WorkflowPublicadoExterno

【WAN2.2】KONTEXT to VIDEO — v1.2

Change of execution order between interpolation and upscaling, really independent and better optimized.

TareaMúltipleCapacidadesImagen a imagen · Texto a imagen · AmpliaciónFamiliaWanVersiónRelease 1566569 — WAN2.1 - FACE to VIDEO 1.2.jsonVRAM estimadaNot yet characterizedUnratedcalidad

Perfil de ejecución

Acceso: Flujo externo
Estado: Publicado
Versión: WAN2.1 - FACE to VIDEO 1.2.json
Fuente: Civitai
Actualizado: 3 nov 2026

Descripción de la fuente

Bugfix : upscaling node

Add :

LoRA,

Change of execution order between interpolation and upscaling, really independent and better optimized.

What you need

Model files: 21.1 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requisitos

Modelos

4x_foolhardy_Remacri.pth
Encontrado
Upscaler · 63.9 MB · PTH · Unknown
ae.safetensors
Archivo especificado
VAE · 878 MB · Hugging Face · UmeAiRT/ComfyUI-Auto_installer
clip_vision_h.safetensors
No resuelto
Clip Vision · Unknown
flux1-dev-Q4_K_S.gguf
Encontrado
Diffusion model · 6.34 GB · GGUF · Unknown
pulid_flux_v0.9.0.safetensors
No resuelto
Checkpoint · Unknown
rife47.pth
Repositorio identificado
Checkpoint · Unknown
t5-v1_1-xxl-encoder-Q3_K_L.gguf
No resuelto
Text encoder · Unknown
Ume_sky_v3.safetensors
No resueltoOpcional
LoRA · Unknown
umt5_xxl_fp8_e4m3fn_scaled.safetensors
Encontrado
Text encoder · 6.27 GB · SAFETENSORS · U8 + FP16 + FP32 + FP8 (tensor header) · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
Unresolved model selection: PulidFluxEvaClipLoader
No resuelto
Text encoder · Unknown
ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors
No resuelto
Text encoder · Hugging Face · UmeAiRT/ComfyUI-Auto_installer
wan_2.1_vae.safetensors
Encontrado
VAE · 242 MB · SAFETENSORS · BF16 (tensor header) · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
wan2.1-i2v-14b-480p-Q3_K_S.gguf
Encontrado
Diffusion model · 7.38 GB · GGUF · Unknown

Paquetes de nodos

comfyui_pulid_flux_ll
Encontrado
Paquete de nodos · Registry
comfyui-custom-scripts
Encontrado
Paquete de nodos · Registry
comfyui-easy-use
Encontrado
Paquete de nodos · Registry
comfyui-frame-interpolation
Encontrado
Paquete de nodos · Registry
comfyui-gguf
Encontrado
Paquete de nodos · GitHub · city96/ComfyUI-GGUF
comfyui-impact-pack
Encontrado
Paquete de nodos · GitHub · ltdrdata/ComfyUI-Impact-Pack
comfyui-kjnodes
Encontrado
Paquete de nodos · GitHub · kijai/ComfyUI-KJNodes
comfyui-mxtoolkit
Encontrado
Paquete de nodos · Registry
comfyui-videohelpersuite
Encontrado
Paquete de nodos · Registry
Fast Bypasser (rgthree)
No resuelto
Paquete de nodos · Unknown
Fast Groups Bypasser (rgthree)
No resuelto
Paquete de nodos · Unknown
kijai/ComfyUI-KJNodes
Encontrado
Paquete de nodos · GitHub · kijai/ComfyUI-KJNodes
mxSlider2D
Encontrado
Paquete de nodos · Unknown
rgthree-comfy
Encontrado
Paquete de nodos · Registry

Comentario generado por IA

Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.

Propósito

Use 【WAN2.2】KONTEXT to VIDEO — v1.2 in ComfyUI to create an image from a text prompt or photo, turn that image into a video, and optionally upscale the image. Its inputs are text prompts or images, and its outputs are images, videos, and optionally upscaled images.

Flujo

It can generate an initial image with FLUX kontext and then create a video from that image, including by animating a person in a photo.
In v1.2, interpolation and upscaling are described as independent, and their execution order has changed.

Entradas y salidas

Generated images include all generation parameters in their metadata.

Configuración inicial

In ComfyUI, turn on Use Nodes V2 (Vue), refresh the page, and then load the workflow; the instructions warn of possible display problems otherwise.
Install ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching “UmeAiRT,” or use the UmeAiRT Auto-Installer.

Dependencias

Listed model files include 4x_foolhardy_Remacri.pth, ae.safetensors, clip_vision_h.safetensors, flux1-dev-Q4_K_S.gguf, pulid_flux_v0.9.0.safetensors, and rife47.pth.
Other listed model files include t5-v1_1-xxl-encoder-Q3_K_L.gguf, umt5_xxl_fp8_e4m3fn_scaled.safetensors, ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors, wan2.1-i2v-14b-480p-Q3_K_S.gguf, and wan_2.1_vae.safetensors.
Listed node packs include comfyui-gguf, comfyui-impact-pack, comfyui-kjnodes, comfyui-mxtoolkit, comfyui-videohelpersuite, rgthree-comfy, comfyui-custom-scripts, comfyui-frame-interpolation, comfyui_pulid_flux_ll, and comfyui-easy-use.

Configuración

The built-in SeedVR2 upscaler provides tiled upscaling and can be toggled on or off.
Six LoRA slots have individual on/off toggles and strength controls, and additional LoRA modules can be connected.
The auto version can download models automatically.

Precauciones

Before loading, verify that the listed model files and node packs are installed in your ComfyUI setup and that their names match.
Sugerencia · sin verificar
Before using or sharing it, check that the title, version, and source page are the ones you intend, and check usage rights because no license is listed.
Sugerencia · sin verificar

¿Es necesario editarlo?

Inicia sesión para solicitar una edición.

Fuentes

1 fuente

CivitaiPrincipalVersión 1566569

civitai.com/models/1363672

Verificado 3 nov