import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stablediffusionapi/anylora-checkpoint", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("dolainu/Annytf_lora_Vtuber")
prompt = "<lora:AnnytfV0.4Reg:0.7>, anny_bikini, purple eyes, sitting, petite"
image = pipe(prompt).images[0]Annytf
- Prompt
- <lora:AnnytfV0.4Reg:0.7>, anny_bikini, purple eyes, sitting, petite
- Negative Prompt
- easynegative
- Prompt
- <lora:AnnytfV0.5:0.7>, anytfvt, sitting, nude
- Negative Prompt
- easynegative
- Prompt
- <lora:AnnytfV0.5:0.7>, anny_casual
- Negative Prompt
- easynegative
- Prompt
- <lora:AnnytfV0.5:0.8>, anny_casual, purple eyes, wariza
- Negative Prompt
- easynegative
- Prompt
- <lora:AnnytfV0.5:0.7>, anny_bikini, purple eyes, petite, sitting
- Negative Prompt
- easynegative
- Prompt
- <lora:AnnytfV0.4Reg:0.7>, anytfvt, purple eyes, petite, sitting, big breasts, beach
- Negative Prompt
- easynegative
Model description
Tested at 0.7-0.8 strength.
Trigger Worlds:
anny_casual: Pink outfit.
anny_bikini: Black bikini.
anytfvt: This tag is less attached to the outfit so it's more malleable.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 8
Model tree for dolainu/Annytf_lora_Vtuber
Base model
stablediffusionapi/anylora-checkpoint