*THIS CHECKPOINT IS SD1.5 VERSION *BEST USED FOR 'Anime Illust Diffusion' CHECKPOINT *Original files for the majority of these versions are pickletensor. I have converted them to safetensors. How well they perform is up to debate. Model trainer/creator: Euge_ Uploaded to MoescapeAI by Laanver Phi [View the full model detail on CivitAI] deformv6 Source: https://civitai.com/models/16807?modelVersionId=53718 badv3 Source: https://civitai.com/models/16807?modelVersionId=19837 badv4 Source: https://civitai.com/models/16807?modelVersionId=30390 badv5 Source: https://civitai.com/models/16807?modelVersionId=36538 aidv1 Source: https://civitai.com/models/16807?modelVersionId=40158 aid28 Source: https://civitai.com/models/16807?modelVersionId=49129 aid29 Source: https://civitai.com/models/16807?modelVersionId=81990 aid291 Source: https://civitai.com/models/16807?modelVersionId=91028 aid210 Source: https://civitai.com/models/16807?modelVersionId=111570 Basic Info Embedds recommended for use with the AnimeIllustDiffusion model Eval Parameters Each text embedd is described by the following parameters: Positive/Negative Text Embedding: If a text embedd is a positive text embedd, it should be used in positive prompts. Conversely, if a text embedd is a negative text embedd, it should be used in negative prompts. Scope: The main content of the image that a text embedd will primarily affect. Vector Count: The number of token that the text embedd represents. Generally, the part of a prompt containing more than 75 tokens will be ignored. Therefore, the fewer the number of vectors in a text embedding, the more space you will have left to input the prompt. Vector Strength: The magnitude of a token's vector. The higher the vector strength, the stronger the effect. The vector strength of token is usually between [-0.05, 0.05]. Using parentheses to enhance prompts is not equivalent to increasing vector strength. Ref [1] AnimeIllustDiffusion Model Webpage: https://civitai.com/models/16828/animeillustdiffusion