We’re on a journey to advance and democratize artificial intelligence through open source and open science.

This ControlNet model uses depth maps (monochrome representations of distance in 3D space) to inject spatial geometry into Stable Diffusion image generation. It's most effective when you want to …

While the code is focused, press Alt+F1 for a menu of operations. Contribute to julian9jin/ControlNet-modules-safetensors development by creating an account on GitHub.

Dec 28, 2025 · Depth Map Generation: Generate depth information of images through the Depth preprocessor to create a more three-dimensional visual effect. Last updated on August 10, 2025. …

All ran on SD v1.5, with VAE=ft-MSE-840000-ema.

It helps AI correctly interpret spatial relationships, ensuring that generated images conform to the spatial structure specified by the depth map, thereby enabling precise control over three-dimensional spatial …

Safetensors/FP16 versions: This model comes in two versions, Safetensors and FP16, which are designed to work efficiently with different systems. Compatibility: It’s best used with ComfyUI, but it …

Apr 1, 2023 · The controller image is what you will actually use to constrain/control the result. What you're using for this image really depends on what model you are using.

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info. We’re on a journey to advance and democratize artificial …

Sep 8, 2025 · ControlNet allows users to control the generation process of stable diffusion images with spatial contexts. One of the most common examples is using a “pose” - a stick figure drawing to …