My first attempt at creating a lora containing both a style and characters feedback is appreciated, I used 200 total images from the show, 75 of them being random characters, scenery, etc and 25 for each character, overall I think it turned out alright but I will train it again because some of the characters aren't consistent and sometimes the style isn't as visible. trained here on civitai using <a target="_blank" rel="ugc" href="https://civarchive.com/models/257749?modelVersionId=290640">Pony Diffusion V6 XL</a> as a training model at 1024Style info:<ul><li>trigger word: kan_style</li><li>weight: 1 is perfect</li></ul>Characters info:<ul><li>Trigger word - looks tag<ol><li>Kim: kimaps - long hair, orange hair, green eyes</li><li>Monique: moniiqkue, black eyes, black hair, dark-skinned female, dark skin</li><li>Bonnie: bomnkinie, short hair, brown hair, green eyes</li><li>Ann: ankkiin, brown hair, short hair, blue eyes, doctor, lab coat</li><li>Shego: shmeikgo, black hair, long hair, green eyes, gloves, bodysuit, lipstick</li></ol></li></ul>Additional information:<ul><li><a target="_blank" rel="ugc" href="https://github.com/lshqqytiger/stable-diffusion-webui-amdgpu-forge">Webui </a>I use</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/660673/pony-standard-vae">VAE </a>I use</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/116225/4x-ultrasharp">4x-Ultrasharp</a> as an Upscaler</li><li>Imagine dimensions vary depending on what I'm trying to do</li><li>Sampling steps I go 20-30</li><li>hires steps I go 8-15 (I don't always use hires fix)</li><li>Denoising strength I go 0.4</li><li>I use 7 CFG Scale and <a target="_blank" rel="ugc" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding">CFG Scale Fix</a> set at 9</li><li><a target="_blank" rel="ugc" href="https://github.com/wkpark/uddetailer">uddetailer</a> for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full face</li></ul>If you wanna support me <a target="_blank" rel="ugc" href="https://ko-fi.com/infamousfish">ko-fi</a>

Kim Possible Style + 5 Characters [Pony]

1038796_training_data.zip

kim_possible_style.safetensors

Pony

My first attempt at creating a lora containing both a style and characters feedback is appreciated, I used 200 total images from the show, 75 of them being random characters, scenery, etc and 25 for each character, overall I think it turned out alright but I will train it again because some of the characters aren't consistent and sometimes the style isn't as visible. trained here on civitai using <a rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/257749?modelVersionId=290640" target="_blank">Pony Diffusion V6 XL</a> as a training model at 1024Style info:<ul><li>trigger word: kan_style</li><li>weight: 1 is perfect</li></ul>Characters info:<ul><li>Trigger word - looks tag<ol><li>Kim: kimaps - long hair, orange hair, green eyes</li><li>Monique: moniiqkue, black eyes, black hair, dark-skinned female, dark skin</li><li>Bonnie: bomnkinie, short hair, brown hair, green eyes</li><li>Ann: ankkiin, brown hair, short hair, blue eyes, doctor, lab coat</li><li>Shego: shmeikgo, black hair, long hair, green eyes, gloves, bodysuit, lipstick</li></ol></li></ul>Additional information:<ul><li><a rel="ugc noopener noreferrer nofollow" href="https://github.com/lshqqytiger/stable-diffusion-webui-amdgpu-forge" target="_blank">Webui </a>I use</li><li><a rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/660673/pony-standard-vae" target="_blank">VAE </a>I use</li><li><a rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/116225/4x-ultrasharp" target="_blank">4x-Ultrasharp</a> as an Upscaler</li><li>Imagine dimensions vary depending on what I'm trying to do</li><li>Sampling steps I go 20-30</li><li>hires steps I go 8-15 (I don't always use hires fix)</li><li>Denoising strength I go 0.4</li><li>I use 7 CFG Scale and <a rel="ugc noopener noreferrer nofollow" href="https://github.com/mcmonkeyprojects/sd-dynamic-thresholding" target="_blank">CFG Scale Fix</a> set at 9</li><li><a rel="ugc noopener noreferrer nofollow" href="https://github.com/wkpark/uddetailer" target="_blank">uddetailer</a> for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full face</li></ul>I do all of my lora training here, if you can spare any buzz I would appreciate it

Files with SHA256: ed2d574131f23d39b47f313115b37e2e945f4e60a69640f97a2136052108ded4