pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Benevolent/Plumpu")
prompt = "masterpiece, best quality, outdoors, 1girl, solo, looking at viewer, cowboy shot, yellow eyes, plump, fat, sweat on body, sweat, <lora:Concept_Plump:1>,"
image = pipe(prompt).images[0]LoRA / Concept | Chubby (Fat Rolls)
- Prompt
- masterpiece, best quality, outdoors, 1girl, solo, looking at viewer, cowboy shot, yellow eyes, plump, fat, sweat on body, sweat, <lora:Concept_Plump:1>,
- Negative Prompt
- FastNegativeV2, worst quality, low quality,
Trigger words
You should use <lora:Concept_Plump:1> to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- -
Model tree for Benevolent/Plumpu
Base model
stabilityai/stable-diffusion-xl-base-1.0
# Gated model: Login with a HF token with gated access permission hf auth login