Instructions to use hf-internal-testing/tiny-AudioLDM2Pipeline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hf-internal-testing/tiny-AudioLDM2Pipeline with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hf-internal-testing/tiny-AudioLDM2Pipeline", 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
| { | |
| "architectures": [ | |
| "ClapModel" | |
| ], | |
| "audio_config": { | |
| "aff_block_r": 4, | |
| "attention_probs_dropout_prob": 0.0, | |
| "depths": [ | |
| 1, | |
| 1 | |
| ], | |
| "drop_path_rate": 0.0, | |
| "enable_fusion": false, | |
| "enable_patch_layer_norm": true, | |
| "flatten_patch_embeds": true, | |
| "fusion_type": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 192, | |
| "initializer_factor": 1.0, | |
| "intermediate_size": 37, | |
| "layer_norm_eps": 1e-05, | |
| "mlp_ratio": 4.0, | |
| "model_type": "clap_audio_model", | |
| "num_attention_heads": [ | |
| 1, | |
| 1 | |
| ], | |
| "num_classes": 527, | |
| "num_hidden_layers": 1, | |
| "num_mel_bins": 8, | |
| "patch_embed_input_channels": 4, | |
| "patch_embeds_hidden_size": 96, | |
| "patch_size": 2, | |
| "patch_stride": 2, | |
| "projection_dim": 16, | |
| "projection_hidden_act": "relu", | |
| "qkv_bias": true, | |
| "spec_size": 8, | |
| "window_size": 4 | |
| }, | |
| "dtype": "float32", | |
| "hidden_size": 8, | |
| "initializer_factor": 1.0, | |
| "logit_scale_init_value": 14.285714285714285, | |
| "model_type": "clap", | |
| "num_hidden_layers": 3, | |
| "projection_dim": 16, | |
| "projection_hidden_act": "relu", | |
| "text_config": { | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 8, | |
| "initializer_factor": 1.0, | |
| "intermediate_size": 37, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "clap_text_model", | |
| "num_attention_heads": 1, | |
| "num_hidden_layers": 1, | |
| "position_embedding_type": "absolute", | |
| "projection_dim": 16, | |
| "projection_hidden_act": "relu", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 1000 | |
| }, | |
| "transformers_version": "4.57.1" | |
| } | |