Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > VideoX-Fun

ComfyUI Extension: VideoX-Fun

Repo Name

VideoX-Fun

Author
aigc-apps (Account age: 1192 days)
Nodes
View all nodes(1)
Latest Updated
2026-11-14
Github Stars
2.34K

How to Install VideoX-Fun

Install this extension via the ComfyUI Manager by searching for VideoX-Fun
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter VideoX-Fun in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

VideoX-Fun Description

VideoX-Fun is a ComfyUI toolkit for AI image and video creation. It turns text into clips, animates images, transforms videos, and guides motion with pose or depth inputs; it also supports image editing.

VideoX-Fun Introduction

VideoX-Fun is a toolkit for creating AI images and videos. You can generate a clip from a written description, animate a still image, transform a reference video, or use visual guides to influence motion and composition. It also supports image generation and editing through compatible image models.

The project brings many model families into a common workflow. You can use existing models to make artwork, or train a base model or a LoRA to adapt a model to a particular visual style. A LoRA is a smaller add-on used with a compatible base model; it does not replace the base model.

VideoX-Fun offers several ways to work:

  • Web interface: An interactive option for supported video-model families.
  • ComfyUI: A node-based option for artists who already build ComfyUI workflows.
  • Python scripts: An option for batch work and settings not exposed in the web interface.

You can explore the hosted CogVideoX-Fun demo and Wan-Fun demo before choosing a local workflow.

How VideoX-Fun Works

Think of a model as an artist that has learned visual patterns, and your inputs as its brief. VideoX-Fun passes those inputs to the model you select and saves the resulting image or video.

Different tasks provide different kinds of guidance:

  1. Text to video: You describe a scene and the model creates a moving clip. For example, you might request a person walking along a rainy street.
  2. Image to video: You provide a still image as a starting point and describe what should move. Some supported models also accept an ending image, giving the clip a destination as well as a starting point.
  3. Video to video: You provide a reference clip whose content or motion guides a new result.
  4. Controlled video generation: You provide a processed guide, such as an edge map, depth map, or body-pose sequence. This is like giving the model a rough storyboard for structure or movement.
  5. Text to image and image editing: Compatible image models create an image from a description or edit an existing one.

The prompt describes what you want; a negative prompt describes elements you would rather avoid. A seed controls the random starting point: keeping it the same can help you compare changes to other settings. Guidance scale adjusts how strongly generation follows the prompt. Video duration, frame rate (FPS), and resolution are available according to the chosen model and workflow. More frames or a larger image generally make a generation task more demanding, so begin with a modest test before committing to a larger output.

VideoX-Fun Features

Choose the workflow that fits your project

The web interface supports text-to-video, image-to-video, video-to-video, and ordinary control-guided video generation for the CogVideoX-Fun, Wan2.1, Wan2.1-Fun, Wan2.2, and Wan2.2-Fun families. You can select a model, enter prompts and other common settings, and generate a result. Other models, including the image models described in the source README, use Python prediction scripts rather than this web interface.

If you prefer arranging steps visually, see the ComfyUI guide. This example image-to-video workflow (https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/asset/v1/cogvideoxfunv1_workflow_i2v.jpg) shows what a node graph can look like.

Python scripts provide the broadest control. Their names indicate the task: predict_t2v.py for text-to-video, predict_i2v.py for image-to-video, predict_v2v.py for video-to-video, and, where available, predict_t2i.py for text-to-image. Check the scripts in examples/{model_name}/ to see which tasks a particular model actually supports.

Guide the result with images and video

For image-to-video work, validation_image_start supplies the opening image and validation_image_end can supply the ending image. This is useful when you need a clip to begin and finish on particular compositions.

For video-to-video work, validation_video supplies a reference clip. For controlled generation, control_video supplies a prepared guide such as Canny edges, Pose, or Depth. You can inspect the source README’s reference video (https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/asset/v1/play_guitar.mp4) and pose-control example (https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/asset/v1.1/pose.mp4) to understand the difference between a clip and a processed motion guide.

Balance GPU memory and speed

Large models can require substantial graphics-card memory. VideoX-Fun provides several memory modes so you can trade speed for a better chance of fitting a model on your GPU:

ModeWhat it means for you
model_full_loadKeeps the model on the GPU. Fastest option, but uses the most GPU memory.
model_cpu_offloadMoves the model to the CPU after use, reducing GPU-memory needs. The source README recommends this when you have enough memory to use it.
model_cpu_offload_and_qfloat8Combines CPU offloading with lower-precision transformer weights to save more memory; lower precision can reduce model performance.
sequential_cpu_offloadMoves individual layers to the CPU after use. Saves substantial GPU memory but is slower.
model_group_offloadMoves groups of weights between CPU and GPU, aiming to balance memory use and speed. Available in prediction scripts.
model_full_load_and_qfloat8Keeps the model on the GPU while reducing transformer precision. Available in prediction scripts.

The web interface exposes only model_full_load, model_cpu_offload, model_cpu_offload_and_qfloat8, and sequential_cpu_offload. The other two modes require a Python prediction script. The source README also notes that compile-based acceleration is incompatible with sequential_cpu_offload and fsdp_dit.

Adapt a model to your style

VideoX-Fun supports training both base models and LoRAs. Training data pairs images or videos with text descriptions. For an artist, a LoRA can be a way to explore a consistent visual treatment while continuing to use a compatible base model. Training is a more advanced workflow than generating with an existing model; consult the model-specific guides before preparing a dataset.

VideoX-Fun Models

Choose by task first, then by model family. A name containing T2V indicates text-to-video, I2V image-to-video, and TI2V support for both. InP models in the supplied catalog cover text/image-guided generation, including start-and-end-image use where noted. Control models accept additional structural guidance. A larger number such as 14B identifies a larger model, not a promised quality or speed improvement on your hardware.

The following are the model weights fully identifiable in the supplied context. Links lead to their Hugging Face pages.

FamilyModelsWhen to consider them
Wan2.2-FunA14B-InP, 5B-InPText- or image-guided video, including start-and-end images. The listed A14B model is described as 81 frames at 16 FPS; the 5B model as 121 frames at 24 FPS.
Wan2.2-Fun ControlA14B-Control, 5B-ControlVideo guided by Canny edges, depth, pose, MLSD lines, or trajectories.
Wan2.2-Fun camera controlA14B-Control-Camera, 5B-Control-CameraProjects where you want to guide camera movement as well as the generated scene.
Wan2.2-VACE-FunA14BControl-guided video or subject-reference generation.
Wan2.2 official modelsTI2V-5B, T2V-A14B, I2V-A14B, S2V-14B, Animate-14BRespectively: combined text/image-to-video, text-to-video, image-to-video, speech-driven digital humans, and character replacement or motion transfer.
Wan2.1-Fun V1.1 InP1.3B-InP, 14B-InPText- and image-guided video with start-and-end-image support. The supplied catalog describes this series as supporting multiple resolutions and 81 frames at 16 FPS.
Wan2.1-Fun V1.1 Control1.3B-Control, 14B-ControlControl-guided video, including a reference image combined with control guidance.
Wan2.1-Fun V1.1 camera control1.3B-Control-Camera, 14B-Control-CameraCamera-motion guidance in the V1.1 series.
Wan2.1-Fun V1.01.3B-InP, 14B-InP, 1.3B-Control, 14B-ControlEarlier InP and control options; the supplied catalog says V1.0 does not include the V1.1 camera-control capability.
Wan2.1 official modelsT2V-1.3B, T2V-14B, I2V-14B-480P, I2V-14B-720PTask-specific original Wan2.1 weights. Choose a T2V model for a prompt alone or an I2V model to animate an image.

The catalog also lists Wan2.2-Fun Reward LoRAs and Wan2.1-Fun Reward LoRAs. These are add-ons for compatible weights, not standalone generation models. VideoX-Fun additionally names CogVideoX-Fun, HunyuanVideo, MiniMax-H3, LTX-2, LongCat-Video, FantasyTalking, LingBot, Qwen-Image, Z-Image, Flux/Flux2, and ERNIE-Image as supported families, but the provided context does not include a complete, usable weight list for them.

What's New with VideoX-Fun

The supplied context does not provide a dated release history. It does identify these model-series differences:

  • Wan2.1-Fun V1.1 compared with V1.0: V1.1 includes camera-control models. That matters when a shot needs a guided camera move rather than only subject or scene control.
  • Wan2.2-Fun options: The catalog includes InP, control, and camera-control weights in both A14B and 5B variants, giving you separate choices for open-ended generation and more directed work.
  • Wan2.2-VACE-Fun: Adds a listed route for control-guided or subject-reference video generation.

These are descriptions of available model families, not a claim about when each change was released.

Troubleshooting VideoX-Fun

The model does not appear or cannot be loaded

  1. Confirm that you obtained the weight for the exact model name you selected.
  2. For the project's scripts or web interface, check that its folder is under models/Diffusion_Transformer/ and that the folder name matches the weight name.
  3. For ComfyUI, check ComfyUI/models/Fun_Models/ instead.
  4. If you are loading a trained model or LoRA in the web interface, check models/Personalized_Model/.
  5. Consult the model's page to confirm you have the files required by that weight.

The task I want is missing from the web interface

  1. Check whether your model family is one of the web-interface families listed above.
  2. Look in examples/{model_name}/ for a script matching the task, such as predict_t2i.py or predict_i2v.py.
  3. If no matching script exists, do not assume that the model supports that task. Choose a listed model designed for it.

Generation runs out of GPU memory

  1. Try a smaller model or a less demanding output setting.
  2. In the web interface, switch from full loading to model_cpu_offload.
  3. If memory is still insufficient, consider model_cpu_offload_and_qfloat8 or sequential_cpu_offload, accepting a potential quality or speed trade-off.
  4. If you use a Python prediction script, review its additional GPU_memory_mode choices.

The result does not follow my intended motion or composition

  1. Check that you chose the right task: a starting image, reference video, and processed control video serve different purposes.
  2. For image-to-video, verify that the opening image is assigned to validation_image_start; use validation_image_end when your selected workflow supports an ending image.
  3. For controlled generation, make sure control_video contains the intended processed guide, such as pose or depth, rather than assuming an ordinary clip will act as one.
  4. Revise the prompt to describe the action clearly, then compare results while keeping the seed fixed.

Frequently asked questions

Do I need to train a model before making art?
No. VideoX-Fun supports generating with already-trained models. Training is an optional path for adapting a model.

Can I use the same interface for every image and video model?
No. The source README lists web interfaces for specific video families; other models, including image models, use prediction scripts. ComfyUI is another option where a compatible workflow is available.

What is the difference between a base model and a LoRA?
A base model performs the main generation. A LoRA is a smaller adaptation used alongside a compatible base model, often for a particular style or behavior.

Will a memory-saving mode make generation faster?
Not necessarily. Moving model parts between CPU and GPU can reduce GPU-memory use but slow generation. Lower-precision modes can also affect model performance.

Learn More about VideoX-Fun

VideoX-Fun Related Nodes

RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

VideoX-Fun detailed guide | ComfyUI