Update README.md

README.md

@@ -14,7 +14,7 @@ tags:
 
 So far, this release is an experiment on MiniMax H3 base model that combines learned patterns from two other video diffusion models — LTX 2.3 and Wan 2.2, and in test3 and later, one image diffusion model — Krea 2 — into H3's transformer architecture. 
 
-H3's transformer is organized into 50 blocks, each containing self-attention and feed-forward layers that process video, audio, and text together in a single unified stream. This work modified those attention and feed-forward layers in specific blocks, blending in the corresponding weights from LTX 2.3, Wan 2.2, and Krea 2. Nothing outside those layers was touched — H3's input processing, output projections, timestep modulation, and all the machinery that decides how to route different modalities remained fully intact and original.
+A unified transformer with modality-specific input projectors (video, audio, condition) feeding into a 52-block transformer stack (2-block token_refiner for text conditioning plus 50 main blocks), with modality-specific output heads. The transformer stack uses identical block architecture throughout, which is what makes the attention and MLP layers architecturally-appropriate targets for character transfer between models — modality routing lives at the pipeline edges, not within the transformer
 
 The LTX pass was applied first to H3's front blocks, followed by a Wan pass targeting H3's middle-to-back blocks. Each pass modified attention weights directly; the second pass also modified the feed-forward layers in a broader block range. Together, these two video-donor passes demonstrated that completely different video model architectures could each contribute their own recognizable character into H3.