|
--- |
|
license: creativeml-openrail-m |
|
language: |
|
- en |
|
base_model: MidnightRunner/MIDNIGHT_NAI-XL_vPred1 |
|
tags: |
|
- SDXL |
|
- noobai-XL |
|
- Vpred-2.0 |
|
- 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), photorealistic, cinematic, film |
|
grain, very awa, (beksinski:1.3)1girl, solo, voluminous, long hair, looking |
|
at viewer, semi-realistic, newest (2023), seductive expression, piercing |
|
gaze, open mouth, sitting, blurry background, pale skin, platinum white |
|
hair, busy background, dress, bow, ribbon, jewelry, bare shoulders, upper |
|
body, sleeveless, pointy ears, hand up, white dress, bracelet, medium |
|
breasts, sleeveless dress, skindentation, see-through clothes, silt eyes, |
|
black sclera, fangs, red bow, armlet, gold, red ribbon, vampire, dress bow, |
|
oshino shinobu, black choker, lips, looking at viewer, open mouth, ring, |
|
smile, smilingwide, teeth, prehensile tail, holding with tail, tail gripping |
|
whiskey jug, whiskey text label "jack daniels", jack daniels logo, tail |
|
gripping, sharp teeth |
|
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: Holding_Whiskey.jpeg |
|
--- |
|
|
|
# MIDNIGHT_NAI-XL_vPredV2 |
|
|
|
**Model Type:** Diffusion-based text-to-image generative model |
|
|
|
**Previous Base Model:** [MIDNIGHT_NAI-XL_vPredV1](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV1) |
|
|
|
**License:** [CreativeML Open RAIL++-M](https://github.com/CompVis/stable-diffusion/blob/main/LICENSE) |
|
|
|
## Model Description |
|
|
|
MIDNIGHT_NAI-XL_vPredV2 is a specialized fine-tuning of the MIDNIGHT_NAI-XL_vPredV2 (NAI-XL) model, designed to enhance realistic precision, compositional coherence, and versatile style integration. This model excels in generating high-quality realistic images with vibrant colors while minimizing overexposure. |
|
|
|
## Usage Recommendations |
|
|
|
### **Sampling Methods** |
|
MIDNIGHT_NAI-XL_vPredV2 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 02-05-25**](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/MIDNIGHT1111_Chasm%2002-05-25.json) ComfyUI workflow. |
|
This workflow is specifically designed to **leverage the strengths of MIDNIGHT_NAI-XL_vPredV2**, 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](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/MIDNIGHT1111_Chasm%2002-05-25.json). 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.* |
|
|
|
### Method I: reForge without MIDNIGHT1111_Chasm Workflow |
|
|
|
1. **Installation:** If not already installed, follow the instructions in the [reForge repository](https://github.com/Panchovix/stable-diffusion-webui-reForge) to set up. |
|
2. **Usage:** Launch WebUI and use the model as usual. |
|
|
|
### Method II: ComfyUI *with* MIDNIGHT1111_Chasm Workflow |
|
|
|
1. **Installation:** Follow the setup instructions in the [ComfyUI repository](https://github.com/comfyanonymous/ComfyUI). |
|
2. **Workflow Sample:** Utilize the provided [ComfyUI workflow sample](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/MIDNIGHT1111_Chasm%2002-05-25.json) for guidance. |
|
|
|
### Method III: WebUI without MIDNIGHT1111_Chasm Workflow |
|
|
|
1. **Installation:** Follow the instructions in the [WebUI repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui) to set up. |
|
|
|
2. **Navigate to the WebUI Directory:** Before updating or switching branches, ensure you're inside the `stable-diffusion-webui` folder |
|
command: | |
|
```bash |
|
cd stable-diffusion-webui |
|
``` |
|
|
|
3. **Switch to the Development Branch (Optional, for testing new features):** If you want to use the latest features from the development branch, run: |
|
command: | |
|
```bash |
|
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. |
|
|
|
4. **Update WebUI (Main or Dev Branch):** To pull the latest updates while on either branch, run: |
|
command: | |
|
```bash |
|
git pull |
|
``` |
|
🔄 **Restart WebUI after updating to apply changes.**" |
|
|
|
5. **Configuration:** Ensure you're using a stable branch, as the dev branch may contain bugs. |
|
|
|
### Method IV: Diffusers without MIDNIGHT1111_Chasm Workflow |
|
|
|
```bash |
|
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") |
|
``` |
|
|
|
## e621/Danbooru Artist Wildcards for A1111 & ComfyUI Enclosed in CSV & TXT Formats |
|
|
|
To enhance the model's performance and specificity, the following trigger word lists in CSV format are included: |
|
|
|
- [`danbooru_artist_webui.csv`](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/danbooru_artist_webui.csv) |
|
- [`danbooru_character_webui.csv`](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/danbooru_character_webui.csv) |
|
- [`e621_artist_webui.csv`](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/e621_artist_webui.csv) |
|
- [`e621_character_webui.csv`](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/e621_character_webui.csv) |
|
|
|
These lists provide recognized tags for various artists and characters, facilitating more accurate and tailored image generation. |
|
|
|
The wildcard file in 'TXT' format is included and designed for seamless integration with **AUTOMATIC1111** and **ComfyUI**, optimized for dynamic prompt generation using artist data from **e621** and **Danbooru**. |
|
|
|
- **TXT Format:** Sanitized artist tags by removing URLs and converted from `.csv` to `.txt` format for improved readability across different extensions. |
|
- **Dual Dataset Support:** Supports both e621 and Danbooru datasets to enhance art style diversity. |
|
- **Smooth Randomization:** Structured with trailing commas for seamless wildcard cycling during prompt generation. |
|
|
|
## How to Use Wildcards |
|
|
|
### For A1111 |
|
1. **Install:** [stable-diffusion-webui-wildcards](https://github.com/AUTOMATIC1111/stable-diffusion-webui-wildcards) |
|
2. **Place the `.txt` file in:** |
|
``` |
|
/A1111/extensions/stable-diffusion-webui-wildcards |
|
``` |
|
3. **Use in your prompt like this:** |
|
``` |
|
__e621_artist_wildcard__, very awa, masterpiece, best quality, amazing quality |
|
``` |
|
``` |
|
__danbooru_character_wildcard__, very awa, masterpiece, best quality, amazing quality |
|
``` |
|
``` |
|
__e621_artist_wildcard__, __danbooru_character_wildcard__, very awa, masterpiece, best quality, amazing quality |
|
``` |
|
|
|
### For ComfyUI |
|
1. **Install:** [ComfyUI-Impact-Pack](https://github.com/ltdrdata/ComfyUI-Impact-Pack) |
|
2. **Place the `.txt` file in:** |
|
``` |
|
/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/wildcards |
|
``` |
|
or |
|
``` |
|
/ComfyUI/custom_nodes/ComfyUI-Impact-Pack/custom_wildcards |
|
``` |
|
3. **Use the wildcard node to trigger dynamic randomization in your workflows.** |
|
|
|
## What’s Included in Wildcards |
|
|
|
TXT formatted file containing clean, artist-focused wildcard files ready for dynamic prompt workflows in A1111 and ComfyUI. |
|
- [danbooru_artist_wildcard.txt](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/danbooru_artist_wildcard.txt) |
|
- [danbooru_character_wildcard.txt](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/danbooru_character_wildcard.txt) |
|
- [e621_artist_wildcard.txt](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/e621_artist_wildcard.txt) |
|
- [e621_character_wildcard.txt](https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/e621_character_wildcard.txt) |
|
|
|
## Acknowledgments |
|
|
|
Special thanks to: |
|
|
|
- **Development Team:** Laxhar Lab |
|
- **Coding Contributions:** Euge |
|
- **e621/Danbooru Wildcards** [ipsylon0000](https://civitai.com/user/ipsylon0000) |
|
- **Community Support:** Various contributors |
|
|
|
## Additional Resources |
|
|
|
- **Guidebook for NoobAI XL:** [English Version](https://civitai.com/articles/8962) |
|
- **Recommended LoRa List for NoobAI XL:** [Resource Link](https://fcnk27d6mpa5.feishu.cn/wiki/IBVGwvVGViazLYkMgVEcvbklnge) |
|
- **Fixing Black Images in ComfyUI on macOS (M1/M2):** [Read the Article](https://civitai.com/articles/11106) |
|
- **Creative Solutions and Services:** [Magnabos.co](https://magnabos.co/) |
|
|
|
## License |
|
|
|
This model is licensed under the [CreativeML Open RAIL++-M License](https://github.com/CompVis/stable-diffusion/blob/main/LICENSE). By using this model, you agree to the terms and conditions outlined in the license. |
