Control image generation by edge maps generated with <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/GeroldMeisinger/edpf">Edge Drawing Parameter Free</a> (edpf). This is similar to ControlNet Canny but uses <a target="_blank" rel="ugc" href="https://github.com/CihanTopal/ED_Lib">a modern algorithm</a> for edge-detection which requires no parameter tuning (Canny was invented in 1986, Edge Drawing in 2012). You can use the <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/GeroldMeisinger/edpf">gradio demo </a>or <a target="_blank" rel="ugc" href="https://gitlab.com/-/snippets/3601881">edpf.py script</a> to generate edge maps until a pre-processor is implemented in your favorite Stable Diffusion UI.Feedback is welcome! I'm still improving this model and you can help me by generating simple usecases and discuss the results.<h1 id="heading-807">The case for a new edge model</h1>Do you find all these settings for canny confusing and time-consuming?<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f9bab56c-741b-4c99-9bf1-fc3129c48520/width=525/f9bab56c-741b-4c99-9bf1-fc3129c48520.jpeg" />Do your default edge maps have noise, artefacts and missing edges?All your images come out a mess like they were drawn by a human?Well look no further!With Edge Drawing Parameter Free you can create a masterpiece with a single mouse click!<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a1033126-7283-493e-9625-0475a4604757/width=525/a1033126-7283-493e-9625-0475a4604757.jpeg" />No tuning! No mistakes! No frustration!By combining recent advances in deep learning, cloud computing and block chain technology(?) we created the EDPF control net model just for you.And the best part: it's free! Parameter Free!<a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/175285">Download now!</a><hr />If you want to train your own control net see my article <a target="_blank" rel="ugc" href="https://civarchive.com/articles/20789">Play in Control - ControlNet training setup guide</a>!

ControlNet MySee - Edge Drawing Parameter Free - easy and hassle-free Canny alternative

Trained on clean image dataset, with non-square images and slightly better captions and batch size=32. Overall much better quality and improved no-prompt inference.see <a target="_blank" rel="ugc" href="https://huggingface.co/GeroldMeisinger/control-edgedrawing">https://huggingface.co/GeroldMeisinger/control-edgedrawing</a> -&gt; Experiment 6.1 for more information on training

Files with SHA256: 5a26d8771ec9084d7949db8bc044f384f7c0cd9bdf2d97b91e4039469ca76a21