Just rolled out a real-time inpainting pipeline using SAM2 and Comfystream , running on an 4090 via RunPod. Followed this guide to get runpod template and required models.
Perfil de execução
Descrição da fonte
Real-Time Inpainting Workflow
Just rolled out a real-time inpainting pipeline using SAM2 and Comfystream , running on an 4090 via RunPod. Followed this guide https://pipelines.livepeer.org/docs/technical/getting-started/install-comfystream#remote-gpu to get runpod template and required models.
Custom nodes:
SAM2 for segmentation: https://github.com/neverbiasu/ComfyUI-SAM2
Comentário gerado por IA
Explicação gerada por IA com base nos detalhes da fonte e da configuração. As sugestões são claramente identificadas.
Use this workflow to inpaint an input image: LoadImage names the image input, SAM2 handles segmentation, Crop Stitch and Impact Pack are the inpainting modules, and PreviewImage is the named preview output.
Other listed processing nodes include InpaintCropImproved, InpaintStitchImproved, KSampler, and VAEDecode.
LoadImage is the named image input, and PreviewImage is the named preview output.
The described setup uses Comfystream on a 4090 via RunPod and links a remote-GPU guide for the RunPod template and required models.
Named node packs include ComfyUI-SAM2, ComfyUI-Inpaint-CropAndStitch, and ComfyUI-Impact-Pack.
Other listed node packs are ComfyUI-Depth-Anything-Tensorrt, ComfyUI-Torch-Compile, ComfyUI-Stream-Pack, and ComfyUI_TensorRT.
Other listed node names are CLIPLoader; CLIPTextEncode; ControlNetApplyAdvanced; ControlNetLoader; DepthAnythingTensorrt; DifferentialDiffusion; FeatureBankAttentionProcessor; GroundingDinoModelLoader (segment anything2); GroundingDinoSAM2Segment (segment anything2); GrowMask; I
The listed base model is SD 1.5.
Before use, check that your local files include CLIPText/model.fp16.safetensors and control_v11f1p_sd15_depth_fp16.safetensors.
Sugestão · não verificado
Isso precisa ser editado?
Faça login para enviar uma solicitação de edição.
Fontes
1 fonteTrechos de fonte
1 trechoSource context: 142 downloads · Type Workflows · Base model SD 1.5
Inpainting modules :
Impact Pack: https://github.com/ltdrdata/ComfyUI-Impact-Pack
I'll be sharing more real-time workflows soon— follow me on X to stay updated !
Estimativa de requisito VRAM
Estimativa indisponível
Os tamanhos de arquivos do modelo ainda não estão completos o suficiente para calcular este requisito.
Requisitos
Requisitos 26CLIPLoader
PossívelText encoder · Unknown
CLIPText/model.fp16.safetensors
Não resolvidoText encoder · Hugging Face · CLIPText/model.fp16.safetensors
control_v11f1p_sd15_depth_fp16.safetensors
Não resolvidoControlNet · Unknown
GroundingDinoModelLoader (segment anything2)
Arquivo não verificadoSegmentation · Unknown · ComfyUI-SAM2
GroundingDinoSAM2Segment (segment anything2)
Arquivo não verificadoSegmentation · Unknown · ComfyUI-SAM2
SAM2ModelLoader (segment anything2)
Arquivo não verificadoSegmentation · Unknown · ComfyUI-SAM2
VAE · Unknown · ComfyUI-Torch-Compile
VAEDecode
PossívelVAE · Unknown
VAELoader
PossívelVAE · Unknown
CLIPTextEncode
PossívelPacote de nós · Unknown
ControlNetApplyAdvanced
PossívelPacote de nós · Unknown
ControlNetLoader
PossívelPacote de nós · Unknown
Pacote de nós · Unknown
DifferentialDiffusion
Não resolvidoPacote de nós · Unknown
Pacote de nós · Unknown
GrowMask
PossívelPacote de nós · Unknown
ImageResize+
PossívelPacote de nós · Unknown
Pacote de nós · Unknown
Pacote de nós · Unknown
InpaintModelConditioning
PossívelPacote de nós · Unknown
Pacote de nós · Unknown
KSampler
PossívelPacote de nós · Unknown
LoadImage
PossívelPacote de nós · Unknown
PreviewImage
PossívelPacote de nós · Unknown
Pacote de nós · Unknown
Pacote de nós · Unknown