Update README.md

README.md

@@ -20,31 +20,31 @@ metrics:
   - IS
 widget:
   - text: >-
-      high quality, masterpiece, detailed, 8K, artist:laxhar , futuristic cityscape at night, towering skyscrapers with glowing neon signs, rain-soaked streets reflecting vibrant colors, lone figure in a sleek black coat walking under a glowing umbrella, dynamic pose, wind-swept hair, cinematic lighting, cool blue and purple tones, hyper-detailed, sharp focus, film grain, chromatic aberration, gritty texture, limited palette, high contrast
+      high quality, masterpiece, detailed, 8K, artist:laxhar, futuristic cityscape at night, towering skyscrapers with glowing neon signs, rain-soaked streets reflecting vibrant colors, lone figure in a sleek black coat walking under a glowing umbrella, dynamic pose, wind-swept hair, cinematic lighting, cool blue and purple tones, hyper-detailed, sharp focus, film grain, chromatic aberration, gritty texture, limited palette, high contrast
     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
+      url: stand_on_ripplewater.png
 ---
 
 # MIDNIGHT_NAI-XL_vPredV1
 
 **Model Type:** Diffusion-based text-to-image generative model
 
-**Base Model:** SDXL 1.0/Laxhar/noobai-XL-Vpred-1.0
+**Base Model:** SDXL 1.0
 
 **License:** [CreativeML Open RAIL++-M](https://github.com/CompVis/stable-diffusion/blob/main/LICENSE)
 
 ## Model Description
 
-MIDNIGHT_NAI-XL_vPredV1 is a fine-tuned version of the NoobAI-XL (NAI-XL) model, optimized for enhanced anatomical accuracy, compositional rationality, and flexible style combinations. This model is designed to generate high-quality images with vibrant colors while minimizing overexposure.
+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.
 
 ## Key Features
 
-- **High-Quality Fine-Tuning:** Utilizes meticulously curated datasets to improve anatomical precision and composition.
-- **Flexible Style Combinations:** Offers robust performance when overlaying multiple artistic styles.
-- **Enhanced Quality Keywords:** Increased effectiveness of quality-related prompts.
+- **Enhanced Fine-Tuning:** Utilizes carefully curated datasets to improve anatomical accuracy and composition.
+- **Versatile Style Integration:** Performs robustly when combining multiple artistic styles.
+- **Optimized Quality Keywords:** Increases the effectiveness of quality-related prompts.
 - **Balanced Color Output:** Produces vibrant images with reduced risk of overexposure.
 
 ## Usage Recommendations
@@ -52,6 +52,25 @@ MIDNIGHT_NAI-XL_vPredV1 is a fine-tuned version of the NoobAI-XL (NAI-XL) model,
 - **Dynamic CFG Plugin:** To prevent oversaturation or dull images, it's recommended to use the Dynamic CFG & CFG Rescale plugin with a configuration setting around 0.2.
 - **Sampling Methods:** While compatible with most sampling methods, V-prediction models do not support the Karras series. For optimal results, use Euler or DDIM sampling methods.
 
+## Custom Workflow: MIDNIGHT1111_Chasm
+
+For an optimized generation process, consider using the custom workflow `MIDNIGHT1111_Chasm 2025-02-02.json`. This workflow is tailored to leverage the strengths of the MIDNIGHT_NAI-XL_vPredV1 model, providing a streamlined and efficient image generation pipeline.
+
+![MIDNIGHT1111_Chasm Workflow](MIDNIGHT1111_Chasm Workflow.png)
+
+*Note: The above image is a preview of the `MIDNIGHT1111_Chasm` workflow.*
+
+## Trigger Word Lists
+
+To enhance the model's performance and specificity, trigger word lists are included in the files:
+
+- `danbooru_artist_webui.csv`
+- `danbooru_character_webui.csv`
+- `e621_artist_webui.csv`
+- `e621_character_webui.csv`
+
+These lists provide recognized tags for various artists and characters, facilitating more accurate and tailored image generation.
+
 ## How to Use
 
 ### Method I: reForge