<h3 id="heading-5">STOP! THESE MODELS ARE NOT FOR PROMPTING/IMAGE GENERATION These models are extracted from the base ControlNet models in a slightly different way from <a target="_blank" rel="ugc" href="https://civarchive.com/models/9251/controlnet-pre-trained-models">the others.</a> They produce different results due to a different extraction method.</h3>These are the models required for the <a target="_blank" rel="ugc" href="https://github.com/Mikubill/sd-webui-controlnet">ControlNet extension</a>, converted to Safetensor and "pruned" to extract the ControlNet neural network. I have tested them, and they work.These models are embedded with the neural network data required to make ControlNet function, they will not produce good images unless they are used with ControlNet. These models were extracted using the <code>extract_controlnet_diff.py</code> script, and produce a slightly different result from the <a target="_blank" rel="ugc" href="https://civarchive.com/models/9251/controlnet-pre-trained-models">models extracted using the </a><code>extract_controlnet.py</code><a target="_blank" rel="ugc" href="https://civarchive.com/models/9251/controlnet-pre-trained-models"> script</a>. The original version of these models in .pth format can be found <a target="_blank" rel="ugc" href="https://huggingface.co/lllyasviel/ControlNet/tree/main/models">here</a>. BUT YOU DO NOT NEED THESE .pth FILES! The files I have uploaded here are direct replacements for these .pth files!<ul><li>control_sd15_canny</li><li>control_sd15_depth</li><li>control_sd15_hed</li><li>control_sd15_scribble</li><li>control_sd15_normal</li><li>control_sd15_openpose</li><li>control_sd15_seg</li><li>control_sd15_mlsd</li></ul>Download these models and place them in the <code>\stable-diffusion-webui\extensions\sd-webui-controlnet\models</code> directory. Note: these models were extracted from the original .pth using the <code>extract_controlnet_diff.py</code> script contained within the extension Github repo. <a target="_blank" rel="ugc" href="https://huggingface.co/kohya-ss/ControlNet-diff-modules/tree/main">Kohya-ss has them uploaded to HF here.</a>

ControlNet Pre-Trained Difference Models

controlnetPreTrained_mlsdDifferenceV10.safetensors

MLSD (Difference) V1.0

Seg (Difference) V1.0

OpenPose (Difference) V1.0

Scribble (Difference) V1.0

Normal (Difference) V1.0

HED (Difference) V1.0

Depth (Difference) V1.0

Canny (Difference) V1.0

<a target="_blank" rel="ugc" href="https://huggingface.co/kohya-ss/ControlNet-diff-modules/tree/main">Original ControlNet Difference Models HuggingFace Repository</a><h2>STOP! THESE MODELS ARE NOT FOR PROMPTING/IMAGE GENERATION AND ARE FOR USE WITH ANY STABLE DIFFUSION 1.5 BASED MODELS (which are most models unless stated to be SD 2.X) AS CONTROL NETWORKS. THE ONES SHARED AT <a target="_blank" rel="ugc" href="https://civarchive.com/models/9251/controlnet-pre-trained-models">https://civarchive.com/models/9251/controlnet-pre-trained-models</a> ARE ControlNets FOR THE BASE SD 1.5 MODEL ITSELF, NOT DIFFERENCE ONES.</h2>Control Nets allow you to guide the structure of an image based on existing ones and preprocessing them, or by using images that match the expected format for a given control net. More information regarding ControlNet and the different types can be found at <a target="_blank" rel="ugc" href="https://github.com/lllyasviel/ControlNet">https://github.com/lllyasviel/ControlNet</a>. All examples generated using preprocessors, with the AbyssOrangeMix2 - Hardcore model, with the prompt used being the same as the original input image (but with different seeds). All settings default except where mentioned on a specific control net type. Canvas width set to 512 x 768 to match the input image. You only need to download the models you want to use, you do not need to download all of them.These are the models required for the <a target="_blank" rel="ugc" href="https://github.com/Mikubill/sd-webui-controlnet">ControlNet extension</a>, converted to Safetensor and "pruned" to extract the ControlNet neural network. I have tested them with AOM2, and they work. Download these models and place them in the <code>\stable-diffusion-webui\extensions\sd-webui-controlnet\models</code> directory.Diagram was shared by Kohya and attempts to visually explain the difference between the original controlnet models, and the difference ones.<img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3d9838bb-79e9-4884-90fa-5c975e7ea300/width=525" />

Difference ControlNets

Adjusted Hough value threshold (MLSD) and Hough distance threshold (MLSD) to 0.01 for the preprocessor to get more lines.

Files with SHA256: 948fe030361fad35b974e4d112b0ac94df41d7ab61d7847ad7e7b9a98648cf25