Tem um workflow do ComfyUI? Gere uma documentação legível direto no navegador.Torne um workflow legível.Experimentar agora ↗
Important credit for this workflow goes to pftq for creating the seamless video extend workflow . That workflow was the first to show me this feature existed and gave the building blocks I used to make this version....
Perfil de execução
Descrição da fonte
Important credit for this workflow goes to pftq for creating the seamless video extend workflow . That workflow was the first to show me this feature existed and gave the building blocks I used to make this version. The workflow by pftq uses Kijai's Wan Wrapper nodes, so if you prefer to work with the wrapper nodes in order to make use of all the options and add-ons, then by all means give pftq's workflow a try. This workflow uses all native ComfyUI nodes for the Wan processing.
This I2V workflow is based on my earlier Wan Join Clips workflow. This simplified version is designed to extend a video using Wan with Vace based on a single beginning frame. Yes, I know Wan Image-to-Video already exists, but the results you get from using the Vace system can be quite different, so I think this is a useful tool.
The workflow looks large, but once you've made sure all your models are loading correctly and your video save paths are set the way you like, you should only need to use the three groups across the top-left. You set your initial image (and reference image, if you like), you set other values like steps and so on, then you run the workflow and check your output. All of the masking, resizing, and frame interpolation/smoothing is automated.
Comentário gerado por IA
Explicação gerada por IA com base nos detalhes da fonte e da configuração. As sugestões são claramente identificadas.
Use Wan Vace Image-to-Video to extend a video with Wan and Vace from a single beginning frame. Provide an initial image, an optional reference image, and settings such as steps; the workflow produces an extended video.
Masking, resizing, and frame interpolation or smoothing are handled automatically after you set the inputs.
Additional controls are exposed in other groups for further adjustment.
Inputs include an initial image, an optional reference image, settings such as steps, and video save paths; the output is an extended video.
Before running, make sure the models load correctly and set your video save paths.
Sugestão · não verificado
Wan processing uses native ComfyUI nodes.
The workflow lists these model files: gimmvfi_r_arb_lpips_fp32.safetensors, umt5_xxl_fp16.safetensors, wan_2.1_vae.safetensors, Wan2_1-VACE_module_14B_fp8_e4m3fn.safetensors, and Wan2.1-VACE-14B-Q4_K_M.gguf.
The workflow lists these node packs: comfyui-logicutils, comfyui-easy-use, comfy-image-saver, gguf, ComfyLiterals, rgthree-comfy, and comfyui-impact-pack.
It also lists comfyui-gguf, comfyui_layerstyle, comfyui-kjnodes, comfyui-rmbg, comfyui-videohelpersuite, and ComfyUI-GIMM-VFI.
Use the three groups across the top-left to set the initial image, optional reference image, and values such as steps.
Sugestão · não verificado
Additional settings include Model Sampling Shift and interpolation controls.
Before running, verify that these files are available: gimmvfi_r_arb_lpips_fp32.safetensors, Wan2_1-VACE_module_14B_fp8_e4m3fn.safetensors, and Wan2.1-VACE-14B-Q4_K_M.gguf.
Sugestão · não verificado
Confirm the exact node-pack names for comfyui-gguf and ComfyUI-GIMM-VFI before using the workflow.
Sugestão · não verificado
Isso precisa ser editado?
Faça login para enviar uma solicitação de edição.
Fontes
1 fonteTrechos de fonte
1 trechoSource context: 712 downloads · Type Workflows · Base model Wan Video 14B t2v
All of the machinery is exposed in all the other groups below, so feel free to mess with anything you like. You will find a few settings buried inside that you may want to tweak, like the Model Sampling Shift value or the interpolation settings, for example.
On my machine, using the default values given here, my 16gb VRAM card can load and run this workflow without using any shared GPU memory and without block swapping. It runs at a steady 14.2gb, usually, though your mileage may vary.
I hope you enjoy.
Estimativa de requisito VRAM
Estimativa indisponível
10,6 GB distribuídos em 1 de 5 arquivos de modelo. Total de arquivos do modelo + 25% de overhead de carregamento + 2 GB de buffer de execução, arredondado para cima.
Requisitos
Requisitos 18gimmvfi_r_arb_lpips_fp32.safetensors
Não resolvidoCheckpoint · Unknown
Text encoder · 10.6 GB · SAFETENSORS · Unknown
VAE · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged · Comfy-Org/Wan_2.1_ComfyUI_repackaged · Hugging Face
Wan2_1-VACE_module_14B_fp8_e4m3fn.safetensors
Não resolvidoCheckpoint · Unknown
Wan2.1-VACE-14B-Q4_K_M.gguf
Não resolvidoCheckpoint · Unknown
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
comfyui-gguf
PossívelPacote de nós · Registry
ComfyUI-GIMM-VFI
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
