Load weights from MiniMaxAI/MiniMax-Music3 (#1)

- Load weights from MiniMaxAI/MiniMax-Music3 (5272e579dbcc4b947e9021bbf13c10c28cfa8ab0)
- Rebase on main (theme-aware logo), keep only the MiniMaxAI/MiniMax-Music3 swap (bc8fe79830f9f35182f9f2cdbda38953219cd761)
- Rebuild on current main (57e8935): keep only the MiniMaxAI/MiniMax-Music3 swap (30702c273ba7eb4d5152157d91f2f1f5178a4182)

README.md

@@ -17,7 +17,7 @@ The input surface is a single Suno-inspired custom `gr.HTML` composer (Simple
 chips, structured-caption fields per the official prompting guide) that drives Gradio events via
 `trigger()`/`props.value`; styling uses only theme CSS vars so it follows the Citrus theme natively.
 
-- Weights: `diffusers-internal-dev/MiniMax-Music3-Diffusers` (private)
+- Weights: `MiniMaxAI/MiniMax-Music3`
 - AoTI kernels: `diffusers-internal-dev/MiniMax-Music3-aoti` (compiled on RTX Pro 6000, matching ZeroGPU hardware)
 - Generation streams chunk by chunk with a configurable playback headroom. The 8B language-model stage runs eager
   on ZeroGPU (its JIT StaticCache ladder needs a persistent process); AoTI-exporting the LM decode step per cache

app.py

@@ -14,7 +14,7 @@ from huggingface_hub import snapshot_download
 from diffusers import ModularPipeline
 from diffusers.models.modeling_outputs import Transformer2DModelOutput
 
-PIPE = ModularPipeline.from_pretrained("diffusers-internal-dev/MiniMax-Music3-Diffusers")
+PIPE = ModularPipeline.from_pretrained("MiniMaxAI/MiniMax-Music3")
 PIPE.load_components(dtype=torch.bfloat16)
 PIPE.to("cuda")