readme

README.md

@@ -7,20 +7,40 @@ pipeline_tag: text-to-image
 
 *XS Size, Excess Quality*
 
-At AiArtLab, we strive to create a compact (1.7b) and fast (3 sec/image) model that can be trained on consumer graphics cards with a limited budget.
+At AiArtLab, we strive to create a free, compact (1.7b) and fast (3 sec/image) model that can be trained on consumer graphics cards.
 
-- We use U-Net for its ability to efficiently handle small datasets and train quickly on GPUs with 16GB of memory.
-- We have chosen the multilingual/multimodal encoder Mexma-SigLIP, which supports 80 languages and processes sentences rather than individual tokens.
-- We use the AuraDiffusion 16ch-VAE architecture, which preserves details and anatomy without the "haze" effect.
-- For training, we have chosen AdamW-8bit, which allows for larger batch sizes and accelerates training on low-cost GPUs.
-- The model was trained on approximately 1 million images with various resolutions and styles, including anime and realistic photos.
-- Various annotation methods were used, including both manual and automated approaches.
+- We use U-Net for its high efficiency.
+- We have chosen the multilingual/multimodal encoder Mexma-SigLIP, which supports 80 languages.
+- We use the AuraDiffusion 16ch-VAE architecture, which preserves details and anatomy.
+- The model was trained (~1 month on 4xA5000) on approximately 1 million images with various resolutions and styles, including anime and realistic photos.
 
 ### Model Limitations:
 - Limited concept coverage due to the small dataset.
 - The Image2Image functionality requires further training.
 
+## Acknowledgments
+- **[Stan](https://t.me/Stangle)** — Key investor. Thank you for believing in us when others called it madness.
+- **Captainsaturnus**
+- **Love. Death. Transformers.**
+
+## Datasets
+- **[CaptionEmporium](https://huggingface.co/CaptionEmporium)**
+
+## Training budget
+
+Around ~$1k for now, but research budget ~$10k
+
+## Donations
+
+Please contact with us if you may provide some GPU's or money on training
+
+DOGE: DEw2DR8C7BnF8GgcrfTzUjSnGkuMeJhg83
+
+BTC: 3JHv9Hb8kEW8zMAccdgCdZGfrHeMhH1rpN
+
+## Contacts
 
+[recoilme](https://t.me/recoilme)
 
 Train status, in progress: [wandb](https://wandb.ai/recoilme/unet)
 
@@ -138,29 +158,4 @@ if __name__ == "__main__":
         image.save(f"{output_folder}/{project_name}_{idx}.jpg")
 
     print("Images generated and saved to:", output_folder)
-```
-
-## Acknowledgments
-- **[Stan](https://t.me/Stangle)** — Key investor. Primary financial support - thank you for believing in us when others called it madness.
-- **Captainsaturnus** — Material support.
-- **Love. Death. Transformers.** — Material support.
-- **Lovescape** & **Whargarbl** — Moral support.
-- **[CaptionEmporium](https://huggingface.co/CaptionEmporium)** — Datasets.
-
-> "We believe the future lies in efficient, compact models. We are grateful for the donations and hope for your continued support."
-
-## Training budget
-
-Around ~$1k for now, research budget ~$10k
-
-## Donations
-
-Please contact with us if you may provide some GPU's or money on training
-
-DOGE: DEw2DR8C7BnF8GgcrfTzUjSnGkuMeJhg83
-
-BTC: 3JHv9Hb8kEW8zMAccdgCdZGfrHeMhH1rpN
-
-## Contacts
-
-[recoilme](https://t.me/recoilme)
+```