Downloads · 30 days
0
ace-step-cs-tempo-r16-all
lukasz-staniszewski/ace-step-cs-tempo-r16-all
ace-step-cs-tempo-r16-all is a machine learning model from lukasz-staniszewski. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Concept Sliders LoRA for steering tempo in ACE-Step, trained at LoRA rank 16 on all 24 transformer blocks (lr=1e-4, eta=7, 500 iterations, 100 prompts). Rank selected per concept on a held-out prompt set (see the benc…
Access
Public
Updated Aug 31, 2026
Repo size
47.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors47.3 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 31, 2026
- Updated
- Aug 31, 2026
- SHA
- fb0f0c48
Model card
From the Hugging Face model README
ACE-Step Concept Slider — tempo (r=16, all)
Concept Sliders LoRA for steering tempo in ACE-Step, trained at LoRA rank 16 on all 24 transformer blocks (lr=1e-4, eta=7, 500 iterations, 100 prompts). Rank selected per concept on a held-out prompt set (see the benchmark paper). Part of the ACE-Step Audio Steering Suite.
from src.steering import ConceptSlidersSteeringController
ctrl = ConceptSlidersSteeringController.from_pretrained("lukasz-staniszewski/ace-step-cs-tempo-r16-all", alpha=0.1)
- License
- apache-2.0
- Created
- Aug 31, 2026
- Updated
- Aug 31, 2026