Instructions to use saddam213/AutoEncoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use saddam213/AutoEncoder with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("saddam213/AutoEncoder", 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
Download AceStepXL/config.json from saddam213/AutoEncoder: direct link, hf CLI and curl.
- Browser
- Download file 438 Bytes
-
https://huggingface.co/saddam213/AutoEncoder/resolve/main/AceStepXL/config.json
- Command line
-
hf download hf://saddam213/AutoEncoder/AceStepXL/config.json
-
curl -L -o config.json https://huggingface.co/saddam213/AutoEncoder/resolve/main/AceStepXL/config.json
438 Bytes
| { | |
| "_class_name": "AutoencoderOobleck", | |
| "_diffusers_version": "0.38.0.dev0", | |
| "_name_or_path": "/vepfs-d-data/q-ace/repo/gongjunmin/ACE-Step-1.5/checkpoints/vae", | |
| "audio_channels": 2, | |
| "channel_multiples": [ | |
| 1, | |
| 2, | |
| 4, | |
| 8, | |
| 16 | |
| ], | |
| "decoder_channels": 128, | |
| "decoder_input_channels": 64, | |
| "downsampling_ratios": [ | |
| 2, | |
| 4, | |
| 4, | |
| 6, | |
| 10 | |
| ], | |
| "encoder_hidden_size": 128, | |
| "sampling_rate": 48000 | |
| } | |