Update README.md

README.md

@@ -41,7 +41,7 @@ Three encoders tested against the same pipeline:
 | `bert_vae/` | bert-base-uncased | 768 | [CLS] token | bidirectional MLM |
 | `beatrix_vae/` | bert-beatrix-2048 | 768 | mean pool | nomic_bert + categorical tokens |
 
-Each VAE has identical architecture: `encoder (text_dim → 1024 → 1024) → μ,σ (256d bottleneck) → decoder (256 → 1024 → 1024 → 2048) → reshape (8, 16, 16)`. Trained to reconstruct adapted FLUX VAE latents from paired prompts. ~4.5M parameters each.
+Each VAE has identical architecture: `encoder (text_dim → 1024 → 1024) → μ,σ (256d bottleneck) → decoder (256 → 1024 → 1024 → 2048) → reshape (8, 16, 16)`. Trained to reconstruct identical-scale as the adapted FLUX VAE latents from the earlier Image VAE experiments. ~4.5M parameters each.
 
 The geometric analyzer is a pretrained `SuperpositionPatchClassifier` from [AbstractPhil/grid-geometric-multishape](https://huggingface.co/AbstractPhil/grid-geometric-multishape) (epoch 200), frozen during evaluation. It extracts gate vectors (64×17 explicit geometric properties) and patch features (64×256 learned representations) from any (8, 16, 16) input.