ControlNet is a neural framework designed to enhance control over generative models by incorporating conditional inputs like edge maps, depth data, or semantic segmentation. Proposed by Lvmin Zhang and Maneesh Agrawala, it integrates with diffusion models to enable precise control over image composition, object placement, and stylistic details via sketches, pose cues, or structural constraints. Widely used in digital art, design prototyping, film previsualization, and photo editing, it trains conditional encoders alongside base models to harmonize creative flexibility with structural guidance. The framework supports multi-modal inputs and real-time interaction, though challenges include stabilizing complex condition integration, optimizing computational overhead, and preventing overfitting.

The source model can be found here

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

• Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

• Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

The model performance benchmarks and example code provided by Model Farm are all implemented based on the APLUX AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md