Instructions to use zhangj1an/AudioX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zhangj1an/AudioX with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zhangj1an/AudioX", 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
-
Rename text_encoder.encoder.embed_tokens.weight -> text_encoder.shared.weight so AutoWeightsLoader can match the HF T5 shared-embedding alias without a remap.
Verified signature921a1c2
-
Upload transformer/diffusion_pytorch_model.safetensors with huggingface_hub
Verified signaturebd3cd6e -
Upload transformer/diffusion_pytorch_model.safetensors with huggingface_hub
Verified signaturec56fc26 -
Upload folder using huggingface_hub
Verified signature108bbbb
-
Repack weights: transformer + vae safetensors (Diffusers layout); drop legacy conditioners shard
Verified signatured55e834
-
Remove redundant weights_format from model_index.json; re-sync safetensors bundle
Verified signature27d5612 -
Canonical weights: offline remap via vLLM-Omni audiox_weights (weights_format=canonical)
Verified signature550443e -
Add Diffusers vae layout: config.json + encoder/decoder safetensors for AutoencoderOobleck.from_pretrained
Verified signatureadeea5f -
AudioX vLLM-Omni sharded safetensors
Verified signature1e3bb96 -
initial commit
Verified signature51411be