MyNovelAnimeGirl

LORA
Original


Updated:

Version Detail

SDXL 1.0
880
10
The CFG scales I recommend are 1, 3 and 7. These will give very good results. Also, always try to use the following prompts. Prompt=score_9,score_8_up,score_7_up,source_anime,BREAK Prompt Negative= score_6, score_5, score_4, source_cartoon, 3d, (censor),monochrome,blurry, lowres,watermark, worst quality,bad quality,bad hands,very displeasing,extra digit,fewer digits,jpeg artifacts, source_cartoon, 3d, (censor),monochrome,blurry, lowres,watermark Another thing I recommend, although it's not mandatory, is to activate the SDXL Refiner option. If possible, also use 25 Sampling Steps because this improves the quality and brings it closer to what you want. Important notice, if you generate an image and it comes out deformed or strange try changing the CFG, each Prompt uses different CFG that is depending on what you have written in your Prompt you need to change the Scale, that is why I have given the recommendations of scale 1, 3 and 7 these 3 scales are the ones that make the most correct images. however you can go testing the Scales that you find most suitable for your image. (Personal recommendation= I personally really like the CFG Scale 3 images, they have a wonderful style)

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts

Describe the image you want to generate, then press Enter to send.