Easy Regional v0.6 - (Please read the Prompt Guide & installation requirements)
This ComfyUI workflow is designed for SDXL/Illustrious models, with built-in support for multi-character image generation. It features an all-in-one solution, with txt2img > hires fix > face detailer. The primary goal of this workflow is to provide an intuitive, easy-to-use UI that mirrors A1111 / Invoke, while remaining flexible for advanced use cases. The final image will include embedded metadata to make uploading to Civitai easier.
Regional LoRA Support!
Regional LoRAs are now supported. To add a LoRA to a region, type <lora:LORA_NAME:STRENGTH> [TRIGGER_WORD] into the region you wish the LoRA to apply to eg: (works best with characters)
<lora:lauma_genshin_impact_ilxl_goofy:1.0> lauma \(genshin impact\)Prompt Guide
Common Prompt: Tags shared between regions such as, quality and background tags. Use this to define the amount of people and their gender eg. 2girls or 1boy, 1girl etc.
masterpiece, best quality, absurdres, outdoors, park, bench, sunny, sunrays, 2girls, front view, straight onRegion 1: First character and/or specific details to this region (start this prompt with the gender of the character male or female NOT 1girl or 1boy)
female, hatsune miku, aqua eyes, long hair, twin tails, hair orniment, white shirt, collard shirt, bare shoulders, black sleeves, pleated miniskirt, black thighhighs, sittingRegion 2: Second character and/or specific details to this region (start this prompt with the gender of the character)
female, frieren, green eyes, pointy ears, twin tails, red earrings, capelet, striped top, white skirt, cuddlingNegative prompt: Standard negative prompt tags, nothing fancy going on here
lowres, worst quality, bad quality, watermark, signatureSuggested Resolutions:
1024 x 1024
896 x 1152
832 x 1216
1152 x 896
1216 x 832
Installation Requirements
If the input fields on the nodes are in the incorrect place after installing the custom nodes, please redownload the workflow and the connections should be correct.
This workflow requires the following model types:
Base model:
ComfyUI/models/checkpointsVAE eg. sdxl-vae-fp16-fix:
ComfyUI/models/vaeUpscale Model eg. remacri:
ComfyUI/models/upscale_models
This workflow also requires these node packs in order to function, these can be easily installed via the built-in Custom Nodes Manager:
Description
Fixed broken subnode issues due to comfyui updates
FAQ
Comments (10)
Hi! Thanks for sharing the workflow.
I'm having a strange issue: the workflow only works the first time I drag/load the original file into ComfyUI. After running it once, or if I open another workflow in another tab and come back, it fails with:
AttributeError: 'NoneType' object has no attribute 'model'
The traceback points to:
RES4LYF\beta\samplers.py
I already installed the required nodes: Image Saver, Impact Pack, rgthree-comfy, RES4LYF, and Impact Subpack. I also updated/restarted ComfyUI, but RES4LYF stays as nightly.
Do you know if this workflow requires a specific RES4LYF version/commit, or if this is a known cache/state issue?
Thank you!
Hmm seems like a node is trying to pass a model name to a sampler. I'll look into it!
Also having this issue! So strange that it works the first time and then not again
I've had a look into some of the subnodes and I've patched v0.6 on the model page, please redownload and see if the issue persists. Let me know if there are any issues!
I know this isn't my thread, but it seems to be working fine for me now! Thank you :3
It works now! Thank you so much for the quick fix.
You're the best. I've tried a lot of regional prompter workflows, but honestly nothing comes close to yours. Amazing work!
I think you should clarify the parameter region_bleed_start_step. After countless failed attempts, I only found its relevant explanation within your example image. The default value of this parameter is 0—or it may be hidden internally—which prevents effective generation of multiple characters in a scene.
is possible to add a 3rd regional prompt or it's only for ttwo
how do I add another region? is that possible?
Thank you very much for this workflow! This helps me a ton in working on my OCs and creating some unique images! I would love to see a three character or four character workflow in the future but I understand this can be difficult to do so I can only hope for one. Otherwise, thanks again for the hard work.