Saltar al contenido
WorkflowPublicadoExterno
Descargar

Wan 2.2 S2V Speech to Video 5 Steps #ComfyUI Native Workflow + Step by Step #s2v #wan22 #lipsync#ai — v1.0

v 1.0

Fuentecivitai.com/models/1924833
TareaImagen a imagenFamiliaWanVersiónRelease 2178574 — S2V_WAN_2.2_14B_RareTutor_Final.jsonVRAM estimadaNot yet characterizedUnratedcalidad

Perfil de ejecución

Acceso
Flujo externo
Estado
Publicado
Versión
S2V_WAN_2.2_14B_RareTutor_Final.json
Fuente
Civitai
Actualizado
3 nov 2026

What you need

Model files
16.5 GiB known subtotal

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

Requisitos

Modelos

9

Paquetes de nodos

10

  • comfyui_essentials

    Encontrado

    Paquete de nodos · Registry

  • comfyui-kjnodes

    Encontrado

    Paquete de nodos · Registry

  • ComfyUI-MelBandRoFormer

    Encontrado

    Paquete de nodos · GitHub · kijai/ComfyUI-MelBandRoFormer

  • comfyui-multigpu

    Encontrado

    Paquete de nodos · Registry

  • GetNode

    No resuelto

    Paquete de nodos · Unknown

  • gguf

    Posible

    Paquete de nodos · Registry

  • image-saver

    Posible

    Paquete de nodos · Registry

  • SetNode

    No resuelto

    Paquete de nodos · Unknown

  • soundflow

    No resuelto

    Paquete de nodos · Registry

  • VHS_VideoCombine

    Posible

    Paquete de nodos · Unknown

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 five-step ComfyUI workflow is for turning speech into video with Wan 2.2; its graph includes LoadAudio and LoadImage inputs and a VHS_VideoCombine node for video assembly.

Entradas y salidas

  • The graph also includes PreviewAudio and PreviewImage nodes.

Configuración inicial

  • The listing describes it as a ComfyUI Native Workflow and advertises step-by-step guidance and a note to download all models.

Dependencias

  • Listed ComfyUI node components: comfyui_essentials, comfyui-kjnodes, ComfyUI-MelBandRoFormer, comfyui-multigpu, GetNode, gguf, image-saver, SetNode, soundflow, and VHS_VideoCombine.

  • Listed model files include MelBandRoformer_fp16.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, umt5-xxl-encoder-Q6_K.gguf, WAN_2_1_VAE_bf16.safetensors, and WAN_pig_wan_vae_fp32-f32.gguf.

  • Other listed model files: Wan2_2-S2V-14B_fp8_e4m3fn_scaled_KJ.safetensors, wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors, wan2.2-s2v-14b-q5_0.gguf, and wav2vec2_large_english_fp16.safetensors.

Configuración

  • The graph includes Sampler Selector and Scheduler Selector nodes, alongside PrimitiveFloat and PrimitiveInt nodes.

Precauciones

  • Before trying it, check that your ComfyUI setup has the listed node components and model files.

    Sugerencia

  • The listing gives no node-pack names for GetNode, SetNode, or VHS_VideoCombine, so check how your ComfyUI setup supplies them.

    Sugerencia

¿Es necesario editarlo?

Inicia sesión para solicitar una edición.

Fuentes

1 fuente
CivitaiPrincipalVersión 2178574
civitai.com/models/1924833

Verificado 3 nov

Workflow instructions

Author notes from S2V_WAN_2.2_14B_RareTutor_Final.json · selected release

[Click here to Download Models](https://www.youtube.com/watch?v=AL3Twi6IODU ) ``` ComfyUI/ ├───📂 models/ │ ├───📂 checkpoints/ │ │ ├─── wan2.2_s2v_14B_fp8_scaled.safetensors │ │ └─── umt5xxl_fp32-q4_0.gguf │ ├───📂 text_encoders/ │ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors │ │ └─── umt5xxl_fp32-q4_0.gguf │ ├───📂 audio_encoders/ # Create one if you can't find this folder │ │ └─── wav2vec2_large_english_fp16.safetensors │ └───📂 vae/ │ └── wan_2.1_vae.safetensors │ └───📂 diffusion_models/ │ └── MelBandRoformer_fp16.safetensors ```

Author notes from S2V_WAN_2.2_14B_RareTutor_Final.json · selected release

[Click here to Download Models](https://www.youtube.com/watch?v=AL3Twi6IODU ) ``` ComfyUI/ ├───📂 models/ │ ├───📂 checkpoints/ │ │ ├─── wan2.2_s2v_14B_fp8_scaled.safetensors │ │ └─── umt5xxl_fp32-q4_0.gguf │ ├───📂 text_encoders/ │ │ └─── umt5_xxl_fp8_e4m3fn_scaled.safetensors │ │ └─── umt5xxl_fp32-q4_0.gguf │ ├───📂 audio_encoders/ # Create one if you can't find this folder │ │ └─── wav2vec2_large_english_fp16.safetensors │ └───📂 vae/ │ └── wan_2.1_vae.safetensors │ └───📂 diffusion_models/ │ └── MelBandRoformer_fp16.safetensors ```

Download files

Artefactos del modelo

2 artefactos

wan22S2VSpeechToVideo5StepsComfyui_v10.zip

zip · 19,1 KB · SHA-256 6fff409b67c1…9a45 · Civitai

Download file

S2V_WAN_2.2_14B_RareTutor_Final.json

json · 261 KB · SHA-256 b6a549eb892a…b7c7

Download file

Extractos de fuentes

3 extractos
Note3 novcivitai.com/models/1924833

Source context: 1818 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note2 octcivitai.com/models/1924833

Source context: 1756 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B

Note19 julcivitai.com/models/1924833

Source context: 1600 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B