Hannah-02 is a revised version of Hannah-01 which had a nasty habit of always putting the subject in a corridor.
Hannah-02 was created by using an AI image created in Character.AI. This image was then used by ChatGPT to create a description which once tweaked, was used as a prompt in CivitAI to generate a series of 20 images with a simple white background (hopefully eliminating the corridor problem) and these images were used to train this LORA.
In the short time of testing this LORA the woman appears to not be in focus. And because the training images all had a white background it seems difficult to have the background be anything other than white. Any suggestions on how to improve that would be greatly appreciated.
Suggested negative prompt:
negative prompt: studio lighting, plain background, neutral background, soft wall, training background
This LORA will be tested and images will be uploaded to the Gallery.
Description
Hannah-02 is a revised version of Hannah-01 which had a nasty habit of always putting the subject in a corridor.
Hannah-02 was created by using an AI image created in Character.AI. This image was then used by ChatGPT to create a description which once tweaked, was used as a prompt in CivitAI to generate a series of 20 images with a simple white background (hopefully eliminating the corridor problem) and these images were used to train this LORA.
This LORA will be tested and images will be uploaded to the Gallery.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.