Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
This workflow is designed to help you easily understand how to generate consistent faces using PuLID in Flux.
Profil d'exécution
Description de la source
This workflow is designed to help you easily understand how to generate consistent faces using PuLID in Flux.
While the basic node is configured with a GGUF model, users who prefer to use standard Flux models can easily switch to the ClipLoader and Diffusion Model included in the workflow's Options.
The workflow provides step-by-step instructions for connecting and configuring PuLID nodes, making it easy even for beginners to follow. Detailed information about where to download and how to install the required models is included within the workflow.
Additionally, this workflow supports the integration of LoRA) models, allowing you to incorporate specific styles or character features into your image generation. By applying LoRA, you can effectively enhance the base model's output with desired styles or characteristics, enabling the creation of more diverse results.
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.
Use the [FLUX] PuLID + LORA simple workflow to generate images with consistent faces using PuLID. It takes text prompts and input images, can apply LoRA models for styles or character features, and provides preview and saved-image outputs.
The workflow loads models, encodes text, applies PuLID guidance, samples and decodes an image, and supports comparison, preview, and saving.
Enter a text prompt through CLIPTextEncode and provide an image through LoadImage.
PreviewImage and SaveImage provide preview and saved-image outputs.
The workflow includes step-by-step guidance for connecting and configuring PuLID nodes, plus information about downloading and installing required models.
Model files named in the workflow include: clip_l.safetensors, FLUX_VAE_diffusion_pytorch_model.safetensors, flux1-dev-fp8.safetensors, flux1-dev-Q8_0.gguf, pulid_flux_v0.9.0.safetensors, t5xxl_fp16.safetensors, and t5xxl_fp8_e4m3fn.safetensors.
Named workflow nodes include ApplyPulidFlux, BasicGuider, BasicScheduler, CLIPTextEncode, DualCLIPLoader, DualCLIPLoaderGGUF, EmptySD3LatentImage, FluxGuidance, Image Comparer (rgthree), KSamplerSelect, LoadImage, and Power Lora Loader (rgthree).
Other named workflow nodes are PreviewImage, PulidFluxEvaClipLoader, PulidFluxInsightFaceLoader, PulidFluxModelLoader, RandomNoise, SamplerCustomAdvanced, SaveImage, UNETLoader, UnetLoaderGGUF, VAEDecode, and VAELoader.
The basic node uses a GGUF model, while Options includes ClipLoader and Diffusion Model for switching to standard Flux models.
LoRA models can add specific styles or character features to generated images.
The base model is Flux.1 D.
Before use, verify that pulid_flux_v0.9.0.safetensors, EmptySD3LatentImage, BasicGuider, DualCLIPLoader, and UnetLoaderGGUF are available in your setup.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
1 extraitSource context: 1653 downloads · Type Workflows · Base model Flux.1 D
=========================================================
이 워크플로우는 Flux에서 PuLID를 활용하여 일관된 얼굴을 생성하는 방법을 쉽게 이해할 수 있도록 구성되었습니다.
기본 노드는 GGUF 모델로 설정되어 있으나, 일반 Flux 모델을 사용하시려는 분들은 워크플로우의 Option에 포함된 ClipLoader와 Diffusion Model로 쉽게 전환하여 사용하실 수 있습니다.
PuLID 노드의 연결과 설정 방법을 초보자도 쉽게 따라할 수 있도록 단계별로 정리했으며, 워크플로우 내에 필요한 모델들의 다운로드 위치와 설치 방법을 상세히 기재해두었습니다.
또한, 이 워크플로우는 LoRA모델을 추가하여 사용할 수 있도록 구성되어 있어,
원하는 스타일이나 특정 캐릭터의 특징을 이미지 생성에 반영할 수 있습니다.
LoRA를 적용하면 기본 모델의 결과물에 원하는 스타일이나 특성을 더욱 효과적으로 반영할 수 있어 더욱 다양한 결과물을 얻을 수 있습니다.
A1 [contact & follow & like & Buzz]
Mail : a01demort@gmail.com
CIVITAI : https://civitai.com/user/a01demort
Youtube : https://www.youtube.com/@A01demort
Instagram : https://www.instagram.com/a01demort/
Naver Cafe : https://cafe.naver.com/sdfkorea
sdhotline : https://sdhotline.com/
Estimation des besoins VRAM
Estimation indisponible
37,2 GB sur 5 de 12 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 30Text encoder · 235 MB · SAFETENSORS · Unknown
DualCLIPLoader
Non résoluText encoder · Unknown
DualCLIPLoaderGGUF
Non résoluText encoder · Unknown
FLUX_VAE_diffusion_pytorch_model.safetensors
Non résoluVAE · Unknown
Checkpoint · 11.5 GB · SAFETENSORS · Unknown
Checkpoint · 11.8 GB · GGUF · fp16 · Unknown
pulid_flux_v0.9.0.safetensors
Non résoluCheckpoint · Unknown
PulidFluxEvaClipLoader
Non résoluText encoder · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Unknown
Text encoder · 4.56 GB · SAFETENSOR · fp8 · Unknown
VAEDecode
Non résoluVAE · Unknown
VAELoader
Non résoluVAE · Unknown
ApplyPulidFlux
Non résoluPack de nœud · Unknown
BasicGuider
Non résoluPack de nœud · Unknown
BasicScheduler
Non résoluPack de nœud · Unknown
CLIPTextEncode
Pack de nœud · Unknown
EmptySD3LatentImage
Non résoluPack de nœud · Unknown
FluxGuidance
Non résoluPack de nœud · Unknown
Image Comparer (rgthree)
Non résoluPack de nœud · Unknown
KSamplerSelect
Non résoluPack de nœud · Unknown
LoadImage
Non résoluPack de nœud · Unknown
Power Lora Loader (rgthree)
Non résoluPack de nœud · Unknown
PreviewImage
Non résoluPack de nœud · Unknown
PulidFluxInsightFaceLoader
Non résoluPack de nœud · Unknown
PulidFluxModelLoader
Non résoluPack de nœud · Unknown
RandomNoise
Non résoluPack de nœud · Unknown
SamplerCustomAdvanced
Non résoluPack de nœud · Unknown
SaveImage
Non résoluPack de nœud · Unknown
UNETLoader
Non résoluPack de nœud · Unknown
UnetLoaderGGUF
Non résoluPack de nœud · Unknown
