V4 NEW VERSION OUT!with magic and a lot of time Cranberry is now SDXL Based. I took Cranberry V2 and force fed it to SDXL models until a decent base appeared that i trained over a new data set of 10 000 images. trained to fit an anime aesthetic with a lot of prompting freedom, it can generate great anthro/feral/human resultsVAE IS NOT BAKED IN PLEASE USE SDXL VAECranberry_4: Second version, trained on a larger dataset of about 10 000 images with a lot of new concepts and artists thanks to SDXL<hr />Trained it with custom captions to still perform good on minimalistic prompts (You really can have a wide range of results for a single prompt)Positive: Same as sdxl, simple as "amazing quality, best quality"Negative: lowres, bad quality and worst quality are nice none but (monochrome, greyscale) are sometimes good as the model tend to generate monochrome images, you can also put (cartoon, toon) if you want to have a real anime lookPS: also for some reasons, High.res fix of 1.5 works better than 2 so use it :)<hr />OLD VERSIONSPonyXl trained to fit an anime aesthetic with a lot of prompting freedom, it can generate great anthro/feral/human resultsVAE IS NOT BAKED IN PLEASE USE PONY VAECranberry_2: Second version, trained on a larger dataset of about 4000 images for about 100 epochs per imagesCranberry_1: First version, trained on a small dataset of about 2000 images for about 100 epochs per images<hr />Trained it with custom captions to still perform good on minimalistic prompts (You really can have a wide range of results for a single prompt)Positive: Same as pony, no need for source:anime, but place them at THE END of your prompt to have better results( score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up)BUT(score_9) only gives good result tooAND(score_6_up, score_5_up, score_4_up) only act as a "good" version of the raw without positives result so try to use it tooNegative: none but (monochrome, greyscale) are sometimes good as the model tend to generate monochrome images, you can also put (cartoon, toon) if you want to have a real anime lookPS: also for some reasons, High.res fix of 1.5 works better than 2 so use it :)

Cranberry_XL

changelogs: baked VAE.Through magic and mystery V4.0 is here, starting as a refined v3 I managed to somewhat mix CV3 with sdxl models and finetune it to have this result with knowledge form pony and artist tags from sdxl. Works best with forge or comfyui, not Vpred yet but V5 will be.use SDXL vae it is not baked in

Files with SHA256: 09ff8d07cc945f9dba45d4dd52a93fe89fbd220d4466000fbf38a75603388948