datacte / proteus-v0.4-lightning

ProteusV0.4: The Style Update - enhances stylistic capabilities, similar to Midjourney's approach, rather than advancing prompt comprehension

  • Public
  • 130.7K runs
  • GitHub
  • License

Run time and cost

This model costs approximately $0.057 to run on Replicate, or 17 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 79 seconds. The predict time for this model varies significantly based on the inputs.

Readme

ProteusV0.4: The Style Update Lightning Edition

This update enhances stylistic capabilities, similar to Midjourney’s approach, rather than advancing prompt comprehension. Methods used do not infringe on any copyrighted material.

Proteus

Proteus serves as a sophisticated enhancement over OpenDalleV1.1, leveraging its core functionalities to deliver superior outcomes. Key areas of advancement include heightened responsiveness to prompts and augmented creative capacities. To achieve this, it was fine-tuned using approximately 220,000 GPTV captioned images from copyright-free stock images (with some anime included), which were then normalized. Additionally, DPO (Direct Preference Optimization) was employed through a collection of 10,000 carefully selected high-quality, AI-generated image pairs.

In pursuit of optimal performance, numerous LORA (Low-Rank Adaptation) models are trained independently before being selectively incorporated into the principal model via dynamic application methods. These techniques involve targeting particular segments within the model while avoiding interference with other areas during the learning phase. Consequently, Proteus exhibits marked improvements in portraying intricate facial characteristics and lifelike skin textures, all while sustaining commendable proficiency across various aesthetic domains, notably surrealism, anime, and cartoon-style visualizations.

Settings for ProteusV0.4-Lightning

Use these settings for the best results with ProteusV0.4-Lightning :

CFG Scale: Use a CFG scale of 1 to 2

Steps: 4 to 10 steps for more detail, 8 steps for faster results.

Sampler: eular

Scheduler: normal

Resolution: 1280x1280 or 1024x1024

please also consider using these keep words to improve your prompts: best quality, HD, ~*~aesthetic~*~.

if you are having trouble coming up with prompts you can use this GPT I put together to help you refine the prompt. https://chat.openai.com/g/g-RziQNoydR-diffusion-master

Use it with 🧨 diffusers

import torch
from diffusers import (
    StableDiffusionXLPipeline, 
    EulerAncestralDiscreteScheduler,
    AutoencoderKL
)

# Load VAE component
vae = AutoencoderKL.from_pretrained(
    "madebyollin/sdxl-vae-fp16-fix", 
    torch_dtype=torch.float16
)

# Configure the pipeline
pipe = StableDiffusionXLPipeline.from_pretrained(
    "dataautogpt3/ProteusV0.4-Lightning", 
    vae=vae,
    torch_dtype=torch.float16
)
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda')

# Define prompts and generate image
prompt = "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed"
negative_prompt = "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image"

image = pipe(
    prompt, 
    negative_prompt=negative_prompt, 
    width=1024,
    height=1024,
    guidance_scale=2,
    num_inference_steps=8
).images[0]

please support the work I do through donating to me on: https://www.buymeacoffee.com/DataVoid or following me on https://twitter.com/DataPlusEngine