Added IPADAPTER, improved Adetailer. Thanks to prodajie for feedback and suggested improvements!
Perfil de execução
Descrição da fonte
For LoRAs, select them in wildcard processor and then copy them below into text field.
Shortcuts to navigate in the workflow are 1 , 2 , 3 , 4 .
FreeU_V2 Doesn't work well with anime so i keep it bypassed. There is a note that should help with setting it's values.
To use ADetailer (FaceDetailer) , upscale or controlnet , etc. click on the Enable Group button in Fast Groups Bypasser (rgthree) top left.
controlnet model for SDXL based checkpoints
3D posing (requires browser with hardware acceleration)
noobIPAMARK1_mark1.safetensors
Comentário gerado por IA
Explicação gerada por IA com base nos detalhes da fonte e da configuração. As sugestões são claramente identificadas.
Use this ComfyUI workflow to inpaint and upscale images, with ControlNet, regional IPAdapter conditioning, and FaceDetailer. Choose LoRAs in the wildcard processor and copy them into a text field; the workflow produces inpainted or upscaled images and includes CivitAI metadata, a
Use shortcuts 1, 2, 3, and 4 to navigate the workflow.
To use FaceDetailer, upscaling, or ControlNet, click Enable Group in Fast Groups Bypasser (rgthree) at the top left.
For LoRAs, select them in the wildcard processor, then copy them into the text field.
Before downloading, check that the CivitAI listing shows version v3 by Blinkdotleh.
Sugestão
Listed node packs include ComfyUI_Mira, rgthree-comfy, comfyui-impact-subpack, comfyui_ultimatesdupscale, comfyui_ipadapter_plus, comfyui_controlnet_aux, comfyui-impact-pack, and comfyui-detail-daemon.
Other listed node packs are comfyui-inpaint-cropandstitch, comfyui-custom-scripts, comfyui_smznodes, ComfyUI_Comfyroll_CustomNodes, comfyui-image-saver, comfyui_fearnworksnodes, and ComfyLiterals.
Listed model files include bbox/face_yolov9c.pt, clip_vision_g.safetensors, Comfyui_00001_.safetensors, controlnet-union-sdxl-1-promax.safetensors, djmilxlvae_dminVae.safetensors, noobIPAMARK1_mark1.safetensors, RealESRGAN_x4plus_anime_6B.pth, sam_vit_b_01ec64.pth, and segm/`
For anime, consider leaving FreeU_V2 bypassed; the description says it does not work well with anime.
Sugestão · não verificado
For SDXL-based checkpoints, the description links a ControlNet model.
3D posing requires a browser with hardware acceleration; the listing says the workflow is best on a 1440p display.
The listing does not state a license; check the source page's terms before reusing or sharing the workflow.
Sugestão
Isso precisa ser editado?
Faça login para enviar uma solicitação de edição.
Fontes
1 fonteTrechos de fonte
1 trechoSource context: 1674 downloads · Type Workflows · Base model Other
comfyanonymous/clip_vision_g
Best on a 1440p display. >:]
Estimativa de requisito VRAM
Estimativa indisponível
5,15 GB distribuídos em 4 de 9 arquivos de modelo. Total de arquivos do modelo + 25% de overhead de carregamento + 2 GB de buffer de execução, arredondado para cima.
Requisitos
Requisitos 24Object Detector · Hugging Face
Vision model · 3.44 GB · Hugging Face · comfyanonymous/clip_vision_g
Comfyui_00001_.safetensors
Não resolvidoCheckpoint · Unknown
controlnet-union-sdxl-1-promax.safetensors
Não resolvidoControlNet · Unknown
djmilxlvae_dminVae.safetensors
Não resolvidoVAE · Civitai · 1257377
noobIPAMARK1_mark1.safetensors
EncontradoCheckpoint · 1.31 GB · Hugging Face · wtz37/sdxl
RealESRGAN_x4plus_anime_6B.pth
Não resolvidoUpscaler · Unknown
Segmentation · 358 MB · Hugging Face · comfyuistudio/sam_vit_b_01ec64.pth
Object Detector · 52.3 MB · PT · Hugging Face · Bingsu/adetailer
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
comfyui_ipadapter_plus
PossívelPacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry