Downloads · 30 days
0
Maestro-Models
Blizaine/Maestro-Models
Maestro-Models is a text-to-audio model from Blizaine. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. It is set up for acestep. The card lists the license as mit.
Consolidated model weights hosted for Maestro, a local AI video, image, and music studio.
Access
Public
Updated Jul 15, 2026
Repo size
15.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.5 GB · 100%
At a glance
- Task
- Text-to-Audio
- Library
- acestep
- License
- mit
- Access
- Public
- Created
- Jul 14, 2026
- Updated
- Jul 15, 2026
- SHA
- 5dbbf111
Model card
From the Hugging Face model README
Maestro Models
Consolidated model weights hosted for Maestro, a local AI video, image, and music studio.
Files
ace_step_v1_5_xl_sft_transformer_bf16.safetensors
The ACE-Step v1.5 XL SFT diffusion transformer, consolidated from the original four fp32 shards into a single bf16 safetensors file (tensor names unchanged) for single-file loaders such as Maestro / Wan2GP.
- Source: ACE-Step/acestep-v15-xl-sft
- License: MIT (same as the source model)
- Conversion: fp32 to bf16 cast, shard merge only. No fine-tuning or other modification.
All credit for the model goes to the ACE-Step team.
- Task
- Text-to-Audio
- Library
- acestep
- License
- mit
- Created
- Jul 14, 2026
- Updated
- Jul 15, 2026