Update 26.11.24 This workflow eliminates the need for a face and skin detailer. The idea is to render directly at a significantly higher resolution and then correct any imperfections in the image using a simple...
Perfil de execução
Descrição da fonte
Update 26.11.24 This workflow eliminates the need for a face and skin detailer. The idea is to render directly at a significantly higher resolution and then correct any imperfections in the image using a simple ultimate upscaling process.
Additionally, image details are enhanced through the Detail Daemon and additional noise injection. In the initial samplers, the sigmas are split to allow the first steps to render with high guidance and the final steps with low guidance. This makes the images appear more natural and less AI-like.
This approach works very well but requires extremely powerful hardware and is not particularly fast. However, the resulting images are of exceptionally high quality.
Update 07.10.24
The workflow now supports GGUF models, improved ViT-L/14 CLIP, and has a significantly enhanced UltimateUpscaler thanks to the fill nodes.
Comentário gerado por IA
Explicação gerada por IA com base nos detalhes da fonte e da configuração. As sugestões são claramente identificadas.
This ComfyUI workflow uses Flux.1 D to render high-resolution portraits, then upscales them to correct image imperfections.
Detail Daemon and added noise injection are used to enhance image details.
Sampling splits the sigmas so early steps use high guidance and final steps use low guidance.
The creator says this approach avoids the need for a separate face and skin detailer.
Flux model download links are in the workflow notes.
Required ComfyUI node packs include ComfyUI-Impact-Pack, ComfyUI-Impact-Subpack, ComfyUI_essentials, ComfyUI-Inspire-Pack, and ComfyUI_Comfyroll_CustomNodes.
Named model files include epicrealism_naturalSinRC1VAE.safetensors, more_details.safetensors, sam_vit_b_01ec64.pth, and t5xxl_fp16.safetensors.
The description lists GGUF model support, an improved ViT-L/14 CLIP, and fill nodes for UltimateUpscaler.
Plan for a demanding run: the creator describes this workflow as extremely hardware-intensive and reports about 10–12 minutes per image on an RTX 3090.
Sugestão · não verificado
Isso precisa ser editado?
Faça login para enviar uma solicitação de edição.
Fontes
1 fonteTrechos de fonte
2 trechosSource context: 11497 downloads · Type Workflows · Base model Flux.1 D
Attention: The skin detailer with upscaler workflow is extremely hardware-intensive. On an RTX 3090, it takes about 10-12 minutes to generate a single image. If you want to generate images faster, please use the older workflow.
Flux is a 12 billion parameter model and it's simply amazing!!! Here’s a workflow from me that makes your face look even better, so you can create stunning portraits.
You can find the download links for the Flux model in the notes within the workflow.
Remaining hardware or download-size estimates are not available yet.
Requisitos
4xFaceUpSharpDAT.pth
Não resolvidoUpscaler · Unknown
Object Detector · Hugging Face · bbox/Eyeful_v1.pt
Source context: 11485 downloads · Type Workflows · Base model Flux.1 D
Object Detector · Hugging Face · bbox/face_yolov8n_v2.pt
clip_l.safetensors
PossívelText encoder · Unknown
CR Upscale Image
Arquivo não verificadoUpscaler · Unknown
DualCLIPLoader
PossívelText encoder · Unknown
epicrealism_naturalSinRC1VAE.safetensors
EncontradoVAE · 1.99 GB · SAFETENSORS · fp16 · Unknown
LoRA · 9.11 MB · SAFETENSORS · Unknown
Segmentation · 358 MB · PTH · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Unknown
VAEDecode
PossívelVAE · Unknown
VAELoader
PossívelVAE · Unknown
BasicGuider
Não resolvidoPacote de nós · Unknown
BasicScheduler
PossívelPacote de nós · Unknown
CheckpointLoaderSimple
PossívelPacote de nós · Unknown
CLIPTextEncode
PossívelPacote de nós · Unknown
CR SDXL Aspect Ratio
EncontradoPacote de nós · Unknown
DetailerForEach
PossívelPacote de nós · Unknown
EmptyLatentImage
PossívelPacote de nós · Unknown
Pacote de nós · Unknown
Image Comparer (rgthree)
Não resolvidoPacote de nós · Unknown
Pacote de nós · Unknown
ImageSharpen
PossívelPacote de nós · Unknown
ImpactSEGSOrderedFilter
EncontradoPacote de nós · Unknown
ImpactSimpleDetectorSEGS
EncontradoPacote de nós · Unknown
KSamplerSelect
PossívelPacote de nós · Unknown
LoraLoader
PossívelPacote de nós · Unknown
Pacote de nós · Unknown
RandomNoise
Não resolvidoPacote de nós · Unknown
SAMLoader
EncontradoPacote de nós · Unknown
SamplerCustomAdvanced
Não resolvidoPacote de nós · Unknown
SaveImage
PossívelPacote de nós · Unknown
SegsToCombinedMask
EncontradoPacote de nós · Unknown
SubtractMaskForEach
EncontradoPacote de nós · Unknown
UltralyticsDetectorProvider
EncontradoPacote de nós · Unknown
UNETLoader
PossívelPacote de nós · Unknown