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 results
VAE IS NOT BAKED IN PLEASE USE SDXL VAE
Cranberry_4: Second version, trained on a larger dataset of about 10 000 images with a lot of new concepts and artists thanks to SDXL
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 look
PS: also for some reasons, High.res fix of 1.5 works better than 2 so use it :)
OLD VERSIONS
PonyXl trained to fit an anime aesthetic with a lot of prompting freedom, it can generate great anthro/feral/human results
VAE IS NOT BAKED IN PLEASE USE PONY VAE
Cranberry_2: Second version, trained on a larger dataset of about 4000 images for about 100 epochs per images
Cranberry_1: First version, trained on a small dataset of about 2000 images for about 100 epochs per images
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 too
AND
(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 too
Negative: 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 look
PS: also for some reasons, High.res fix of 1.5 works better than 2 so use it :)
Description
V2 is here, trained more, refined more and added some better understanding of concepts
Scores from pony ( score_9....) are still needed but the model still work well without so try as you want
FAQ
Comments (8)
Checkpoint of V2 is lovely at producing consistent Furry/human characters. I would love to see a refinement with style and look. Maybe using a lora along with my prompts would help! I will continue to experiment with this. It's lovely~!
Generates wonderful looking characters and backgrounds however whenever I gen it seems it has this weird sort of sepia filter on it with white dots strewn randomly about the image. I've verified that I was using the correct vae and prompts were correct/no workflow errors.
Anyone else having this issue?
which version are you using ?
if you are using V2 you do not need a Vae anymore
@N_Endo it seemed to be an issue with either prompt, lora, or something in between as I cannot seem to replicate the issue after cleaning up the workflow. I am using V2. If it pops up again I'll provide screenshots along with the images generated Edit: scratch that, got the issue again, let me post a few to the gallery.
@kazekaze1 looks like a problem on your side, either vae, sd related or lora. it work fine for me
@kazekaze1 maybe the sampler too idk
@N_Endo still pokin' around, seems to be doing it regardless of lora or sampler. Dunno what I'm doing wrong.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.