Saltar al contenido
WorkflowPublicadoExterno
Abrir fuente

SocksLatentPatcher GGUF Subgraph — v2.0

Fixed version and some addition

Fuentecivitai.com/models/2128200
TareaMúltipleCapacidadesImagen a vídeo · AmpliaciónFamiliaWanVersiónRelease 2414586 — SocksLatentPatcherGGUF.jsonVRAM estimadaNot yet characterizedBcalidad

Perfil de ejecución

Acceso
Flujo externo
Estado
Publicado
Versión
SocksLatentPatcherGGUF.json
Fuente
Civitai
Actualizado
18 oct 2026

What you need

Model files
6.9 GiB known subtotal

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

Requisitos

Modelos

8

Paquetes de nodos

10

  • comfyui_essentials

    Encontrado

    Paquete de nodos · Registry

  • comfyui_memory_cleanup

    Encontrado

    Paquete de nodos · Registry

  • comfyui-easy-use

    Encontrado

    Paquete de nodos · Registry

  • comfyui-frame-interpolation

    Encontrado

    Paquete de nodos · Registry

  • ComfyUI-GGUF

    Posible

    Paquete de nodos · Registry

  • comfyui-kjnodes

    Encontrado

    Paquete de nodos · Registry

  • ComfyUI-Rife-Tensorrt

    Encontrado

    Paquete de nodos · Registry

  • ComfyUI-Upscaler-Tensorrt

    Encontrado

    Paquete de nodos · Registry

  • comfyui-videohelpersuite

    Encontrado

    Paquete de nodos · Registry

  • 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

  • This workflow is for experimental image-to-video generation with Wan Video 2.2 I2V-A14B; it uses `wan2.2_i2v_high_noise_14B_Q4_K_S.gguf` and `wan2.2_i2v_low_noise_14B_Q4_K_S.gguf`, patches latent tensors instead of decoding through the VAE, and can produce video with interpolated

Flujo

  • The subgraph combines PainterI2V, SocksLatentPatcher, Rife Tensorrt, and Upscaler Tensorrt.

  • It bypasses VAE decode and directly patches the latent tensor; the workflow description presents this as a way to handle detail loss and saturation or desaturation during infinite-length video generation.

Entradas y salidas

  • The main model inputs are `wan2.2_i2v_high_noise_14B_Q4_K_S.gguf` and `wan2.2_i2v_low_noise_14B_Q4_K_S.gguf`.

  • The video output path includes interpolation and upscaling options.

Configuración inicial

  • Links for model, CLIP, and VAE files are included in the workflow.

  • This is version v2.0, published by Donzo15.

Dependencias

  • Listed model files include `wan2.2_i2v_high_noise_14B_Q4_K_S.gguf`, `wan2.2_i2v_low_noise_14B_Q4_K_S.gguf`, `lightx2v_I2V_14B_480p_cfg_step_distill_rank256_bf16.safetensors`, and `Wan_2_2_I2V_A14B_HIGH_lightx2v_4step_lora_v1030_rank_64_bf16.safetensors`.

  • Other listed model files are `nsfw_wan_umt5-xxl_fp8_scaled.safetensors`, `wan_2.1_vae.safetensors`, `rife49.pth`, and `film_net_fp32.pt`.

  • Listed node packs include `comfyui_memory_cleanup`, `comfyui-videohelpersuite`, `rgthree-comfy`, `ComfyUI-GGUF`, `ComfyUI-Rife-Tensorrt`, `ComfyUI-Upscaler-Tensorrt`, `comfyui-frame-interpolation`, `comfyui_essentials`, `comfyui-kjnodes`, and `comfyui-easy-use`.

Configuración

  • For interpolation, choose between `rife vf1` and `rife tensorrt`.

Precauciones

  • The I2V path is marked experimental.

  • Before running, verify the exact `ComfyUI-GGUF` package and confirm that these files are available: `lightx2v_I2V_14B_480p_cfg_step_distill_rank256_bf16.safetensors`, `Wan_2_2_I2V_A14B_HIGH_lightx2v_4step_lora_v1030_rank_64_bf16.safetensors`, `nsfw_wan_umt5-xxl_fp8_scaled.safet v

    Sugerencia · sin verificar

¿Es necesario editarlo?

Inicia sesión para solicitar una edición.

Fuentes

1 fuente
CivitaiPrincipalVersión 2414586
civitai.com/models/2128200

Verificado 18 oct

Extractos de fuentes

3 extractos
Note18 octcivitai.com/models/2128200

Source context: 244 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note7 agocivitai.com/models/2128200

Source context: 195 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note19 julcivitai.com/models/2128200

Source context: 186 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B