Text-to-Audio
Diffusers
Safetensors
MossSoundEffectPipeline
sound-effects
foley
flow-matching
diffusion-transformer
dac-vae
english
chinese
moss
mirror
Instructions to use AEmotionStudio/moss-soundeffect-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AEmotionStudio/moss-soundeffect-models with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AEmotionStudio/moss-soundeffect-models", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Commit History
-
Mirror OpenMOSS-Team/MOSS-SoundEffect-v2.0 for MAESTRO
Verified signature- DiT cast to bf16 (smoke-gate verdict); Qwen3 text encoder shards and tokenizer verbatim (bf16 storage) - DAC VAE converted from vae_128d_48k.pth (pickled audiotools package) to safetensors via save_model; constructor kwargs written into vae/config.json - full-pipeline load verified against MAESTRO's vendored moss_soundeffect inference graph before upload Loaded by MAESTRO via backend/ai/models/moss_soundeffect.py.41a7f2b