1.6b

README.md

@@ -5,7 +5,7 @@ datasets:
 - CaptionEmporium/midjourney-niji-1m-llavanext
 ---
 
-# Simple Diffusion XS
+# Simple Diffusion XS (train in progress)
 
 *XS Size, Excess Quality*
 ![promo](media/girl.jpg)
@@ -19,9 +19,7 @@ At AiArtLab, we strive to create a free, compact and fast model that can be trai
 - Resolution:  from 768px to 1404px, with step 64px
 - Limitations: trained on small dataset ~1-2kk, focused on illustrations
 
-### Train in progress
-
-Key points
+### Key points
 
  - Dec 24: Started research on Linear Transformers.
  - Feb 25: Started research on UNet-based diffusion models.
@@ -147,7 +145,7 @@ As a result, I focused on building a strong local benchmark for rapid, cost-effe
 ## The Evolutionary Path
 The second turning point was the transition to a continuous evolutionary improvement strategy. Unfortunately, the Butterflies dataset does not allow for evaluating prompt-following or anatomical generation capabilities. As a result, the model evolved incrementally rather than through revolutionary changes. The same model, from December 2025, underwent around 10 changes, including radical architectural shifts—while always preserving the pre-trained weights. It’s remarkable how well and quickly pre-trained models adapt to changes in architecture and external factors, even radical ones (e.g., switching VAE models, text encoders, or their combinations).
 In addition to saving on training costs, this approach helped maintain minimal model size—for example, adding extra transformer blocks followed by an assessment of necessity and rolling back if the changes had no significant impact.
-## tldr;
+## tldr; Main idea
 Stop reading, start training
 ## The Role of Hyperparameters
 One of the initial mistakes was an excessive focus on hyperparameters during training. Ironically, 80% of training speed and quality depend on the model architecture (UNet) and the quality of embeddings (VAE), while other 20% is influenced by the text encoder’s embeddings. The rest is Role of Hyperparameters. The irony here is that Adam (adamw8bit) is surprisingly forgiving of hyperparameter errors, so I won’t even list them. Default is ok.
@@ -158,7 +156,7 @@ A dataset script to convert a folder of image-text pairs into latent representat
 A training script provided as a single monolithic file.
 Additionally, there’s a script that can be pasted directly into the terminal to automatically train the model with optimized parameters.
 ## Training Optimization
-All pre-training was done using the AdamW8bit optimizer, which significantly reduced training costs. 
+All training was done using the AdamW8bit optimizer, which significantly reduced training costs. 
 
 ### Train:
 

test.ipynb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266e739c156b3e1d25b4c49491ab1aa69cb7ae3c68ce7099d36da0008804a3f1
-size 12848775
+oid sha256:d8a1f50bb6e009d6f8efb6184fd51b66f0f55b213294c796a7bd0d5df703f65a
+size 18316400

unet/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17892431f616faa8ac069a94089992b74080248e7e4c2476d88c9fe31e09174f
+oid sha256:61a1cf70b3652cf3f179005e6703b6881a3489d36c6a6b5254741d047d885c6b
 size 3210307232