Instructions to use saddam213/LongCat-AudioDiT-3.5B-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use saddam213/LongCat-AudioDiT-3.5B-diffusers 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/LongCat-AudioDiT-3.5B-diffusers", 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": "LongCatAudioDiTTransformer", | |
| "_diffusers_version": "0.39.0.dev0", | |
| "adaln_type": "global", | |
| "adaln_use_text_cond": true, | |
| "bias": true, | |
| "cross_attn": true, | |
| "cross_attn_norm": false, | |
| "dit_depth": 32, | |
| "dit_dim": 2560, | |
| "dit_heads": 32, | |
| "dit_text_dim": 768, | |
| "dropout": 0.0, | |
| "eps": 1e-06, | |
| "ff_mult": 3.6, | |
| "latent_dim": 64, | |
| "long_skip": true, | |
| "qk_norm": true, | |
| "text_conv": true, | |
| "use_latent_condition": true | |
| } | |