Update README.md

README.md

@@ -2,7 +2,7 @@
 license: creativeml-openrail-m
 language:
   - en
-thumbnail: 
+thumbnail: "https://huggingface.co/ai-characters/DarkAndDarker-Style-SDXL/resolve/main/ComfyUI_04231_.png"
 pipeline_tag: text-to-image
 tags:
   - stablediffusion
@@ -15,70 +15,70 @@ tags:
   - characters
 ---
 
-![model cover]()
+![model cover](https://huggingface.co/ai-characters/DarkAndDarker-Style-SDXL/resolve/main/ComfyUI_04231_.png)
 
-An SDXL 1.0 LoRa made by AI_Characters based on the official artwork for the "fantasy extraction shooter" game Dark and Darker by Ironmace, which can be found here.
+An SDXL 1.0 LoRa made by AI_Characters based on the official artwork for the "fantasy extraction shooter" game Dark and Darker by Ironmace, which can be found [here](https://www.ironmace.com/).
 
-Usage recommendations:
+**Usage recommendations**
 
-Weight: 1.0 (may need to be adjusted down when using in conjunction with other LoRa's) Model: SDXL 1.0 with 0.9 vae Generation parameters: 35 steps | DPM++ 2M Karras | CFG 7 Negative prompt: text, watermark, low-quality, signature, moiré pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast with only the "G" text encoder enabled (see my article here for how to do that)
+- Weight: **1.0** *(may need to be adjusted down when using in conjunction with other LoRa's)* 
 
-Trigger words
+- Model: **[SDXL 1.0 with 0.9 vae](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors)** 
 
-"artwork in imst artstyle"
+- Generation parameters: **35 steps | DPM++ 2M Karras | CFG 7** 
 
-Changelog
+- Negative prompt: text, watermark, low-quality, signature, moiré pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast with only the "G" text encoder enabled *(see my article [here](https://civitai.com/articles/2141) for how to do that)*
 
-v2.0
+**Trigger words**
 
-Complete revision - trained with a much lower learning rate but more epochs, leading to increased likeness, flexibility, and variety; added 12 official artworks of the various ingame classes which no longer exist ingame
+- "artwork in imst artstyle"
 
-v1.0
+**Samples**
 
-Initial release
+For the generation data of these samples such as prompts and sampler settings please see the samples on the model's page on CivitAI [here(https://civitai.com/models/139182?modelVersionId=159232)]!
 
-Additional Info
+![sample1](https://huggingface.co/ai-characters/DarkAndDarker-Style-SDXL/resolve/main/ComfyUI_04231_.png)
 
-Credit is not mandatory but I would still appreciate credit when posting images using these LoRa's on social media! Feel free to @ my Twitter and/or Instagram accounts too (@ai_characters)! I would love to know when it is used!
+![sample2](https://huggingface.co/ai-characters/DarkAndDarker-Style-SDXL/resolve/main/ComfyUI_04234_.png)
 
-I share all of my model's and training knowledge for free, but donations to my Ko-Fi would be greatly appreciated! Testing so much and training so many model's costs a lot of money (and time).
+![sample3](https://huggingface.co/ai-characters/DarkAndDarker-Style-SDXL/resolve/main/ComfyUI_04236_.png)
 
-Feel free to also try out my RVC2 AI voice models which you can find here!
+![sample4](https://huggingface.co/ai-characters/DarkAndDarker-Style-SDXL/resolve/main/ComfyUI_04237_.png)
 
-See here for an extensive article about my entire training workflow and configuration if you want to train your own SDXL 1.0 LoRa's and achieve results similar as me!
+![sample5](https://huggingface.co/ai-characters/DarkAndDarker-Style-SDXL/resolve/main/ComfyUI_04238_.png)
 
-Stats (v2.0)
+**Changelog**
 
-Dataset:
+- v2.0
 
-26x artworks
+  - Complete revision - trained with a much lower learning rate but more epochs, leading to increased likeness, flexibility, and variety; added 12 official artworks of the various ingame classes which no longer exist ingame
 
-Epoch chosen for the final model:
+- v1.0
 
-50
+  - Initial release
 
-Learning rate:
+**Additional Info**
 
-3e-6
+Credit is not mandatory but I would still appreciate credit when posting images using these LoRa's on social media! Feel free to @ my Twitter and/or Instagram accounts too (@ai_characters)! I would love to know when it is used!
 
-For more info - including the training configuration used - see the article linked at the end of the "Additional Info" section.
+I share all of my model's and training knowledge for free, but **donations to my [Ko-Fi](https://ko-fi.com/aicharacters)** would be greatly appreciated! Testing so much and training so many model's costs a lot of money (and time).
 
-**Samples**
+Feel free to also try out my RVC2 AI voice models which you can find [here](https://huggingface.co/ai-characters/AI-Voice-Models-by-AI_Characters)!
 
-For the generation data of these samples such as prompts and sampler settings please see the samples on the model's page on CivitAI [here(https://civitai.com/models/139182?modelVersionId=159232)]!
+See **[here](https://civitai.com/articles/1771)** for an extensive article about my entire **training workflow** and configuration if you want to train your own SDXL 1.0 LoRa's and achieve results similar as me!
 
-![sample1]()
+**Stats (v2.0)**
 
-![sample2]()
+Dataset:
 
-![sample3]()
+- 26x artworks
 
-![sample4]()
+Epoch chosen for the final model:
 
-![sample5]()
+- 50
 
-![sample6]()
+Learning rate:
 
-![sample7]()
+- 3e-6
 
-![sample8]()
+*For more info - including the training configuration used - see the article linked at the end of the "Additional Info" section.*