# aigc-apps/videox-fun architecture

> Architecture diagram of the GitHub repository aigc-apps/videox-fun, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/aigc-apps/videox-fun
- Repository: https://github.com/aigc-apps/videox-fun

## Overview

VideoX-Fun is a multi-model image/video generation and model-training toolkit, exposed through interactive UIs, Python/API interfaces, and ComfyUI nodes. The generation workflow accepts text and optional image, video, audio, or control inputs; model-specific pipelines run diffusion models and return generated media. Training and dataset preparation, reward/caption utilities, and ComfyUI control annotators are distinct supporting capabilities. The README documents capabilities broadly; source excerpts are partial, so some cross-layer links are intentionally omitted or marked unverified.

Main entry points: [`videox_fun/pipeline`](https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/pipeline) (Generation Pipelines), [`comfyui/wan2_1/nodes.py`](https://github.com/aigc-apps/videox-fun/blob/main/comfyui/wan2_1/nodes.py) (Model Nodes), [`videox_fun/ui/controller.py`](https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/ui/controller.py) (UI Controller), [`videox_fun/ui`](https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/ui) (Web UIs)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_entry["User Interfaces"]
  node_ui["Web UIs"]
  node_api["Inference API"]
  node_comfy["ComfyUI Nodes<br/>[comfyui_nodes.py]"]
  node_comfy_models["Model Nodes<br/>[nodes.py]"]
  node_controller["UI Controller<br/>[controller.py]"]
end

subgraph group_generation["Generation Runtime"]
  node_pipelines["Generation Pipelines"]
  node_models["Diffusion Models"]
  node_samplers["Flow Samplers<br/>[fm_solvers.py]"]
  node_optimization["Memory And LoRA<br/>[lora_utils.py]"]
  node_media["Media Utilities<br/>[utils.py]"]
end

subgraph group_learning["Training Data"]
  node_datasets["Training Datasets<br/>[dataset_video.py]"]
  node_batching["Bucket Sampling<br/>[bucket_sampler.py]"]
  node_training["Training Scripts"]
end

subgraph group_support["Controls And Evaluation"]
  node_caption["Caption Processing"]
  node_annotators["Control Annotators<br/>[nodes.py]"]
  node_rewards["Reward Evaluation<br/>[reward_fn.py]"]
  node_comfy_helpers["ComfyUI Helpers<br/>[comfyui_utils.py]"]
end

node_creator(("Creator"))
node_generated["Generated Media"]
node_weights[("Model Weights")]

node_creator -->|"selects generation"| node_ui
node_creator -->|"requests inference"| node_api
node_creator -->|"builds workflow"| node_comfy
node_ui -.->|"delegates requests"| node_controller
node_api -.->|"runs inference"| node_pipelines
node_comfy -->|"registers nodes"| node_comfy_models
node_comfy_models -->|"runs generation"| node_pipelines
node_comfy_models -->|"resolves models"| node_comfy_helpers
node_pipelines -->|"invokes models"| node_models
node_pipelines -->|"uses solvers"| node_samplers
node_pipelines -.->|"applies adapters"| node_optimization
node_controller -.->|"selects pipeline"| node_pipelines
node_controller -->|"loads weights"| node_weights
node_pipelines -.->|"writes media"| node_media
node_media -.->|"encodes output"| node_generated
node_creator -->|"trains models"| node_training
node_training -.->|"consumes datasets"| node_datasets
node_datasets -->|"uses bucketing"| node_batching
node_creator -->|"prepares captions"| node_caption
node_creator -->|"creates controls"| node_annotators
node_pipelines -.->|"scores outputs"| node_rewards

click node_ui "https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/ui"
click node_api "https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/api"
click node_comfy "https://github.com/aigc-apps/videox-fun/blob/main/comfyui/comfyui_nodes.py"
click node_comfy_models "https://github.com/aigc-apps/videox-fun/blob/main/comfyui/wan2_1/nodes.py"
click node_controller "https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/ui/controller.py"
click node_pipelines "https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/pipeline"
click node_models "https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/models"
click node_samplers "https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/utils/fm_solvers.py"
click node_optimization "https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/utils/lora_utils.py"
click node_media "https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/utils/utils.py"
click node_datasets "https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/data/dataset_video.py"
click node_batching "https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/data/bucket_sampler.py"
click node_training "https://github.com/aigc-apps/videox-fun/tree/main/scripts"
click node_caption "https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/video_caption"
click node_annotators "https://github.com/aigc-apps/videox-fun/blob/main/comfyui/annotator/nodes.py"
click node_rewards "https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/reward/reward_fn.py"
click node_comfy_helpers "https://github.com/aigc-apps/videox-fun/blob/main/comfyui/comfyui_utils.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_ui,node_api,node_comfy,node_comfy_models,node_controller toneBlue
class node_pipelines,node_models,node_samplers,node_optimization,node_media,node_weights toneAmber
class node_datasets,node_batching,node_training toneMint
class node_caption,node_annotators,node_rewards,node_comfy_helpers toneRose
class node_creator,node_generated toneIndigo
```

## Components

### User Interfaces

- [Web UIs](https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/ui): `videox_fun/ui`
- [Inference API](https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/api): `videox_fun/api`
- [ComfyUI Nodes](https://github.com/aigc-apps/videox-fun/blob/main/comfyui/comfyui_nodes.py): `comfyui/comfyui_nodes.py`
- [Model Nodes](https://github.com/aigc-apps/videox-fun/blob/main/comfyui/wan2_1/nodes.py): `comfyui/wan2_1/nodes.py`
- [UI Controller](https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/ui/controller.py): `videox_fun/ui/controller.py`

### Generation Runtime

- [Generation Pipelines](https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/pipeline): `videox_fun/pipeline`
- [Diffusion Models](https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/models): `videox_fun/models`
- [Flow Samplers](https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/utils/fm_solvers.py): `videox_fun/utils/fm_solvers.py`
- [Memory And LoRA](https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/utils/lora_utils.py): `videox_fun/utils/lora_utils.py`
- [Media Utilities](https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/utils/utils.py): `videox_fun/utils/utils.py`

### Training Data

- [Training Datasets](https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/data/dataset_video.py): `videox_fun/data/dataset_video.py`
- [Bucket Sampling](https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/data/bucket_sampler.py): `videox_fun/data/bucket_sampler.py`
- [Training Scripts](https://github.com/aigc-apps/videox-fun/tree/main/scripts): `scripts`

### Controls And Evaluation

- [Caption Processing](https://github.com/aigc-apps/videox-fun/tree/main/videox_fun/video_caption): `videox_fun/video_caption`
- [Control Annotators](https://github.com/aigc-apps/videox-fun/blob/main/comfyui/annotator/nodes.py): `comfyui/annotator/nodes.py`
- [Reward Evaluation](https://github.com/aigc-apps/videox-fun/blob/main/videox_fun/reward/reward_fn.py): `videox_fun/reward/reward_fn.py`
- [ComfyUI Helpers](https://github.com/aigc-apps/videox-fun/blob/main/comfyui/comfyui_utils.py): `comfyui/comfyui_utils.py`

### Other components

- **Creator**
- **Generated Media**
- **Model Weights**

## Connections

- Creator → Web UIs: selects generation (evidence: `README.md`)
- Creator → Inference API: requests inference (evidence: `README.md`)
- Creator → ComfyUI Nodes: builds workflow (evidence: `README.md`)
- Web UIs → UI Controller: delegates requests
- Inference API → Generation Pipelines: runs inference
- ComfyUI Nodes → Model Nodes: registers nodes (evidence: `comfyui/comfyui_nodes.py`)
- Model Nodes → Generation Pipelines: runs generation (evidence: `comfyui/wan2_1/nodes.py`)
- Model Nodes → ComfyUI Helpers: resolves models (evidence: `comfyui/wan2_1/nodes.py`)
- Generation Pipelines → Diffusion Models: invokes models (evidence: `videox_fun/pipeline/pipeline_minimax_h3.py`)
- Generation Pipelines → Flow Samplers: uses solvers (evidence: `videox_fun/pipeline/pipeline_wan_flex_forcing.py`)
- Generation Pipelines → Memory And LoRA: applies adapters
- UI Controller → Generation Pipelines: selects pipeline
- UI Controller → Model Weights: loads weights (evidence: `videox_fun/ui/controller.py`)
- Generation Pipelines → Media Utilities: writes media
- Media Utilities → Generated Media: encodes output
- Creator → Training Scripts: trains models (evidence: `README.md`)
- Training Scripts → Training Datasets: consumes datasets
- Training Datasets → Bucket Sampling: uses bucketing (evidence: `videox_fun/data/__init__.py`)
- Creator → Caption Processing: prepares captions (evidence: `README.md`)
- Creator → Control Annotators: creates controls (evidence: `README.md`)
- Generation Pipelines → Reward Evaluation: scores outputs
