For best results, use the following command

• prompt (Trigger Words): melaura, girl
• negative prompts: ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, bad anatomy, bad proportions, cloned face, disfigured, out of frame, extra limbs, bad anatomy, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, mutated hands, fused fingers, too many fingers, long neck, text, letters, signature, web address, copyright name, username, error, extra digit, fewer digits, loadscreen, grid, stock image, a stock photo, promo poster, fat, text, logo, brand, watermark, water mark, low quality,
• scheduler: EulerAncestralDiscreteScheduler (Euler a).

License: CreativeML Open RAIL++-M License

You are free to:

• Share - copy and redistribute the material in any medium or format
• Adapt - remix, transform, and build upon the material

Under the following terms:

• Attribution - You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
• NonCommercial - You may not use the material for commercial purposes.

Examples of prompts used

Prompt: melaura, girl, asian woman with long dark hair wearing a white dress, a photorealistic painting by Lü Ji, trending on cg society, photorealism, popular korean makeup, popular south korean makeup, clear makeup

Guidance_Scale: 7.5

Num_Inference_Steps: 50

scheduler type: EulerAncestralDiscreteScheduler

Prompt: melaura, girl, a woman with a pearl necklace and pearl necklace, a photorealistic painting by Kim Deuk-sin, featured on cg society, photorealism, portrait of female korean idol, popular korean makeup, popular south korean makeup, shiny cheeks

Guidance_Scale: 7.5

Num_Inference_Steps: 50

scheduler type: EulerAncestralDiscreteScheduler

Prompt: melaura, girl,

Guidance_Scale: 7.5

Num_Inference_Steps: 50

scheduler type: EulerAncestralDiscreteScheduler

Gradio & Colab

We also support a Gradio Web UI and Colab with Diffusers to run Melaura:

🧨 Diffusers

Before running it, make sure you have the necessary pip libraries installed:

pip install -q diffusers transformers omegaconf

Running the pipeline (if you don't swap the scheduler, it will run with the default EulerDiscreteScheduler. In this example, we're swapping it to EulerAncestralDiscreteScheduler:

from diffusers import StableDiffusionPipeline, EulerAncestralDiscreteScheduler
import torch
import os

repo_id = "DamarJati/melaura-v1"

pipe = StableDiffusionPipeline.from_pretrained(
    repo_id,
    torch_dtype=torch.float16,
    use_karras_sigmas=True,
    algorithm_type="sde-dpmsolver++"
    )
pipe.to('cuda')

#Safety Checker
pipe.safety_checker = None
pipe.requires_safety_checker = False

#Scheduler
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)


Prompt = "melaura, girl, hd, pink lips, detailed, age 16, Off-shoulder top, shiny cheeks"
Negative_prompt = "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry"

image = pipe(
    prompt=Prompt, 
    negative_prompt=Negative_prompt, 
    width=512,
    height=512,
    guidance_scale=8,
    num_inference_steps=50
    ).images[0]
image.save("melaura.png")

Limitation

This model inherit Stable Diffusion 1.5 limitation