Original Concept by AloeVera_Purple
Revamped by Graybles
In the words of its original creator: “This workflow will take your input images, distribute them into the two different IPAdapter models, with different timesteps (distribution in time basically), and shift your results, like a LORA would… but in this case, you don’t have to train anything. It has likeness scores up to 95%. + With the right settings, it can be incredibly accurate. Unfortunately, there are no “Golden” settings that work for all. You’ll have to tweak things a little bit, up and down. See what works best for you.”
More information and a “How to Use” can be found in the Update that AloeVera made him/herself check out: https://civitai.com/articles/2345/2024-update-aloeveras-instant-lora-enhanced
Revamp Info:
Greetings everyone, quick word as to the why I created and uploaded this. Recently IPAdapter’s Developers released v2 material and it broke some of AloeVera’s original nodes. I took it upon myself to patch up and while I was at it implement newer files to his/her Workflow. So, it’s up-to-date and working better than ever.
Changes:
Better Batch Loader
It now allows for easy addition of more pictures should you want to do that
Upgraded Nodes from some of the permanent Broken ones
In AloeVera’s latest Workflow this pertains to the Adapter#1 and Adapter#2 Nodes. (These have been replaced with Advanced Nodes that came with the Updates)
File Updates
clip_vision_1.5.safetensors –> CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
ip-adapter-plus_sd15.bin –> Latest Update
ip-adapter-plus-face_sd15.bin –> Latest Update
File Additions
Added ip-adapter-plus_sdxl_vit-h.bin –> SDXL Specific Compatibility
Added ip-adapter-plus-face_sdxl_vit-h.bin –> SDXL Specific Compatibility
Setup:
Install ComfyUI Manager by ltdrdata ( https://github.com/ltdrdata/ComfyUI-Manager )
This will make sure you can easily install the missing nodes you’ll need for this Workflow to function.
Download the *.zip file containing the Workflow and all the extra files you’ll need.
Launch ComfyUI and Load the Workflow
Use Manager to install the Missing Nodes and then restart ComfyUI (there should be no Red Colored Nodes after this step)
Put the Extra Files into the Correct Folders
CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors –> Copy this into your ComfyUI\models\clip_vision Folder
The 4 *.bin Files –> Copy these into your ComfyUI\models\ipadapter Folder
If at this point you don’t have these folders in the Model folder it’s perfectly okay to create them.
How to Use:
Basically, you just load at least 6 Images into the Image Loaders. Fill in the Prompts as per usual. Choose your preferred settings and Checkpoints in the 2 pipeloaders and then generate.
The Top output is the Output of just your Prompt and Settings.
The Bottom Output is the one that also uses your 6 images as a guideline like a LoRa would be used.