Ir para o conteúdo
WorkflowListadosExterno
Baixar

Wan2.2 I2V Fast And Quality [MORE MOTION + UPSCALE + INTERPOLATION] — v1.0

It was created

Fontecivitai.com/models/1899038
TarefaMúltiploCapacidadesImagem para imagem · Aumento de resoluçãoFamíliaWanVersãoRelease 2149588 — WAN 2.2 I2V Fast And Quality.jsonEstimado VRAM12 GiBUnratednota

Perfil de execução

Acesso
Fluxo de trabalho externo
Status
Listados
Versão
WAN 2.2 I2V Fast And Quality.json
Fonte
Civitai
Atualizado
3 de nov. de 2026

What you need

GPU memory
12 GiB
System memory
32 GiB
Model files
0.1 GiB known subtotal

Requisitos

Modelos

9

  • MiaoshouAI/Florence-2-base-PromptGen-v2.0

    Repositório identificado

    Vision model · Hugging Face · MiaoshouAI/Florence-2-base-PromptGen-v2.0

  • RealESRGAN_x2plus.pth

    Encontrado

    Upscaler · 64.0 MB · PTH · Unknown

  • rife49.pth

    Encontrado

    Checkpoint · 20.4 MB · PTH · Unknown

  • umt5_xxl_fp8_e4m3fn_scaled.safetensors

    Repositório identificado

    Text encoder · Unknown

  • wan_2.1_vae.safetensors

    Repositório identificado

    VAE · Unknown

  • WAN2.2 I2V High 4 Steps.safetensors

    Não resolvido

    LoRA · Unknown

  • WAN2.2 I2V High_Q4_K_M.gguf

    Não resolvido

    Diffusion model · Unknown

  • WAN2.2 I2V Low_Q4_K_M.gguf

    Não resolvido

    Diffusion model · Unknown

  • WAN2.2I2V Low 4 Steps.safetensors

    Não resolvido

    LoRA · Unknown

Pacotes de nós

15

  • comfy-mtb

    Encontrado

    Pacote de nós · Registry

  • comfyui_memory_cleanup

    EncontradoOpcional

    Pacote de nós · Registry

  • comfyui-dream-video-batches

    Encontrado

    Pacote de nós · Registry

  • comfyui-easy-use

    Encontrado

    Pacote de nós · Registry

  • comfyui-florence2

    Encontrado

    Pacote de nós · GitHub · kijai/ComfyUI-Florence2

  • comfyui-frame-interpolation

    Encontrado

    Pacote de nós · Registry

  • ComfyUI-GGUF

    Possível

    Pacote de nós · Registry

  • ComfyUI-Jjk-Nodes

    Encontrado

    Pacote de nós · Registry

  • comfyui-kjnodes

    Encontrado

    Pacote de nós · Registry

  • comfyui-logicutils

    Encontrado

    Pacote de nós · Registry

  • comfyui-unload-model

    EncontradoOpcional

    Pacote de nós · Registry

  • comfyui-videohelpersuite

    Encontrado

    Pacote de nós · Registry

  • crt-nodes

    Encontrado

    Pacote de nós · Registry

  • Label (rgthree)

    Não resolvido

    Pacote de nós · Unknown

  • rgthree-comfy

    Encontrado

    Pacote de nós · Registry

Comentário gerado por IA

Explicação gerada por IA com base nos detalhes da fonte e da configuração. As sugestões são claramente identificadas.

Propósito

  • Use this image-to-video workflow to turn an image into a video, then upscale the video and interpolate its frames.

Fluxo

  • The author describes three samplers and paths with and without LoRA.

Entradas e saídas

  • The author gives an example output of a 5-second, 16 fps, 480p video upscaled to 960p at 32 fps.

Configuração

  • The base model is Wan Video 2.2 I2V-A14B.

Dependências

  • Model files listed for this workflow include MiaoshouAI/Florence-2-base-PromptGen-v2.0, RealESRGAN_x2plus.pth, rife49.pth, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, WAN2.2 I2V High_Q4_K_M.gguf, and WAN2.2 I2V Low_Q4_K_M.gguf.

  • Listed node packs include comfy-mtb, comfyui-dream-video-batches, comfyui-easy-use, comfyui-florence2, comfyui-frame-interpolation, ComfyUI-GGUF, ComfyUI-Jjk-Nodes, comfyui-kjnodes, comfyui-logicutils, comfyui-videohelpersuite, crt-nodes, and rgthree-comfy.

Configuração

  • The description lists 2-step and 4-step high/low options, with and without LoRA.

  • The author calls 9 steps at 480p their quality/speed sweet spot and recommends Sageattention.

Precauções

  • The author says NSFW generation is possible but that they have not tested it.

Isso precisa ser editado?

Faça login para enviar uma solicitação de edição.

Fontes

1 fonte
CivitaiPrimárioVersão 2149588
civitai.com/models/1899038

Verificado 3 de nov.

Workflow instructions

Author notes from WAN 2.2 I2V Fast And Quality.json · selected release

I Use The GGUF Q4_K_M on my Rtx 3080Ti with 12GB of Vram and 32GB of Ram

Author notes from WAN 2.2 I2V Fast And Quality.json · selected release

Green is Positve Red Negative Blue are stuff you change sometimes Black are stuff you won't change usually Yellow are "advanced" stuff you can change Purple is for stuff you can bypass

Author notes from WAN 2.2 I2V Fast And Quality.json · selected release

You can Bypass the Upscaler and Interporlation to save ram, or generation time

Author notes from WAN 2.2 I2V Fast And Quality.json · selected release

If you take this last frame and use it as a input youre ensentially extending the video

Author notes from WAN 2.2 I2V Fast And Quality.json · selected release

Models I use:

Download files

Artefatos de modelo

2 artefatos

wan22I2VFastAndQualityMORE_v10.zip

zip · 9,24 KB · SHA-256 88fea0ae5e54…4f5f · Civitai

Download file

WAN 2.2 I2V Fast And Quality.json

json · 50,2 KB · SHA-256 2610bd101022…682d

Download file

Trechos de fonte

3 trechos
Note3 de nov.civitai.com/models/1899038

Source context: 997 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note2 de out.civitai.com/models/1899038

Source context: 971 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note19 de jul.civitai.com/models/1899038

Source context: 880 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B