Witch. Tested with my Illustrious and SDXL checkpoint available on TA. Trained on TA with 80 pics with my checkpoint, generated with SDXL and ILL checkpoint.This model does not use any real-life or celebrity content. Please do not use this model for any real-life, celebrity, or pornographic content.
Please read this first : -------> If you like my models, please read, it's important. | Civitai
My work goes on only thanks to your help, with donations in buzz. If you can, always vote for my models and videos and always donate something to allow me to train other models on CivitAi or TA. Without these donations, I probably won't be able to continue. With higher prices from CivitAi and censorship, it becomes very difficult to proceed. I hope for your understanding and support. Thank you.
SDXL Weight 0.6 to 0.9 CFG 3.5 to 5.5
IMPORTANT: All my models work only if the trigger words and the recommended negative and positive prompts and embeddings are used. If you have a different result from the images, it is because you have not used the recommended settings. Too many loras and/or embeddings can ruin the model's result. To have images like the ones I made, use ONLY the recommended settings. Thanks.
If you like the character, always leave a like and a picture, and if you give some buzz you will allow me to train other LORAs or MODELS. Downloading only is not useful. For model visibility, remember to rate the images in my gallery and leave a like. Thank you.
SDXL Negative prompt : low quality, low realism, 3d rendering, anime, deformed body
SDXL Positive prompt : LORA, (realistic:1.3), photorealistic, masterpiece, realistic, detailed, 8k, 1girl, beautiful photography of mywitch, witch hat, thong,...
Add cleavage, large breasts, black underwear, for better results
Add big ass, bubble butt for back views
You can add veil or coat or set background with castle, mist, cemetery or bedroom, sitting pose
You can choose bra or corset, or lingerie for different results
You can choose black hair or white hair
Recommended for a better result: ADETAILER mediapipe face full with impaint 0.55
Setting : Sampling Euler A or DPM++2M, HiresFix on, ITF-skinDiffDetail-Lite at 2x, Denoising 0.38, Upscale 2x, Sampling steps 35+, Resolution 768x1024, Upscale 2x ITF-skinDiffDetail-Lite next passage.
If you appreciate the lora, please consider leaving us a review and sharing the images generated using this model. Your feedback is valuable to both us and the AI community. Thanks.
IMPORTANT : If you can, please donate me some buzz to allow me to train other loras and generate other content. Please always vote with a like for the model and images (not only download), it costs nothing and help me continue to share. Thank you.
Please follow me on TA for new content.