※A LoRa model trained by a friend with multires noise.
This is a LoRa model that trained by 50+ img generated with NijiV5,and it's the multires noise version.
This model can achieve more detailed decorative design and hanafuda background in the costume.
This name is a description of pattern style
weight 1.0 maybe generates better imgs.
Flower, obi and so on are suggersted tag.
Description
FAQ
Comments (4)
Do you know the Zold:out game? Can you train a model in that same art style like the character art? It would be appreciated.
I'm sorry, but I don't know this game. Can you tell me what the art style is like?
@L_A_X It's hard to explain but it's like a pencil anime art style sharp and clean.
Here's a link to what the art looks like in the game.
@Soli The data is likely to be insufficient, making it impossible for him to create a beautiful Lora. To achieve the desired result, it is necessary to have numerous images.
You can gather a minimum of 50 or one hundred images of high quality and clarity, and then send them to him via a (mega )
I hope this information proves helpful to you.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.