import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("OpenMOSS-Team/MOSS-Image-Base", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Te2douNin9/MOSS-Image-TendouAris")
prompt = "-"
image = pipe(prompt).images[0]MOSS-ArisuLoRA-v1.0.0
- Prompt
- -
- Prompt
- -
Model description
A small Tendou_Aris character enhancing LoRA for MOSS Image. Given that the MOSS Image model is already quite powerful on its own, this LoRA focuses primarily on preserving specific character traits—such as face shape and the halo—during generation; therefore, you should not expect it to produce drastic changes. Additionally, there are still some limitations regarding the rendering of the irises, as it fails to accurately replicate the white circular rings characteristic of Aris’s eyes.
Trigger words
You should use tendou_aris_moss to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 279
Model tree for Te2douNin9/MOSS-Image-TendouAris
Base model
OpenMOSS-Team/MOSS-Image-Base