We have updated our quality standards found under our uploading guidelines.
This was done mostly because modern AI generations are of much better quality now than they have been in the past, and we would like for this archive to focus on displaying the best work, not just any and all work. Please take a moment to review the guidelines before uploading going forward now. Older submissions will be exempt for this at this point in time, but keep in mind in the far future we might clean those up as quality continues to improve.
teriyakiFur
MemberWhat kind of prompt did you use to make this is really good man
agreenfish
MemberThis was with fluffyrock and the quality tags LoRa. Artist tags don't make too much of a difference, I recommend a mix of "styles" and some artists that specialize in tf to capture details.
Key tags are "transformation sequence", "mid transformation", "human to anthro transformation", all the growth tags, torn clothing and more (Example below):
The other thing that helps is manipulating the image A lot of the models, especially older ones trained on fixed size images (although you don't need to use them) repeat characters and content at extreme aspect ratios
you can force the aspect ratio to be very big and wide (as above) to take advantage of this
It took many iterations to get a nice outcome from this, and a lot of inpainting/touch up. Another trick is to break the sequence up into smaller images and inpaint / img2img them separately, then recombine again. An img2imged image lines up nicely with the original image which makes editing easier
Updated
Login to respond »