import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SG161222/RealVisXL_V5.0", torch_dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("steven-fei/emma_realvisxl_lora")
prompt = "`emma, young woman, long dark hair, white dress, studio lighting, neutral background`"
image = pipe(prompt).images[0]emma_realvisxl_lora
- Prompt
- `emma, young woman, long dark hair, white dress, studio lighting, neutral background`
Model description
SDXL LoRA (Kohya) for consistent character "Emma" — trigger: emma_hero01 — base: RealVisXL V5.0 fp16 — photoreal portrait / fashion try-on MVP.
Trigger words
You should use Use **`emma_hero01`** at the beginning of the positive prompt (same token used in training captions). to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 5
Model tree for steven-fei/emma_realvisxl_lora
Base model
SG161222/RealVisXL_V5.0