Update README.md

README.md

@@ -9,33 +9,31 @@ license: creativeml-openrail-m
 ---
 
 
-# SD_Anime_Futuristic_Armor_Model is an open source Stable Diffusion Model on art style of futuristic armor, by Akumetsu971 (https://www.tiktok.com/@akumetsu971)
+# SD_Black_Ancient_Egyptian_Style is an open source Stable Diffusion embedding and model on art style of black Ancient Egypt, by Akumetsu971 (https://www.tiktok.com/@akumetsu971)
 ---
 
 ### What for ?: 
 
-Robot, Android, Mecha, futuristic armor, wepons, etc...
+Men, Women, Animals, Egyptian Gods, Egypt backgrounds, 
 
 ### Model used to train: 
 
-DreamBooth based on Elysium_Anime_V2.ckpt (https://gigazine.net/gsc_news/en/20221012-automatic1111-stable-diffusion-webui-deep-danbooru/)
+DreamBooth based on SD v2-1_512-ema-pruned.ckpt
 
-### Files 
-4 files available :
+Embedding based on SD v2-1_512-ema-pruned.ckpt
 
--JhnsT3_step_4000.ckpt - 4000 steps (recommanded, last version I trained on Dreambooth)
+### Files 
+2 files available :
 
--JhnsT3_step_4000_0.8-arcane-diffusion-v3_0.2-Weighted_sum-merged.ckpt - 4000 steps (mixed with an Arcane Diffusion model)
+-EMB_Blck_Egpt.zip (Best embedding version is around 1000 steps)
 
--JhsnT_Style4_step_5000.ckpt - 5000 steps(really good also, train with different images)
+- (model in development)
 
--JhsnT_Style4_step_5000_0.8-arcane-diffusion-v3_0.2-Weighted_sum-merged (mixed with an Arcane Diffusion model)
+- Blck_Egpt_DataSet (if you want to train your own model)
 
 ### Prompt 
 
-You need to use DeepDanBooru Tags (https://gigazine.net/gsc_news/en/20221012-automatic1111-stable-diffusion-webui-deep-danbooru/) 
-
-I also used Nixeu_style embedding (not necessary): https://huggingface.co/sd-concepts-library/nixeu)
+Keyword for model is Bck_Egpt
 
 If the image is blurry, use an upscaller like: 4x_fatal_Anime_500000_G, 4x-AnimeSharp, 4x_NMKD-Siax_200k (they are all in my files)