Skip to content
WorkflowListedExternal
Open source

CogvideoX Image to Video ComfyUI workflow — v1.0

Initial release

Sourcecivitai.com/models/1117606
TaskMultiCapabilitiesImage to image · UpscalingFamilyCogVideoXVersionRelease 1255983 — cogvideox-imagetovideo-tomgoodnoise.jsonEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
cogvideox-imagetovideo-tomgoodnoise.json
Source
Civitai
Updated
Oct 18, 2026

What you need

Model files
0.1 GiB known subtotal

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

Requirements

Models

6

  • 4x-UltraSharp.pth

    Found

    Upscaler · 63.9 MB · PTH · Unknown

  • alibaba-pai/CogVideoX-Fun-V1.1-5b-InP

    Not resolved

    Checkpoint · Hugging Face · alibaba-pai/CogVideoX-Fun-V1.1-5b-InP

  • microsoft/Florence-2-large

    File unverified

    Vision model · Hugging Face · microsoft/Florence-2-large

  • pytorch_lora_weights.safetensors

    Possible

    LoRA · Unknown

  • rife47.pth

    File unverified

    Checkpoint · Unknown

  • t5xxl_fp8_e4m3fn.safetensors

    Not resolved

    Text encoder · Unknown

AI-generated commentary

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

Purpose

  • Use this ComfyUI workflow to turn a starter image and motion text into a CogVideoX video.

Flow

  • The workflow includes a CogVideoX motion LoRA intended to guide camera movement.

Inputs and outputs

  • A simple method for upscaling the generated video is also included.

Setup

  • The ZIP includes the workflow JSON, a starter image, and a creation PNG that also contains the workflow.

  • Expand the collapsed Note nodes to find model links and instructions on where to place the models.

    Suggestion

Dependencies

  • The workflow’s model list names 4x-UltraSharp.pth, alibaba-pai/CogVideoX-Fun-V1.1-5b-InP, microsoft/Florence-2-large, pytorch_lora_weights.safetensors, rife47.pth, and t5xxl_fp8_e4m3fn.safetensors.

Configuration

  • Add movement details to the prompt; the creator says CogVideoX relies on motion information in text.

    Suggestion

  • The creator describes Fun 1.1 as fixed to a 16:10 format and 720×480, while Fun 1.5 goes up to double size.

Cautions

  • The creator reports that the included motion LoRA works with Fun 1.1 but not Fun 1.5.

  • The creator could not run CogVideoX on an 8 GB card; they expect 12 GB may work but have not tested it, and currently render on a 16 GB card.

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 1255983
civitai.com/models/1117606

Verified Oct 18

Source excerpts

2 excerpts
NoteOct 18civitai.com/models/1117606

Source context: 1992 downloads · Type Workflows · Base model CogVideoX

NoteJul 20civitai.com/models/1117606

Source context: 1839 downloads · Type Workflows · Base model CogVideoX