Views
No views yet
miladyii in your prompts to activate the trained style. Trained using the StationThis pipeline.miladyii |  |
| This digital anime-style drawing features a chibi character ... | This is a digital anime-style drawing of a young girl, known... |
 |  |
| This is a digital drawing of a chibi-style anime character w... | This is a digital drawing in a chibi anime style featuring a... |
.safetensors file from the Files tabComfyUI/models/loras/0.8-1.0miladyii in your prompt1import torch
2from diffusers import FluxPipeline
3
4pipe = FluxPipeline.from_pretrained(
5 "black-forest-labs/FLUX.1-dev",
6 torch_dtype=torch.bfloat16
7)
8pipe.load_lora_weights("ms2stationthis/hffinal_miladyii_30")
9pipe.to("cuda")
10
11image = pipe(
12 prompt="miladyii portrait, soft lighting, detailed",
13 guidance_scale=3.5-4.0,
14 num_inference_steps=20-30,
15 generator=torch.Generator("cuda").manual_seed(42)
16).images[0]
17
18image.save("output.png")| Parameter | Value |
|---|---|
| LoRA Strength | 0.8-1.0 |
| Guidance Scale | 3.5-4.0 |
| Inference Steps | 20-30 |
| Resolution | 1024x1024 |
miladyii teary black eyesmiladyii pale skinmiladyii and longmiladyii gentle smile. at the bottom of the imagemiladyii