Wan 2.1 Image to Video
An image to video ComfyUI workflow with the video model Wan Vace
Perfil de ejecución
- Acceso
- Flujo externo
- Estado
- Publicado
- Fuente
- Civitai
- Actualizado
- 24 oct 2026
Descripción de la fuente
Description
An image to video ComfyUI workflow with the video model Wan Vace
Howto
Drag an initial image into the image node, adjust the prompt, and press queue. The rest should fit.
Description
An image to video ComfyUI workflow with the video model Wan Vace and a special lora called Causvid. Which reduces the creation time dramatically. It is based at the default template that you can find in ComfyUI. But with some modifications.
Note that upscaling better happens in an extra step. You can find example upscaling workflows in my article about video upscaling in comfyui: https://www.tomgoodnoise.de/index.php/video-upscaling-in-comfyui/
There are some collapsed Note nodes besides the important nodes. Click at them to expand them. Some contains valuable informations.
Time
The example video in 480p , the 14b model and the causvid lora off took 67 minutes.
The example video in 480p , the 14b model and the causvid lora on took 10 minutes.
The example video in 480p , the 1.3b model and the causvid lora off took 3 minutes.
Requirements
This workflow was generated with 16 gb vram. Minimum requirement is 12 gb vram. And you should not have fewer than 32 gb system ram. I was not able to create the 720p version of the video with just 16 gb vram and my 32 gb ram.
What you need
- Model files
- 4.1 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Requisitos
Modelos
6- Archivo sin verificar
Text encoder · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged · Wan 2.1 ComfyUI Repackaged
- Archivo sin verificar
VAE · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged · Wan 2.1 ComfyUI Repackaged
wan2.1_vace_1.3B_fp16.safetensors
EncontradoCheckpoint · 4.01 GB · SAFETENSORS · Unknown
wan2.1_vace_14B_fp16.safetensors
Archivo sin verificarCheckpoint · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged · Wan 2.1 ComfyUI Repackaged
LoRA · Hugging Face · Kijai/WanVideo_comfy
LoRA · 87.0 MB · SAFETENSORS · Unknown
Paquetes de nodos
3- Encontrado
Paquete de nodos · Registry
- Encontrado
Paquete de nodos · Registry
- 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 Wan 2.1 Image to Video in ComfyUI to turn an initial image and prompt into a 480p video with Wan Vace.
Flujo
Drag an initial image into the image node, adjust the prompt, and press queue to start video generation.
Entradas y salidas
Provide an initial image and prompt; the workflow produces a video.
If you want to upscale the video, plan upscaling as a separate extra step.
Sugerencia · sin verificar
Configuración inicial
The stated minimum is 12 GB of VRAM and 32 GB of system RAM; the workflow was generated with 16 GB of VRAM.
Dependencias
Model files listed for the workflow include umt5_xxl_fp16.safetensors, wan_2.1_vae.safetensors, wan2.1_vace_1.3B_fp16.safetensors, and wan2.1_vace_14B_fp16.safetensors.
LoRA files listed for the workflow are Wan21_CausVid_14B_T2V_lora_rank32.safetensors and Wan21_CausVid_bidirect2_T2V_1_3B_lora_rank32.safetensors.
Node packs listed for the workflow are comfyui-frame-interpolation, comfyui-kjnodes, and comfyui-videohelpersuite.
Configuración
The workflow includes 14B and 1.3B model variants and a CausVid LoRA that can be on or off.
The description reports 480p example times of 67 minutes with the 14B model and CausVid off, 10 minutes with 14B and CausVid on, and 3 minutes with 1.3B and CausVid off.
Expand the collapsed Note nodes to read their additional information.
Sugerencia · sin verificar
Precauciones
Before running, verify that ComfyUI has the listed model files, LoRA files, and node packs available.
Sugerencia · sin verificar
For 720p, verify your hardware first: the provided details say the 720p version could not be created with 16 GB of VRAM and 32 GB of system RAM.
Sugerencia · sin verificar
¿Es necesario editarlo?
Inicia sesión para solicitar una edición.
Fuentes
1 fuente
Fuentes
1 fuenteExtractos de fuentes
1 extracto
Extractos de fuentes
1 extractoSource context: 2034 downloads · Type Workflows · Base model Wan Video 14B i2v 480p
