Rename to MiniMax-H3 Reference; describe the tab order and image slots

README.md

@@ -1,5 +1,5 @@
 ---
-title: MiniMax-H3 references (split, bf16)
+title: MiniMax-H3 Reference
 emoji: 🎭
 colorFrom: pink
 colorTo: purple
@@ -7,7 +7,7 @@ sdk: gradio
 sdk_version: 6.20.0
 app_file: app.py
 pinned: false
-short_description: Unquantized MiniMax-H3 ref2va with AoTI blocks, split in two
+short_description: Unquantized MiniMax-H3 from image, audio, video refs
 suggested_hardware: zero-a10g
 ---
 
@@ -39,10 +39,11 @@ fit unquantized:
 A request carries up to **12** references — at most 9 images, 3 videos and 3 audio clips — **in the order the model
 reads them**. The order is semantic: it numbers the labels of MiniMax-H3's prompt presentation (`<Picture 1>`,
 `<Video 1>`, `<Audio 1>`) and it advances the shared audio/video rotary clock, so the same references in a different
-order are a different request. This demo exposes the first four slots as one tab per modality — one video, two
-images, one audio clip — and the tabs are laid out in reading order, so it assembles them video, images, audio. A
-reference left in a tab that is not the open one is still part of the request; the tabs lay the slots out, they do
-not choose between them.
+order are a different request. This demo lays the slots out as one tab per modality in reading order — images, then
+audio, then video — and assembles the request that way. The Images tab opens with two slots and **+ Add another
+image** reveals the rest, up to the model's own nine; the audio and video tabs hold one each. A reference left in a
+tab that is not the open one is still part of the request; the tabs lay the slots out, they do not choose between
+them.
 
 Rules the model imposes, enforced here before anything is uploaded: