After testing numerous community workflows, I created this version to keep the generation process simple, reliable and easy to understand.
Profil d'exécution
Description de la source
FLUX Power LoRA + ControlNet + Face Detailer (Simple)
A clean and beginner-friendly FLUX workflow focused on realistic character generation.
After testing numerous community workflows, I created this version with one goal in mind: keeping things simple while maintaining high-quality results.
This workflow combines the tools I use most often for character photography and LoRA showcase generation:
FLUX Dev
Power LoRA Loader
Flux ControlNet
Face Detailer
Commentaire généré par l’IA
Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.
FLUX Power LoRA + ControlNet Pose + Face Detailer (Simple) is for generating realistic character images—such as portraits, lifestyle, fashion, social media, and showcase images—from text prompts, source images, LoRA choices, and pose/depth guidance, with a decoded image as the ou
The process encodes prompts, loads a source image, prepares depth guidance, applies Flux ControlNet, loads a LoRA, samples, applies Face Detailer, decodes, and saves an image.
Use a text prompt, source image, LoRA selection, and pose/depth guidance as the described inputs.
Suggestion · non vérifié
The output is a decoded image saved by the workflow.
Download version v1.0 Initial Release from https://civitai.com/models/2674282?modelVersionId=3002771; it is published by YelomythLabs.
Suggestion
The listed base model is Flux.1 D, and the item is classified as Workflows.
Listed node packs are cg-use-everywhere, comfyui_controlnet_aux, comfyui-impact-pack, comfyui-impact-subpack, rgthree-comfy, and x-flux-comfyui.
Listed model files are ae.safetensors, bbox/face_yolov8m.pt, clip_l.safetensors, depth_anything_v2_vitl.pth, flux-depth-controlnet-v3.safetensors, flux1-dev-fp8.safetensors, and t5xxl_fp8_e4m3fn.safetensors.
Listed pins are cg-use-everywhere 7.8.0, comfyui-impact-pack 8.28.2, comfyui-impact-subpack 1.3.5, rgthree-comfy 1.0.2604070017, and x-flux-comfyui 00328556efc9472410d903639dc9e68a8471f7ac.
For medium-distance and full-body generations, use the included Face Detailer; the description says it helps maintain facial consistency and preserve smaller details at greater distances.
Suggestion · non vérifié
You can customize the workflow by adjusting the Power LoRA Loader, Flux ControlNet, Face Detailer, and VRAM Cleanup components.
Suggestion · non vérifié
Before use, verify that your setup includes comfyui_controlnet_aux, depth_anything_v2_vitl.pth, bbox/face_yolov8m.pt, flux1-dev-fp8.safetensors, and ae.safetensors.
Suggestion · non vérifié
No license is specified for this workflow.
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
3 extraitsSource context: 210 downloads · Type Workflows · Base model Flux.1 D
VRAM Cleanup
The workflow is designed to be easy to understand, easy to modify, and practical for everyday use without unnecessary complexity.
Ideal For
Character LoRAs
Portrait Photography
Lifestyle Images
Fashion Photography
Social Media Content
Showcase Images
Notes
A Face Detailer node is included and highly recommended for medium-distance and full-body generations. It helps maintain facial consistency and preserves smaller details that can become less defined at greater distances.
This is the workflow used for many of the images featured on my IdentityLabs profile.
Feel free to customize it and make it your own.
Estimation des besoins VRAM
Estimation indisponible
22,3 GB sur 5 de 7 fichiers de modèle. Total des fichiers du modèle + 25 % de surcharge de chargement + 2 Go de tampon d'exécution, arrondi à l'unité supérieure.
Exigences
Exigences 13Object Detector · 49.6 MB · Hugging Face · Bingsu/adetailer
Text encoder · 235 MB · SAFETENSORS · Hugging Face · Comfy-Org/stable-diffusion-3.5-fp8
Checkpoint · Hugging Face · AyushSahaUndergrad/Depth-Anything-V2-vitl-checkpoint
ControlNet · 1.39 GB · SAFETENSORS · Hugging Face · XLabs-AI/flux-controlnet-collections
Checkpoint · 16.1 GB · Hugging Face · Comfy-Org/flux1-dev
Text encoder · 4.56 GB · SAFETENSOR · fp8 · Hugging Face · comfyanonymous/flux_text_encoders
Pack de nœud · Registry
comfyui_controlnet_aux
PossiblePack de nœud · Registry
Source context: 176 downloads · Type Workflows · Base model Flux.1 D
Source context: 175 downloads · Type Workflows · Base model Flux.1 D
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry
Pack de nœud · Registry