<h2 id="checkpoint-midnight_nai-xl_vpred">Checkpoint // MIDNIGHT_NAI-XL_vPred</h2>MIDNIGHT_NAI-XL_vPred (MDNT_NAI-XL_vPred as the shorthand alternative) is a specialized fine-tuning of the NoobAI-XL (NAI-XL) model, designed to enhance anatomical precision, compositional coherence, and versatile style integration.<h3 id="usage-recommendations">Usage Recommendations</h3>// VAE: To achieve optimal results with MIDNIGHT_NAI-XL_vPred, it's essential to load the appropriate Variational Autoencoder (VAE). This model is intentionally provided without a baked-in VAE to offer advanced users greater flexibility. Ensure that the sdxl_vae is correctly loaded to maximize compatibility. You can find the SDXL_VAE at <a target="_blank" rel="ugc" href="https://civarchive.com/models/296576/sdxl-vae">Civitai</a> or <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sdxl-vae/tree/main">Hugging Face</a>. Otherwise, use MDNT_NAI-XL_vPredV1_VAE, which has the VAE already baked in, eliminating the need for separate VAE loaders. No baked-in VAE for V2.// Sampling Methods: MIDNIGHT_NAI-XL_vPred 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.// Custom Workflow for comfyUI users: For an optimized generation process, consider using the custom workflow <a target="_blank" rel="ugc" href="https://civarchive.com/models/1209891/midnight1111chasm-workflow">MIDNIGHT1111_Chasm 2025-02-05</a>, which is also available on <a target="_blank" rel="ugc" href="https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/MIDNIGHT1111_Chasm%2002-05-25.json">huggingface.co. </a>This workflow is tailored to leverage the strengths of the NAI-XL_vPred model, providing a streamlined and efficient image generation pipeline.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6e0e4817-ecec-4a93-93dc-3faa28835d61/width=525/6e0e4817-ecec-4a93-93dc-3faa28835d61.jpeg" /> Note: The above image is a preview of the <code>MIDNIGHT1111_Chasm</code> workflow.CFG Scaling: Dynamic CFG Plugin is bypassed as a backup for potential future needs.Manually adjust CFG scaling within a range of 3-4 for the best balance. For optimal results, a preferred setting of 3.5 is recommended.<h3 id="trigger-word-lists">Trigger Word Lists</h3>To enhance the model's performance and specificity, the following trigger word lists are included:- <a target="_blank" rel="ugc" href="https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV1/blob/main/danbooru_artist_webui.csv">danbooru_artist_webui.csv</a>- <a target="_blank" rel="ugc" href="https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV1/blob/main/danbooru_character_webui.csv">danbooru_character_webui.csv</a>- <a target="_blank" rel="ugc" href="https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV1/blob/main/e621_artist_webui.csv">e621_artist_webui.csv</a>- <a target="_blank" rel="ugc" href="https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV1/blob/main/e621_character_webui.csv">e621_character_webui.csv</a>These lists provide recognized tags for various artists and characters, facilitating more accurate and tailored image generation. Those can be also found <a target="_blank" rel="ugc" href="https://civarchive.com/models/952156/noobai-xl-nai-xl-artist-wildcards-e621danbooru">noobai-xl-nai-xl-artist-wildcards-e621danbooru</a><h3 id="how-to-use">How to Use</h3>// Method I: reForge1. Installation: If not already installed, follow the instructions in the <a target="_blank" rel="ugc" href="https://github.com/Panchovix/stable-diffusion-webui-reForge">reForge repository</a> to set up.2. Usage: Launch WebUI and use the model as usual.// Method II: ComfyUI1. Installation: Follow the setup instructions in the <a target="_blank" rel="ugc" href="https://github.com/comfyanonymous/ComfyUI">ComfyUI repository</a>.2. Workflow Sample: Utilize the provided <a target="_blank" rel="ugc" href="https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2/blob/main/MIDNIGHT1111_Chasm%2002-05-25.json">ComfyUI workflow sample</a> for guidance.// Method III: WebUI1. Installation: Follow the setup instructions in the <a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">WebUI repository</a>.2. Navigate to the WebUI Directory: Before updating or switching branches, ensure you're inside the <code>stable-diffusion-webui</code> foldercommand:<pre><code>cd stable-diffusion-webui</code></pre>3. Switch to the Development Branch: If you want to use the latest features from the development branch, run:command:<pre><code>git switch dev</code></pre><pre><code>git pull</code></pre>⚠️ Note: The <code>dev</code> branch may contain bugs. If stability is your priority, it's best to stay on the <code>main</code> branch.4. Update WebUI (Main or Dev Branch): To pull the latest updates while on either branch, run:command:<pre><code>git pull</code></pre>🔄 Restart WebUI after updating to apply changes.5. Configuration: Ensure you're using a stable branch, as the dev branch may contain bugs.// AcknowledgmentsSpecial thanks to:<ul><li>Development Team: Laxhar Lab</li><li>Coding Contributions: Euge</li><li>Community Support: Various contributors</li></ul>// Additional Resources<ul><li>Guidebook for NoobAI XL: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/8962">English Version</a></li><li>Recommended LoRa List for NoobAI XL: <a target="_blank" rel="ugc" href="https://fcnk27d6mpa5.feishu.cn/wiki/IBVGwvVGViazLYkMgVEcvbklnge">Resource Link</a></li></ul>// LicenseThis model is licensed under the <a target="_blank" rel="ugc" href="https://github.com/CompVis/stable-diffusion/blob/main/LICENSE">CreativeML Open RAIL++-M License</a>. By using this model, you agree to the terms and conditions outlined in the license. // Changelog2025-02-07: Added VAE Baked-In Version:For those who prefer a version with the VAE baked in, it is available MDNT_NAI-XL_vPredV1_VAE.<hr /><h3 id="availability-on-hugging-face">Availability on Hugging Face</h3>This model is also available on Hugging Face for ease of access, packaged files, and verification of its original source: 🔗 <a target="_blank" rel="ugc" href="https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV1">Hugging Face - MidnightRunner/MIDNIGHT_NAI-XL_vPredV1</a>🔗 <a target="_blank" rel="ugc" href="https://huggingface.co/MidnightRunner/MIDNIGHT_NAI-XL_vPredV2">Hugging Face - MidnightRunner/MIDNIGHT_NAI-XL_vPredV2</a><hr />Created by <a target="_blank" rel="ugc" href="http://Magnabos.co">Magnabos.co</a> | Creative Artist 2025 © Midnight1111

MDNT_NAI-XL_vPred

Fine-tuned SDXL-based model utilizing the V-Prediction architecture, now available with a baked-in VAE.

Files with SHA256: 0845d1531af35d47780ddaf396d46929a28da5d77ba66ff426e8b4dc2552c823