Instructions to use hf-internal-testing/tiny-AceStepPipeline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hf-internal-testing/tiny-AceStepPipeline 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-AceStepPipeline", 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
| { | |
| "_class_name": "AceStepConditionEncoder", | |
| "_diffusers_version": "0.39.0.dev0", | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "head_dim": 8, | |
| "hidden_size": 32, | |
| "intermediate_size": 64, | |
| "layer_types": null, | |
| "num_attention_heads": 4, | |
| "num_key_value_heads": 2, | |
| "num_lyric_encoder_hidden_layers": 2, | |
| "num_timbre_encoder_hidden_layers": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 16, | |
| "text_hidden_dim": 32, | |
| "timbre_hidden_dim": 8 | |
| } | |