JK🐉
Image Input Switch JK🐉
Mask Input Switch JK🐉
Int Input Switch JK🐉
Float Input Switch JK🐉
Latent Input Switch JK🐉
Conditioning Input Switch JK🐉
Clip Input Switch JK🐉
Model Input Switch JK🐉
ControlNet Input Switch JK🐉
Text Input Switch JK🐉
VAE Input Switch JK🐉
Switch Model and CLIP JK🐉
Pipe Input Switch JK🐉
Impact Pipe Input Switch JK🐉
ComfyMath Fix Nodes
BoolToInt JK🐉
IntToBool JK🐉
BoolUnaryOp JK🐉
BoolBinaryOp JK🐉
FloatUnaryCon JK🐉
FloatBinaryCon JK🐉
IntUnaryCon JK🐉
IntBinaryCon JK🐉
NumberUnaryCon JK🐉
NumberBinaryCon JK🐉
Vec2UnaryCon JK🐉
Vec2BinaryCon JK🐉
Vec2ToFloatUnaryOp JK🐉
Vec2ToFloatBinaryOp JK🐉
Vec2FloatOp JK🐉
Vec3UnaryCon JK🐉
Vec3BinaryCon JK🐉
Vec3ToFloatUnaryOp JK🐉
Vec3ToFloatBinaryOp JK🐉
Vec3FloatOp JK🐉
Vec4UnaryCon JK🐉
Vec4BinaryCon JK🐉
Vec4ToFloatUnaryOp JK🐉
Vec4ToFloatBinaryOp JK🐉
Vec4FloatOp JK🐉
ComfyMath Nodes
FloatToInt JK🐉
IntToFloat JK🐉
IntToNumber JK🐉
NumberToInt JK🐉
FloatToNumber JK🐉
NumberToFloat JK🐉
ComposeVec2 JK🐉
ComposeVec3 JK🐉
ComposeVec4 JK🐉
BreakoutVec2 JK🐉
BreakoutVec3 JK🐉
BreakoutVec4 JK🐉
FloatUnaryOp JK🐉
FloatBinaryOp JK🐉
IntUnaryOp JK🐉
IntBinaryOp JK🐉
NumberUnaryOp JK🐉
NumberBinaryOp JK🐉
Vec2UnaryOp JK🐉
Vec2BinaryOp JK🐉
Vec3UnaryOp JK🐉
Vec3BinaryOp JK🐉
Vec4UnaryOp JK🐉
Vec4BinaryOp JK🐉
Simple Evaluate Nodes
Evaluate Ints JK🐉
Evaluate Floats JK🐉
Evaluate String JK🐉
Evaluate Examples JK🐉
JakeUpgrade Group Nodes
Tools
JK🐉::CLIPSegMask
JK🐉::Pad Image for Outpainting
JK🐉::SegAnythingMask
Workflow
JK🐉::Concept
JK🐉::Inpaint Simple
JK🐉::Inpaint Checkpoint
JK🐉::Outpaint Checkpoint
JK🐉::Tex2Img
Reference Custom Nodes
Jake Upgrade Nodes are inspired by:
- rgthree
- Comfyroll
- Efficiency Nodes
- ControlNet AUX
- Impact Pack
- Image Saver
- Prompt Reader
- ComfyMath
- Embedding Picker
Changelog
- 2024-06-23 - v1.0.0 released.
Languages
Python
53.9%
JavaScript
46%
Batchfile
0.1%
























