Instructions to use BiliSakura/BitDance-14B-64x-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/BitDance-14B-64x-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("BiliSakura/BitDance-14B-64x-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
- Local Apps
- Draw Things
- DiffusionBee
Update all files for BitDance-14B-64x-diffusers
Browse files- diffusion_head/config.json +17 -0
diffusion_head/config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"P_mean": 0.0,
|
| 3 |
+
"P_std": 1.0,
|
| 4 |
+
"_class_name": "BitDanceDiffusionHead",
|
| 5 |
+
"_diffusers_version": "0.36.0",
|
| 6 |
+
"ch_cond": 5120,
|
| 7 |
+
"ch_latent": 5120,
|
| 8 |
+
"ch_target": 32,
|
| 9 |
+
"depth_adanln": 2,
|
| 10 |
+
"depth_latent": 6,
|
| 11 |
+
"diff_batch_mul": 1,
|
| 12 |
+
"grad_checkpointing": false,
|
| 13 |
+
"parallel_num": 64,
|
| 14 |
+
"time_schedule": "logit_normal",
|
| 15 |
+
"time_shift": 1.0,
|
| 16 |
+
"use_swiglu": true
|
| 17 |
+
}
|