This is the first time I train concept Lora, comments are appriciate
Recommend Prompt: You can try red lips and skindentation if the face not look mature enough
The difference between 3 LoRA versions are training different methods and datasets. V1 is trained on Usual Dreambooth, PixAI is trained on PixAI's New Lora Maker, SeaArt trained on their Lora Training. Mix is like its name, the mix of all three.
LoHA is trained with V1's dataset, but with LoHA training method and it gave kinda different result. LoCon has an improvement of dataset from V1. And A1111 is now support for LyCORIS so you no longer need to install extensions to use LoHA version
Since this Lora has too many versions, I think I would recommend you using 1 of 3 best versions: LoCon, Mix3 and LoCon2. The comparasion between them is at gallery.
The newest version is for SDXL, you can ignore it if you are using SD15
There are some images I left with no prompt, some are from PixAI and some are from tensor.art. You can download and you use "SD Prompt Reader" to read prompt
Description
FAQ
Comments (9)
i can't get the same result like you
Is it the color or girl's body? If it is the color then you can use epi_noiseoffset I have recommended
it has the same result but the quality is very poor
dunno where is the problem, i already follow everything i can
@Rendai i already use that, its the same not a good art
@pandoraox00 the recommend weight for this is 0.7. You can check my Quality Prompt and The Neg Embedding I'm using. And what model and VAE did you use? Steps and CFG too?
@Rendai im using ur image as the prompt and the others, but i cant find where i can download vae and upscaler you using for
@pandoraox00
There is no upscaling here, I only use this vae https://huggingface.co/phamhungd/GuoZovya/resolve/main/Anime-fp16.vae.pt and ADeatiler for face. Please be noticed that I used “Negative Embeddings” for these images, they are the prompts with (…:1.2). If you still have bad quality images then I don’t know why, because I have used this LoRA to generate at other AI generated website like tensor.art and pixai and they still give me similar good result.
@Rendai alright i will try it again, do you have a discord so i can ask you about it but it fine if you dont want to since is your hard work. and thanks for answering my question