MIDNIGHT_NAI-XL_vPredV1 / README.md

MidnightRunner

Update README.md

e6e65e1 verified 10 months ago

preview code

raw

history blame

8.46 kB

metadata

license: creativeml-openrail-m
language:
  - en
base_model: Laxhar/noobai-XL-Vpred-1.0
tags:
  - SDXL
  - noobai-XL
  - Vpred-1.0
  - text-to-image
  - ComfyUI
  - Automatic1111
  - Diffuser
pipeline_tag: text-to-image
library_name: diffusers
datasets:
  - LaxharLab/NoobAI-XL-dataset
metrics:
  - FID
  - IS
widget:
  - text: >-
      high quality, masterpiece, detailed, 8K, artist:nyantcha,
      evangeline_(nyantcha), vibrant surreal artwork, rainbow, light particles,
      from above, volumetric lighting, ((adult girl:1.2)), natural huge breasts,
      woman dressed as white rabbit, sleek pure white outfit, delicate white
      bunny ears, braid, plump, skindentation, huge breasts, falling into
      swirling black hole, seen from behind, glancing over shoulder, alluring
      mysterious expression, dress, zipper, zipper pull, detached sleeves,
      breasts apart (shoulder straps), buckles, long dress, swirling cosmic
      patterns, glowing particles, dramatic lighting, vibrant neon pink and blue
      tones, hyper-detailed, cinematic depth of field, smooth texture, film
      grain, chromatic aberration, high contrast, limited palette
    parameters:
      negative_prompt: >-
        lowres, worst quality, low quality, bad anatomy, bad hands, 4koma,
        comic, greyscale, censored, jpeg artifacts, overly saturated, overly
        vivid, (multiple views:1.1), (bad:1.05), fewer, extra, missing, worst
        quality, jpeg artifacts, bad quality, watermark, unfinished,
        displeasing, sepia, sketch, flat color, signature, artistic error,
        username, scan, (blurry, lowres, worst quality, (low quality:1.1), ugly,
        (bad anatomy:1.05), artist name, (patreon username:1.2)
    output:
      url: stand_on_ripplewater.jpeg

MIDNIGHT_NAI-XL_vPredV1

Model Type: Diffusion-based text-to-image generative model

Base Model: SDXL 1.0 & Laxhar/noobai-XL-Vpred-1.0

License: CreativeML Open RAIL++-M

Model Description

MIDNIGHT_NAI-XL_vPredV1 is a specialized fine-tuning of the NoobAI-XL (NAI-XL) model, designed to enhance anatomical precision, compositional coherence, and versatile style integration. This model excels in generating high-quality images with vibrant colors while minimizing overexposure.

Usage Recommendations

Sampling Methods

MIDNIGHT_NAI-XL_vPredV1 is optimized specifically for Euler (normal).
Use ModelSamplingDiscrete with V-prediction and ZsNR set to true.
Other samplers may not provide stable results, and V-prediction models do not support other samplers.

CFG Scaling

Dynamic CFG Plugin is bypassed as a backup for potential future needs.
Manually adjust CFG scaling within a range of 5-6 for the best balance.
For optimal results, a preferred setting of 5.3 is recommended.

Custom Workflow

For an optimized generation process, use the MIDNIGHT1111_Chasm 2025-02-04 ComfyUI workflow.
This workflow is specifically designed to leverage the strengths of MIDNIGHT_NAI-XL_vPredV1, providing a streamlined and efficient image generation pipeline.

MIDNIGHT1111_Chasm

For an optimized generation process, consider using the custom workflow MIDNIGHT1111_Chasm 02-05-25. This workflow is tailored to leverage the strengths of the MIDNIGHT_NAI-XL_vPredV1 model, providing a streamlined and efficient image generation pipeline.

Note: The above image is a preview of the MIDNIGHT1111_Chasm workflow.

Trigger Word Lists

To enhance the model's performance and specificity, the following trigger word lists are included:

These lists provide recognized tags for various artists and characters, facilitating more accurate and tailored image generation.

How to Use

Method I: reForge

Installation: If not already installed, follow the instructions in the reForge repository to set up.
Usage: Launch WebUI and use the model as usual.

Method II: ComfyUI

Installation: Follow the setup instructions in the ComfyUI repository.
Workflow Sample: Utilize the provided ComfyUI workflow sample for guidance.

Method III: WebUI

Installation: Follow the instructions in the WebUI repository to set up. Switch to dev branch: git switch dev

Follow the setup instructions in the WebUI repository."

Navigate to the WebUI Directory: Before updating or switching branches, ensure you're inside the stable-diffusion-webui folder command: |
```
cd stable-diffusion-webui
```
Switch to the Development Branch (Optional, for testing new features): If you want to use the latest features from the development branch, run: command: |
```
git switch dev
git pull
```
⚠️ Note: The dev branch may contain bugs. If stability is your priority, it's best to stay on the main branch.
Update WebUI (Main or Dev Branch): To pull the latest updates while on either branch, run: command: |
```
git pull
```
🔄 Restart WebUI after updating to apply changes."
Configuration: Ensure you're using a stable branch, as the dev branch may contain bugs.

Method IV: Diffusers

import torch
from diffusers import StableDiffusionXLPipeline
from diffusers import EulerDiscreteScheduler

ckpt_path = "/path/to/model.safetensors"
pipe = StableDiffusionXLPipeline.from_single_file(
    ckpt_path,
    use_safetensors=True,
    torch_dtype=torch.float16,
)
scheduler_args = {"prediction_type": "v_prediction", "rescale_betas_zero_snr": True}
pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config, **scheduler_args)
pipe.enable_xformers_memory_efficient_attention()
pipe = pipe.to("cuda")

prompt = """masterpiece, best quality,artist:john_kafka,artist:nixeu,artist:quasarcake, chromatic aberration, film grain, horror \(theme\), limited palette, x-shaped pupils, high contrast, color contrast, cold colors, arlecchino \(genshin impact\), black theme,  gritty, graphite \(medium\)"""
negative_prompt = "nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro"

image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=832,
    height=1216,
    num_inference_steps=28,
    guidance_scale=5,
    generator=torch.Generator().manual_seed(42),
).images[0]

image.save("output.png")

Acknowledgments

Special thanks to:

Development Team: Laxhar Lab
Coding Contributions: Euge
Community Support: Various contributors

Additional Resources

Guidebook for NoobAI XL: English Version
Recommended LoRa List for NoobAI XL: Resource Link
Fixing Black Images in ComfyUI on macOS (M1/M2): Read the Article
Creative Solutions and Services: Magnabos.co

License

This model is licensed under the CreativeML Open RAIL++-M License. By using this model, you agree to the terms and conditions outlined in the license.