Skip to content
WorkflowListedExternal
Open source

Wan2.1 image to video_LowVram_gguf_Simple — V1

Plenty of people still don't know how to run I2V with Wan2.1, so here's the bare-bones Image-to-Video workflow—it's the standard template, barely tweaked—to help anyone stuck on weak hardware or still hunting for a...

TaskImage to imageFamilyWanEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Source
Civitai
Updated
Oct 2, 2026

Source description

Plenty of people still don't know how to run I2V with Wan2.1, so here's the bare-bones Image-to-Video workflow—it's the standard template, barely tweaked—to help anyone stuck on weak hardware or still hunting for a basic starting point.

The reason why the sample video is stuck is that I only set the video frame rate to 4 frames in order to get a higher sample resolution and longer video length.

My poor potato computer! If you set the frame rate to at least 16 or 20 or 24, you can get a smooth video.

What you need

Hardware and download-size estimates are not available yet.

Requirements

Models

7
  • Vision model · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged · Wan 2.1 ComfyUI Repackaged

  • CLIPLoader

    Possible

    Text encoder · Unknown

  • Text encoder · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged · Wan 2.1 ComfyUI Repackaged

  • VAEDecode

    Possible

    VAE · Unknown

  • VAELoader

    Possible

    VAE · Unknown

  • VAE · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged · Wan 2.1 ComfyUI Repackaged

  • wan2.1-i2v-14b-480p-Q4_0.gguf

    Not resolved

    Checkpoint · Unknown

Node packs

10
  • CLIPTextEncode

    Possible

    Node pack · Unknown

  • CLIPVisionEncode

    Possible

    Node pack · Unknown

  • CLIPVisionLoader

    Possible

    Node pack · Unknown

  • KSampler

    Possible

    Node pack · Unknown

  • LoadImage

    Possible

    Node pack · Unknown

  • ModelSamplingSD3

    Found

    Node pack · Unknown

  • Power Lora Loader (rgthree)

    Not resolved

    Node pack · Unknown

  • UnetLoaderGGUF

    Possible

    Node pack · Unknown

  • VHS_VideoCombine

    Possible

    Node pack · Unknown

  • WanImageToVideo

    Not resolved

    Node pack · Unknown

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • Use this workflow to turn an image into a Wan2.1 video with the Wan Video 14B i2v 480p model; it is presented as a bare-bones starting point, including for people using weak hardware.

Flow

  • Its listed requirements connect it to the Comfy-Org/Wan_2.1_ComfyUI_repackaged model and to ComfyUI for ModelSamplingSD3.

Inputs and outputs

  • Start with an image; the description presents a video as the output. Listed nodes include LoadImage and VHS_VideoCombine.

Setup

  • Find it on Civitai under “Wan2.1 image to video_LowVram_gguf_Simple” by SamLiu.

Dependencies

  • Listed model files: clip_vision_h.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, and wan2.1-i2v-14b-480p-Q4_0.gguf.

  • Listed nodes include CLIPLoader, CLIPTextEncode, CLIPVisionEncode, CLIPVisionLoader, KSampler, LoadImage, and ModelSamplingSD3.

  • Also listed: Power Lora Loader (rgthree), UnetLoaderGGUF, VAEDecode, VAELoader, VHS_VideoCombine, and WanImageToVideo.

Configuration

  • The author says the sample uses frame rate 4 to get higher sample resolution and a longer video.

  • For smoother video, try a frame rate of 16, 20, or 24, as the author suggests.

    Suggestion · not verified

Cautions

  • The listed GGUF file has no provider specified, so confirm where to obtain it before setup.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimary
civitai.com/models/1801984

Verified Jul 19

Source excerpts

1 excerpt

Source context: 1705 downloads · Type Workflows · Base model Wan Video 14B i2v 480p