Trained for 2000 steps with: "#:0.41|~maniacal laughter:0.2|^maniacal laughter:0.05" using <a target="_blank" rel="ugc" href="https://github.com/ntc-ai/conceptmod">https://github.com/ntc-ai/conceptmod</a> animations with lora value from 0.0 to 1.8. All examples use the trigger phrase: "maniacal laughter" Words are pale shadows of forgotten names. As names have power, words have power. Words can light fires in the minds of <s>men</s> stable diffusion models. Tutorial: This tutorial is technical. For a much easier path, follow <a target="_blank" rel="ugc" href="https://civarchive.com/models/58873/conceptmod-tutorial-fire-train-any-lora-with-just-text-no-data-required">https://civarchive.com/models/58873/conceptmod-tutorial-fire-train-any-lora-with-just-text-no-data-required</a> and run on runpod. It's cheap. $5 to train a model and &lt;$1 to create animations. Local installation (technical) Requires 20 GB vram 0) Install a111 1) git clone <a target="_blank" rel="ugc" href="https://github.com/ntc-ai/conceptmod.git">https://github.com/ntc-ai/conceptmod.git</a> 2) cd conceptmod 3) edit train_sequential.sh and add your training phrase (see above) 4) install dependencies (see <a target="_blank" rel="ugc" href="https://github.com/ntc-ai/conceptmod#installation-guide">https://github.com/ntc-ai/conceptmod#installation-guide</a> ) and ImageReward <a target="_blank" rel="ugc" href="https://github.com/THUDM/ImageReward">https://github.com/THUDM/ImageReward</a> 5) train the model with <code>bash train_sequential.sh</code>(takes a while) 6) once you are successfully training you will save a new checkpoint into <code>models</code> , there will be samples during training if you have enabled them in the <code>samples</code> directory. 7) mv the models to a a111 models path: `mv -v models/*/*.ckpt ../stable-diffusion-webui2/models/Stable-diffusion/0new` 8) extract the lora with sd-scripts <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">https://github.com/kohya-ss/sd-scripts</a> (requires new conda env) here is the script I use to create loras of everything in a directory. replace dir and basemodel with yours. Run it in the sd-scripts project. <a target="_blank" rel="ugc" href="https://github.com/ntc-ai/conceptmod/blob/main/extract_lora.sh">https://github.com/ntc-ai/conceptmod/blob/main/extract_lora.sh</a> 9) Start a111 webui.py with '--api'. 10) Create the animations I used: &gt; python3 lora_anim.py -s -0.0 -e 1.8 -l "mania" -lp ", maniacal laughter" -np "nipples, weird image." -n 32 -sd 7 -m 2.0 If you create something with this, please tag it 'conceptmod' - React!: <a target="_blank" rel="ugc" href="https://civarchive.com/user/ntc/images?sort=Most+Reactions">https://civarchive.com/user/ntc/images?sort=Most+Reactions</a>

Files with SHA256: d7a230af6a815be4791c4365c3f1cf4242fb2c0fbab4d9bed4cea6f52cc5ce42