In this case, either increase Face Recognition minimum confidence or disable this options. May cause problems on images with small character head (full-height pictures and landscapes). Inpaint only the biggest face on the image: does what it says, can be great to prevent undesired face detection and inpaint of background or body parts. May negatively impact desired result on "noisy" and blurry artstyles. Many small fixes in code's logic and parametersĬomprehensive description of Advanced and Really Advanced options and tips for their usage:įiltering function: sharpens and applies denoising filter to image after High-Res Fix to improve quality and reduce the number of necessary img2img steps. Styles from Styles Menu are now working properly True img2img mode: edit existing pictures with SD upscale and automatic face&eyes inpaintīrand new Really Advanced options tab for brave enthusiasts willing to take complete control of AutoChar's generation pipeline and maximize their creativityįixed infamous bug with OpenCV on inpaint step (If you STILL have it, do this: please download archive again, I made changes to the code which helped people! )įixed inpaint only masked padding, drastically improving results on some artstyles and checkpointsįixed High-Res Fix upscalers' list, now it shows all available upscalers as it should Upscaler choosing changed from check panels to dropdowns to reduce distractionįunction and slider groups divided to different blocks with clarification headers Info added for all crucial parameters, containing tips for usage and clarification for not-so-obvious functions Click "Generate" and enjoy 0.9.5 changes: Select "AutoChar 0.9.5" in dropdown menu Scripts in the lower part of pageĤ. Write prompt, select basic parameters as usual (you don't need highres fix, since it's included in the algorithm)ģ. PLEASE, don't try to install via URL, it's not an extension, it won't be visible this way!Īlso I highly recommend to download 4x-UltraSharp Upscaler ( ) and put in /modes/ESRGAN folder How to use, in shortĢ. onnx face recognition model in your stable-diffusion-webui/scripts folder Updated the YuNet version for improved face detection.įor text description of scripts' basic idea check 0.9 version tab. Added automatic check in script body on startup to always ensure latest version.įixed LoRA not transferring to Inpaint step correctly. All the other steps will be stored in Img2img folder.įixed critical bug with OpenCV. Now only first and last generation of each cycle will be saved to Txt2img output folder by default. On by default.īiggest face: inpaints only the largest face on generation, no more abominable body horrors on armpits and breasts, also helps with crowdy pictures. Lower LoRA: new measure to avoid burnout on faces when using strong or multiple LoRAs. Much greater detail and sharpness + customization with your preferred upscaler. Enjoy fully automatic enhancement for all of your randomized generations.Īdded SD Upscale as a new default instead of basic Image2Image. New and improved AutoChar Beta 0.9 is ready to enhance your art like never before!Īdded full support for Dynamic Prompts.
0 Comments
|
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |