Sathariel
Sathariel - a latent diffusion model for weebs. Like other anime-styled Stable Diffusion models, it also supports danbooru tags to generate images.
To create this model, I made two finetunes based on the merge of MidnightMixerV2 and MidnightMapleV1 and then mixed these finetunes together.
At the moment there are several versions of the model in the repository, there is the usual SatharielV1 and there is SatharielV1A, SatharielV1B or SatharielV1C, the difference between them is minimal, so they were released as alternative models.
SatharielV1C_DX is a merge of SatharielV1C and the model by DutchaAlex, it has better colors.
🧨 Diffusers
This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion.
from diffusers import StableDiffusionPipeline
import torch
model_id = "ShussarSDFA/Sathariel"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "masterpiece, best quality, 1girl, fox ears, looking at viewer"
image = pipe(prompt).images[0]
image.save("./SV1.png")
