Added changelog and guideline

README.md

@@ -38,6 +38,18 @@ base_model:
 ## Overview
 
 **Animagine XL 4.0**, also stylized as **Anim4gine**, is the ultimate anime-themed finetuned SDXL model and the latest installment of [Animagine XL series](https://huggingface.co/collections/Linaqruf/animagine-xl-669888c0add5adaf09754aca). Despite being a continuation, the model was retrained from [Stable Diffusion XL 1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) with a massive dataset of 8.4M diverse anime-style images from various sources with the knowledge cut-off of January 7th 2025 and finetuned for approximately 2650 GPU hours. Similar to the previous version, this model was trained using tag ordering method for the identity and style training.
+With the release of **Animagine XL 4.0 Opt (Optimized)**, the model has been further refined with an additional dataset, improving **stability**, **anatomy accuracy**, **noise reduction**, **color saturation**, and **overall color accuracy**. These enhancements make **Animagine XL 4.0 Opt** more consistent and visually appealing while maintaining the signature quality of the series.
+
+
+## Changelog
+- 2025-02-13 – Added Animagine XL 4.0 Opt
+  - Better stability for more consistent outputs
+  - Enhanced anatomy with more accurate proportions
+  - Reduced noise and artifacts in generations
+  - Fixed low saturation issues, resulting in richer colors
+  - Improved color accuracy for more visually appealing results
+- 2025-01-24 – Initial release
+
 
 ## Model Details
 
@@ -85,8 +97,8 @@ image = pipe(
     negative_prompt=negative_prompt,
     width=832,
     height=1216,
-    guidance_scale=6,
-    num_inference_steps=25
+    guidance_scale=5,
+    num_inference_steps=28
 ).images[0]
 
 image.save("./arima_kana.png")
@@ -94,15 +106,19 @@ image.save("./arima_kana.png")
 
 ## Usage Guidelines
 
+The summary can be seen in the image for the prompt guideline.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c088660a4d02f37a965f6c/YPe3MCnQAHM7nCZ1vQ7vI.png)
+
 ### 1. Prompt Structure
 The model was trained with tag-based captions and the tag-ordering method. Use this structured template:
 
 ```
-1girl/1boy/1other, character name, from which series, everything else in any order.
+1girl/1boy/1other, character name, from which series, rating, everything else in any order and end with quality enhancement
 ```
 
 ### 2. Quality Enhancement Tags
-Add these tags at the start or end of your prompt:
+Add these tags at the end of your prompt:
 
 ```
 masterpiece, high score, great score, absurdres
@@ -114,8 +130,8 @@ lowres, bad anatomy, bad hands, text, error, missing finger, extra digits, fewer
 ```
 
 ### 4. Optimal Settings
-- **CFG Scale**: 5-7 (6 Recommended)
-- **Sampling Steps**: 25-28 (25 Recommended)
+- **CFG Scale**: 4-7 (5 Recommended)
+- **Sampling Steps**: 25-28 (28 Recommended)
 - **Preferred Sampler**: Euler Ancestral (Euler a)
 
 ### 5. Recommended Resolutions
@@ -134,7 +150,7 @@ lowres, bad anatomy, bad hands, text, error, missing finger, extra digits, fewer
 
 ### 6. Final Prompt Structure Example
 ```
-masterpiece, high score, great score, absurdres, 1girl, firefly \(honkai: star rail\), honkai \(series\), honkai: star rail, casual, solo, looking at viewer, outdoors, smile, reaching towards viewer, night
+1girl, firefly \(honkai: star rail\), honkai \(series\), honkai: star rail, safe, casual, solo, looking at viewer, outdoors, smile, reaching towards viewer, night, masterpiece, high score, great score, absurdres
 ```
 
 ## Special Tags
@@ -236,13 +252,13 @@ We extend our heartfelt appreciation to our dedicated team members who have cont
 - [**Fiqi**](https://huggingface.co/saikanov)
 - [**William Adams Soeherman**](https://huggingface.co/williamsoeherman)
 
-## Fundraising  Are Now Open Again!
+## Fundraising Has New Methods!
 
-We’re excited to reopen Fundraising to fund new training, research, and model development. Your support helps us push the boundaries of what’s possible with AI.
+We're excited to introduce new fundraising methods through GitHub Sponsors to support training, research, and model development. Your support helps us push the boundaries of what's possible with AI.
 
 **You can help us with:**
 
-* **Donate**: Contribute via ETH or USDT to the address below.
+* **Donate**: Contribute via ETH, USDT, or USDC to the address below, or sponsor us on GitHub.
 
 * **Share**: Spread the word about our models and share your creations!
 
@@ -252,6 +268,8 @@ We’re excited to reopen Fundraising to fund new training, research, and model
 
 ETH/USDT/USDC(e): ```0xd8A1dA94BA7E6feCe8CfEacc1327f498fCcBFC0C```
 
+**Github Sponsor**: [https://github.com/sponsors/cagliostrolab/](https://github.com/sponsors/cagliostrolab/)
+
 
 <details>
 <summary>Why do we use Cryptocurrency?</summary>