Text-to-Image
Diffusers
art
music
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("M5-Dev/Miku-lora-for-sd-1.5", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

๐Ÿ“„ Model Card: Miku_ME (Legacy SD 1.5 Edition) โœจ Overview A lightweight, high-performance LoRA designed for Hatsune Miku with a unique Egyptian flair. Optimized specifically for the Anything V5 base model to deliver that classic, vibrant anime aesthetic.

๐Ÿš€ Key Features Optimized for SD 1.5: Fast generation and low VRAM usage.

Vibrant Style: Enhanced colors and sharp anime lines characteristic of the Anything V5 engine.

Cultural Fusion: Seamlessly integrates Miku with Egyptian themes, clothing, and backgrounds.

๐Ÿ› ๏ธ Usage Base Model: Anything V5 (Recommended)

Trigger Word: miku_sd1.5

LoRA Weight: 0.6 - 0.8

๐Ÿ“œ Note This is the legacy version for creators who prefer the speed and flexibility of SD 1.5.

Downloads last month
8
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for M5-Dev/Miku-lora-for-sd-1.5

Finetuned
(1)
this model

Collections including M5-Dev/Miku-lora-for-sd-1.5