## ComfyUI Jake Upgrade
A [ComfyUI](https://github.com/comfyanonymous/ComfyUI) workflow customization by Jake.
If you like what I share, please support me with [PayPal](https://paypal.me/jakechaikefu).
## Installation
1. `git clone https://github.com/jakechai/ComfyUI-JakeUpgrade` into the `custom_nodes` folder
- e.g. `custom_nodes\ComfyUI-JakeUpgrade`
OR: Install using ComfyUI Manager.
2. Open a Command Prompt/Terminal/etc.
3. Change to the `custom_nodes\ComfyUI-JakeUpgrade` folder you just created
- e.g. `cd C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-JakeUpgrade`
4. Install python packages
- **Windows Standalone installation** (embedded python):
`../../../python_embeded/python.exe -s -m pip install -r requirements.txt`
OR: run install.bat.
- **Manual/non-Windows installation**
`pip install -r requirements.txt`
## Video Introduction
- txt2img&img2img workflow: [Youtube](https://www.youtube.com/watch?v=PKnxhFZNu2c) [Bilibili](https://www.bilibili.com/video/BV1h6421f7AQ/)
- txt2img&img2img SD3 workflow: [Youtube](https://youtu.be/MZBNzaWHdr8) [Bilibili](https://www.bilibili.com/video/BV1ceHheqEru/)
- prompt generation workflow: [Youtube](https://youtu.be/h_2PimL3iXY) [Bilibili](https://www.bilibili.com/video/BV1FZp4ebEjK/)
- img2mesh workflow: [Youtube](https://www.youtube.com/watch?v=CbG2Vq3kps0) [Bilibili](https://www.bilibili.com/video/BV1CE4m1R7br/)
- 3D-Pack Installation Tips๏ผ [Youtube](https://www.youtube.com/watch?v=RjuoLMCpvbI) [Bilibili](https://www.bilibili.com/video/BV1Nm421375F/)
- 3D-Pack Algorithm Comparison๏ผ [Youtube](https://www.youtube.com/watch?v=E7Oj8UUGLic) [Bilibili](https://www.bilibili.com/video/BV1CU411U7y4/)
## JakeUpgrade Workflow
### Main
- [JK_workflow_txt2img_img2img_SD3](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Main/JK_workflow_txt2img_img2img_SD3.json)
- [JK_workflow_txt2img_img2img_SDXL](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Main/JK_workflow_txt2img_img2img_SDXL.json)
- [JK_workflow_txt2img_img2img_SD15](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Main/JK_workflow_txt2img_img2img_SD15.json)
- [JK_workflow_txt2prompt_img2prompt](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Main/JK_workflow_txt2prompt_img2prompt.json)
- [JK_workflow_img2mesh_CRM&Zero123plus&MVDream&CharacterGen](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Main/JK_workflow_img2mesh_CRM&Zero123plus&MVDream&CharacterGen.json)
- [JK_workflow_img2mesh_Unique3D&Wonder3D&Era3D](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Main/JK_workflow_img2mesh_Unique3D&Wonder3D&Era3D.json)
- [JK_workflow_img2mesh_Zero123&SV3D](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Main/JK_workflow_img2mesh_Zero123&SV3D.json)
- [JK_workflow_img2mesh_3DGS](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Main/JK_workflow_img2mesh_3DGS.json)
> [!NOTE]
> - ComfyUI-3D-Pack needs pytorch 2.3.0+cu121 and xformers, but the latest ComfyUI_windows_portable version uses pytorch 2.3.1+cu121 or higher, you should separate those two ComfyUI.
> - ComfyUI-3D-Pack 3DMesh | 3DGS Preview not working seems to be related to the frontend change of ComfyUI. Fall back to the legacy frontend by adding `--front-end-version Comfy-Org/ComfyUI_legacy_frontend@latest` to the command line argument. [ComfyUI/pull/4379](https://github.com/comfyanonymous/ComfyUI/pull/4379).
> - [CXH joy caption](https://github.com/StartHua/Comfyui_CXH_joy_caption) conflicts with [VLM Nodes](https://github.com/gokayfem/ComfyUI_VLM_nodes) and is not included in the prompt generation workflow.
### Module
- [JK_workflow_NoiseInjectionVariation](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Module/JK_Workflow_NoiseInjectionVariation.json)
- [JK_workflow_Concept](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Module/JK_workflow_Concept.json)
- [JK_workflow_Seamless Texture](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Module/JK_workflow_Seamless%20Texture.json)
- [JK_workflow_Detailer](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Module/JK_workflow_Detailer.json)
- [JK_workflow_Inpaint](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Module/JK_workflow_Inpaint.json)
- [JK_workflow_txt2img_Simple](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Module/JK_workflow_txt2img_Simple.json)
- [JK_workflow_Upscale](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Module/JK_workflow_Upscale.json)
- [JK_Workflow_Mesh-ReMesh_Projection](https://github.com/jakechai/ComfyUI-JakeUpgrade/blob/master/Workflow/Module/JK_Workflow_Mesh-ReMesh_Projection.json)
## Required Custom Nodes
### Common
- [rgthree](https://github.com/rgthree/rgthree-comfy)
- [pythongosssss](https://github.com/pythongosssss/ComfyUI-Custom-Scripts)
- [ControlNet AUX](https://github.com/Fannovel16/comfyui_controlnet_aux)
- [Impact Pack](https://github.com/ltdrdata/ComfyUI-Impact-Pack)
- [Inspire Pack](https://github.com/ltdrdata/ComfyUI-Inspire-Pack)
- [IP Adapter Plus](https://github.com/cubiq/ComfyUI_IPAdapter_plus)
- [KJ Nodes](https://github.com/kijai/ComfyUI-KJNodes)
- [Essentials](https://github.com/cubiq/ComfyUI_essentials)
- [WAS Node Suite](https://github.com/WASasquatch/was-node-suite-comfyui)
- [JakeUpgrade](https://github.com/jakechai/ComfyUI-JakeUpgrade)
### txt2img_img2img workflow
- [Adv ControlNet](https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet)
- [Segment Anything](https://github.com/storyicon/comfyui_segment_anything)
- [NNLatentUpscale](https://github.com/Ttl/ComfyUi_NNLatentUpscale)
- [Ultimate SD Upscale](https://github.com/ssitu/ComfyUI_UltimateSDUpscale)
- [Seamless tiling](https://github.com/spinagon/ComfyUI-seamless-tiling)
- [Comfyroll](https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes)
- [ComfyUI Noise](https://github.com/BlenderNeko/ComfyUI_Noise)
- [Face Analysis](https://github.com/cubiq/ComfyUI_FaceAnalysis)
- [StyleAligned](https://github.com/brianfitzgerald/style_aligned_comfy)
- [ComfyUI ELLA](https://github.com/TencentQQGYLab/ComfyUI-ELLA)
- [Dynamic Prompts](https://github.com/adieyal/comfyui-dynamicprompts)
- [One Button Prompt](https://github.com/AIrjen/OneButtonPrompt)
- [Portrait Master](https://github.com/florestefano1975/comfyui-portrait-master)
- [Flux Prompt Generator](https://github.com/fairy-root/Flux-Prompt-Generator)
- [Merlin Magic Photo Prompter](https://github.com/Xclbr7/ComfyUI-Merlin)
- [WD14 Tagger](https://github.com/pythongosssss/ComfyUI-WD14-Tagger)
- [VLM Nodes](https://github.com/gokayfem/ComfyUI_VLM_nodes)
- [IF AI Tools](https://github.com/if-ai/ComfyUI-IF_AI_tools)
### img2mesh workflow
- [ComfyUI 3D Pack](https://github.com/MrForExample/ComfyUI-3D-Pack)
### Install and copy | replace files
- [ComfyUI Manager](https://github.com/ltdrdata/ComfyUI-Manager) : Copy _JK.pack in the replacement folder to `custom_nodes\ComfyUI-Manager\component'.
- [Prompt Stylers](https://github.com/wolfden/ComfyUi_PromptStylers) : Copy new styles (optional).
> [!NOTE]
> - Make sure to replace _JK.pack again if it's updated.
> - img2mesh workflow doesn't need to copy _JK.pack or prompt styles.
## JK_workflow : txt2img_img2img
โน๏ธ See More Information
### 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:
Image Resolution
Load SDXL Ckpt | Vae for Base | Refine | Upscale | Detailer | In/Out Paint
FreeU SDXL settings
Auto Variation SDXL settings
Disable SD15 ELLA Text Encode (in Base Model Sub Workflow JK๐)
Enable SDXL Text Ecode (in Base Model Sub Workflow JK๐) (Optional)
Enable SDXL Refine Text Encode (in Refine Sub Workflow JK๐) (optional)
Switch plus, plus-face, and faceid ipadapter to sdxl_vit-h version
Switch faceid lora to sdxl version
Switch Image Upscale ControlNet Depth|Tile to sdxl version (in Upscale Sub Workflow JK๐)
Switch NNLatentUpscale version to SDXL
Set Ultimate SD Upscale Tile size to 1024
Switch Detailer's Add Detail Lora to SDXL version
Use Load ControNet++ Model of ComfyUI Advanced ControNet to load xinsir controlnet union inpaint/outpaint for Inpaint/Outpaint ControlNet in I/O Paint process
Enable Black Pixel switch for Inpaint/Outpaint ControlNet in I/O Paint process
(If it is SD15, choose the opposite)
Other:
1. Nodes State JK๐ 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.
### Explanation
- Overall Workflow
- Image Comparer
- Project Setting
- Base Model Parameters
- TI Parameters
- Fine Tune String 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
## JK_workflow : img2mesh
โน๏ธ See More Information
### Introduction
Hotkey:
\`: Main Workflow Control Pannels
Workflow Control:
Each img2mesh workflow contains several sub-workflows as the filename indicates.
Each sub-workflow consists of one or more sub-steps.
Each sub-step saves the result as images or meshes when it finishes generation.
Each sub-step can switch from generation mode to loading mode.
It's recommended to enable sub-step step by step and switch to loading mode after the generation.
Other:
TripoSR workflow is not included because it is straightforward.
Triplane workflow is not included because it is straightforward.
### Explanation
- Workflow breakdown: img2mesh types
- Workflow breakdown: CRM&Zero123plus&MVDream&CharacterGen
- Workflow breakdown: JUnique3D&Wonder3D&Era3D
- Workflow breakdown: Zero123&SV3D
- Workflow breakdown: 3DGS
- Workflow Control Panels: CRM&Zero123plus&MVDream&CharacterGen
- Workflow Control Panels: Unique3D&Wonder3D&Era3D
- Workflow Control Panels: Zero123&SV3D
- Workflow Control Panels: 3DGS
## JakeUpgrade Custom Nodes
โน๏ธ See More Information
Misc Nodes
SD1.5 Aspect Ratio JK๐
SDXL Aspect Ratio JK๐
Reroute Nodes
Reroute List JK๐
Reroute Ckpt JK๐
Reroute Vae JK๐
Reroute Sampler JK๐
Reroute Upscale JK๐
Reroute Resize JK๐
Reroute String JK๐
ControlNet Nodes
Apply ControlNet JK๐
Multi-ControlNet Stack JK๐
Apply Multi-ControlNet JK๐
Apply Multi-ControlNet SD3 JK๐
LoRA Nodes
Load LoRA JK๐
LoRA Stack JK๐
Embedding Nodes
Embedding Picker JK๐
Embedding Picker Multi JK๐
Loader Nodes
Ckpt Loader JK๐
Vae Loader JK๐
Sampler Loader JK๐
Upscale Model Loader JK๐
Pipe Nodes
Nodes State JK๐
Ksampler Parameters JK๐
Project Setting JK๐
Base Model Parameters JK๐
Base Model Parameters Extract JK๐
Base Image Parameters Extract JK๐
Base Model Pipe JK๐
Base Model Pipe Extract JK๐
Refine Pipe JK๐
Refine Pipe Extract JK๐
Noise Injection Parameters JK๐
Noise Injection Pipe Extract JK๐
Refine Model Parameters JK๐
Refine 1 Parameters Extract JK๐
Refine 2 Parameters Extract JK๐
Upscale Model Parameters JK๐
Image Upscale Parameters Extract JK๐
Latent Upscale Parameters Extract JK๐
Upscale Model Parameters Extract JK๐
Detailer Parameters JK๐
Pipe End JK๐
Metadata Pipe JK๐
Metadata Pipe Extract JK๐
Image Nodes
Save Image With Metadata JK๐
Save Image With Metadata Flow JK๐
Load Image With Metadata JK๐
Enchance And Resize Hint Images JK๐
Remove Image Alpha JK๐
Animation Nodes
Animation Prompt JK๐
Animation Value JK๐
Logic switches Nodes
Boolean JK๐
Image Input Switch JK๐
Mask Input Switch JK๐
Int Input Switch JK๐
Float Input Switch JK๐
Latent Input Switch JK๐
Conditioning Input Switch JK๐
Clip Input Switch JK๐
Model Input Switch JK๐
ControlNet Input Switch JK๐
Text Input Switch JK๐
VAE Input Switch JK๐
Switch Model and CLIP JK๐
Pipe Input Switch JK๐
Impact Pipe Input Switch JK๐
Mesh Input Switch JK๐
Ply Input Switch JK๐
Orbit Pose Input Switch JK๐
ComfyMath Fix Nodes
BoolToInt JK๐
IntToBool JK๐
BoolUnaryOp JK๐
BoolBinaryOp JK๐
StringBinaryCon JK๐
Prompt Combine JK๐
FloatUnaryCon JK๐
FloatBinaryCon JK๐
IntUnaryCon JK๐
IntBinaryCon JK๐
NumberUnaryCon JK๐
NumberBinaryCon JK๐
Vec2UnaryCon JK๐
Vec2BinaryCon JK๐
Vec2ToFloatUnaryOp JK๐
Vec2ToFloatBinaryOp JK๐
Vec2FloatOp JK๐
Vec3UnaryCon JK๐
Vec3BinaryCon JK๐
Vec3ToFloatUnaryOp JK๐
Vec3ToFloatBinaryOp JK๐
Vec3FloatOp JK๐
Vec4UnaryCon JK๐
Vec4BinaryCon JK๐
Vec4ToFloatUnaryOp JK๐
Vec4ToFloatBinaryOp JK๐
Vec4FloatOp JK๐
ComfyMath Nodes
FloatToInt JK๐
IntToFloat JK๐
IntToNumber JK๐
NumberToInt JK๐
FloatToNumber JK๐
NumberToFloat JK๐
ComposeVec2 JK๐
ComposeVec3 JK๐
ComposeVec4 JK๐
BreakoutVec2 JK๐
BreakoutVec3 JK๐
BreakoutVec4 JK๐
FloatUnaryOp JK๐
FloatBinaryOp JK๐
IntUnaryOp JK๐
IntBinaryOp JK๐
NumberUnaryOp JK๐
NumberBinaryOp JK๐
Vec2UnaryOp JK๐
Vec2BinaryOp JK๐
Vec3UnaryOp JK๐
Vec3BinaryOp JK๐
Vec4UnaryOp JK๐
Vec4BinaryOp JK๐
Simple Evaluate Nodes
Evaluate Ints JK๐
Evaluate Floats JK๐
Evaluate String JK๐
Evaluate Examples JK๐
3D Nodes
Orbit Poses JK๐
OrbitLists to OrbitPoses JK๐
OrbitPoses to OrbitLists JK๐
## JakeUpgrade Group Nodes
โน๏ธ See More Information
Tools
JK๐::CLIPSegMask
JK๐::Pad Image for Outpainting
JK๐::SegAnythingMask
JK๐::Image to Prompt (LLava Local)
JK๐::Image to Prompt Advanced (LLava Local)
Workflow
JK๐::Concept
JK๐::Inpaint Simple
JK๐::Inpaint Checkpoint
JK๐::Outpaint Checkpoint
JK๐::txt2img
JK๐::Inpaint ControlNet
JK๐::Outpaint ControlNet
## Reference Custom Nodes
โน๏ธ See More Information
- [rgthree](https://github.com/rgthree/rgthree-comfy)
- [Comfyroll](https://github.com/Suzie1/ComfyUI_Comfyroll_CustomNodes)
- [Efficiency Nodes](https://github.com/jags111/efficiency-nodes-comfyui)
- [ControlNet AUX](https://github.com/Fannovel16/comfyui_controlnet_aux)
- [Impact Pack](https://github.com/ltdrdata/ComfyUI-Impact-Pack)
- [Image Saver](https://github.com/giriss/comfy-image-saver)
- [Prompt Reader](https://github.com/receyuki/comfyui-prompt-reader-node)
- [ComfyMath](https://github.com/evanspearman/ComfyMath)
- [Embedding Picker](https://github.com/Tropfchen/ComfyUI-Embedding_Picker)
- [Layer Style](https://github.com/chflame163/ComfyUI_LayerStyle)
## Changelog
- 2024-06-23 - v1.0.0 released.
- 2024-07-11 - v1.0.6 Noise Injection for Upscale Workflow.
- 2024-07-16 - v1.0.7 Single Image to Mesh Workflow updated.
- 2024-07-21 - v1.0.8 Orbit Poses Constant nodes added. 3 Image to Mesh Workflows updated.
- 2024-07-22 - v1.0.9 3DGS workflow added.
- 2024-07-24 - v1.1.0 img2mesh workflow updated. Craftsman Mesh added.
Three OrbitPoses nodes been added to 3D-Pack.
- 2024-07-31 - v1.1.1 Prompt Combine node added.
- 2024-08-03 - v1.1.2 Resize to Focus added to image2mesh workflow.
- 2024-08-21 - v1.1.3 Random Beats node added (not for AIGC).
- 2024-09-01 - v1.2.0 SD3 workflow added. Noise Injection (Inspire) added.
Refine, Upscale, and Detailer process major updated.
SD15 Hand Fix supports SDXL and SD3 workflow.
SDXL IPAdapter supports SD3 workflow.
NoiseInjection Component and workflow added.
- 2024-09-04 - v1.2.1 In/Out Paint ControlNet Component added.
Inpaint Module Workflow updated.
SD15|SDXL|SD3 Workflow updated.
Image Remove Alpha JK node added.
- 2024-09-05 - v1.2.2 Black Pixel switch added for Inpaint ControlNet Component following ControlNet Preprocessor AUX Custom Node's update.
- 2024-09-06 - v1.2.3 Refinement Noise Injection added.
txt2prompt and img2prompt workflow added.
img2prompt component added.
- 2024-09-07 - v1.2.4 img2mesh workflow doesn't need _JK.pack, so that doesn't need to install segment anything, VLM nodes, and IF AI tools.
- 2024-09-09 - v1.2.5 Clip l, clip g, t5xxl texture encode logic upgrade.
Clip l & g switch added.
Negative g switch added.
SDXL Clip Text Encode Target Resolution Scale added.
- 2024-09-10 - v1.2.6 detailer: add detail lora.
- 2024-09-11 - v1.2.7 Magic Photo Prompter added.