¿Tienes un flujo de trabajo de ComfyUI? Obtén un Workflow Doc legible en tu navegador.Haz legible un flujo de trabajo.Pruébalo ahora ↗
I've spent a lot of time learning from others and tweaking this workflow, and I thought someone might find it useful. it is very customized to my need and way of thinking / working, but hopefully some part will make...
Perfil de ejecución
Descripción de la fuente
I've spent a lot of time learning from others and tweaking this workflow, and I thought someone might find it useful. it is very customized to my need and way of thinking / working, but hopefully some part will make sense / help you.
What it can do :
Save configuration of different checkpoints (recommended sampler, scheduler, cfg, positive and negative tags). I love to play with various models, and having a workflow per model was a pain, and keeping track of what settings worked for which model was cumbersome. This workflow adresses these issues.
Hint image will be resized to fit the picked resolution, will be used as latent if you set denoise below 1, and can be used by various control nets (depth, canny, scribble, openpose and tile)
FaceID IPA can be enabled (setup can be troublesome though, I've installed my comfy with miniforge and it worked like a charm). The workflow has a "FACE" prompt in the create group, that must match a folder in your input directory (change the path in the Face IPA group to match your setup). I usually put between 3 and 6 face photography of the subject, 512px square PNG.
Comentario generado por IA
Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.
All In One SDXl / Ill workflow is for generating Illustrious/SDXL images from text prompts or optional hint images; it can use depth, canny, scribble, openpose, and tile controls, enable FaceID IPA, PAG, Face Detailer, or upscaling, and save images with Civitai model and LoRA met
A practical pass is to run a batch without PAG, Face Detailer, or upscaling, then refine a selected image; checkpoint-specific sampler, scheduler, CFG, positive tags, and negative tags stay together with each checkpoint.
Sugerencia · sin verificar
An optional hint image is resized to the chosen resolution; with denoise below 1, it is used as the latent and can feed depth, canny, scribble, openpose, or tile controls.
You can generate prompts from a hint image with an LLM through Florence2, select a random line from a text file, or mix English with your natural language through Google Translate.
Dragging an image from the viewer into the workflow can recreate the workflow and seed used in that image generation.
To use the save-image node, clone https://github.com/nkchocoai/ComfyUI-SaveImageWithMetaData.git into /custom_nodes.
Sugerencia · sin verificar
For FaceID IPA, set the Face IPA path to an input folder whose name matches the FACE prompt, and use 3 to 6 square 512px PNG face photos.
Sugerencia · sin verificar
The workflow specifies these node packs: comfyui-kjnodes; comfyui-florence2; comfyui_tinyterranodes; pr-was-node-suite-comfyui-47064894; sd-perturbed-attention; comfyui_custom_nodes_alekpet; comfyui-easy-use; comfyroll; comfyui_ipadapter_plus.
It also specifies these node packs: comfyui-inspire-pack; comfyui-crystools; comfyui_ultimatesdupscale; comfyui_controlnet_aux; comfyui-saveimagewithmetadata; comfyui_fearnworksnodes; comfyui-impact-pack; comfyui-impact-subpack; rgthree-comfy.
It also specifies these model and file names: magicILL_magicILLEPSV2.safetensors; pixelAlchemy_pixelAlchemyV30.safetensors; 4x_foolhardy_Remacri.pth; diffusion_pytorch_model_V2.safetensors; BSSEquinoxILPNSemi_v10.safetensors; MiaoshouAI/Florence-2-large-PromptGen-v2.0; bridget統ోഒ
Fast Group Bypasser can match groups by color, giving separate toggles for power-ups and models; a toggle arrow centers the view on that group.
You can label reroute nodes from their outputs and move a reroute connection to switch model choice or turn PAG routing on when a direct condition is not possible.
FaceID IPA setup can be troublesome, and the Face Detailer may not be optimal.
PAG runs after the basic KSampler on a 1.3x-upscaled image, adds 14 steps to the render process, and requires manual routing when enabled.
¿Es necesario editarlo?
Inicia sesión para solicitar una edición.
Fuentes
1 fuenteExtractos de fuentes
1 extractoSource context: 3076 downloads · Type Workflows · Base model Illustrious
PAG / Perturbed Attention Guidance , discovered this last week and I think I like it. In this workflow, it will run after the basic ksampler, on an 1.3 x upscaled image. It adds 14 steps to the render process, so it's a personal choice. It can be toggled on and off (but you also need to wire the routing manually).
Face Detailer is there, but It might not be optimal, if you have any advice....
Upscaler is there too, nothing fancy.
for prompting, you can :
have an llm write the prompt based on the Hint image (Florence2)
pick a random line from a text file
mix english with your natural language, via google translate
Image saved will have correct metadata for Civitai (models and loras)
Tricks used :
Fast Group Bypasser node, from rgthree, can be setup to match only Groups of a certain color :
This way I've got 2 distinct "toggles" block, one for the power-ups, one for the models.
Worth noting : if you click the arrow next to a toggle, if will center your view on the selected group.
Reroute node can have a label, right click on the output to add / change :
So my workflow uses this when a condition is not possible with Comfy, for the model choice above, and for perturbed attention :
Here it's off, to wire it you just have to move the connexion :
And a pretty obvious one, but I've only found it recently : you can drag an image from the viewer to the workflow ; it will re-create the workflow and seed used in this image generation.
What I tend to do is run a batch without anything fancy (PAG, face detailer or upscaler), then pick one picture I like and try to improve it.
Setup
Install missing custom nodes and pray ? It won't work for the save image node I use, you'll have to clone it.
cd /custom_nodes git clone https://github.com/nkchocoai/ComfyUI-SaveImageWithMetaData.git
I've tried to add notes on the workflow, but my main advice is don't hesitate to trash parts of it for now, replace nodes or stuff you don't need, etc...
Most control net should be available on Comfy Model Manger.
Requisito de VRAM estimado
Estimación no disponible
13,5 GB en 4 de 22 archivos de modelos. Total de archivos de modelos + 25 % de sobrecarga de carga + 2 GB de margen de ejecución, redondeado hacia arriba.
Requisitos
39 requisitosUpscaler · 63.9 MB · PTH · Unknown
Object Detector · Hugging Face · bbox/face_yolov8n_v2.pt
Object Detector · Hugging Face · bbox/hand_yolov8s.pt
bridgetoonsMix_v40.safetensors
No resueltoCheckpoint · Unknown
BSSEquinoxILPNSemi_v10.safetensors
No resueltoCheckpoint · Unknown
CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors
No resueltoVision model · Unknown
Upscaler · Registry · ComfyUI_UltimateSDUpscale
controlnetxlCNXL_eugeoterDepth.safetensors
No resueltoControlNet · Unknown
diffusion_pytorch_model_V2.safetensors
EncontradoControlNet · 2.33 GB · SAFETENSORS · fp16 · full · Unknown
diffusion_pytorch_model.safetensors
PosibleControlNet · Unknown
dmd2_sdxl_4step_lora.safetensors
No resueltoLoRA · Unknown
hyphoriaRealIllu_v09.safetensors
No resueltoCheckpoint · Unknown
magicILL_magicILLEPSV2.safetensors
No resueltoCheckpoint · Unknown
matrixHentai_v50.safetensors
No resueltoCheckpoint · Unknown
MiaoshouAI/Florence-2-large-PromptGen-v2.0
Archivo sin verificarVision model · Hugging Face · MiaoshouAI/Florence-2-large-PromptGen-v2.0 · Florence 2 Large PromptGen v2.0
noobaiXLNAIXL_vPred10Version.safetensors
No resueltoCheckpoint · Unknown
noobIPAMARK1_mark1.safetensors
No resueltoCheckpoint · Unknown
ControlNet · 4.66 GB · SAFETENSORS · fp32 · full · Unknown
pixelAlchemy_pixelAlchemyV30.safetensors
No resueltoCheckpoint · Unknown
plantMilkModelSuite_hempII.safetensors
No resueltoCheckpoint · Unknown
plantMilkModelSuite_walnut.safetensors
EncontradoCheckpoint · 6.46 GB · SAFETENSOR · fp16 · Unknown
sam_vit_b_01ec64.pth
ConflictoSegmentation · Unknown
comfyroll
No resueltoPaquete de nodos · Registry
comfyui_controlnet_aux
PosiblePaquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
comfyui_ipadapter_plus
PosiblePaquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
comfyui-florence2
PosiblePaquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
pr-was-node-suite-comfyui-47064894
No resueltoPaquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
