Image-Text-to-Image
Diffusers
English
wuwa
wuthering_waves
iuno
iuno_(wuthering_waves)
iuno_\(wuthering_waves\)
lora
character
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Laxhar/noobai-XL-Vpred-1.0,circlestone-labs/Anima", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("StarkEater/Iuno_Wuthering_Waves")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]No tokens were kept. ==> No trigger words needed.
Important tags were protected and, hence, automatically shuffled.
Rest of the tags were dropped and shuffled.
I will post the NoobAI XL vpred 1.0 lora first, since I can easily do it in my own PC.
For Anima, it will take time since I will be fully finetuning a personal style in it first - this time with [2048, 1536, 1024, 768, 512] resolution. Yes, the batch size for full finetuning will be 38-40, like always.
- Downloads last month
- -
Model tree for StarkEater/Iuno_Wuthering_Waves
Base model
Laxhar/noobai-XL-1.0 Finetuned
Laxhar/noobai-XL-Vpred-0.5 Finetuned
Laxhar/noobai-XL-Vpred-0.6 Finetuned
Laxhar/noobai-XL-Vpred-0.65 Finetuned
Laxhar/noobai-XL-Vpred-0.75 Finetuned
Laxhar/noobai-XL-Vpred-1.0