Instructions to use ByteDance/Bernini-R-1.3B-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ByteDance/Bernini-R-1.3B-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("ByteDance/Bernini-R-1.3B-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
Commit ·
ff4c5d4
1
Parent(s): 3b0d3f5
Fix transformer/config.json: 14B dims should be 1.3B (#1)
Browse files- Update transformer/config.json (3fef913143df05ccc4a8ddf2e578781fdde8afb2)
Co-authored-by: stuttlepress <FartingBackwards@users.noreply.huggingface.co>
- transformer/config.json +3 -3
transformer/config.json
CHANGED
|
@@ -5,12 +5,12 @@
|
|
| 5 |
"attention_head_dim": 128,
|
| 6 |
"cross_attn_norm": true,
|
| 7 |
"eps": 1e-06,
|
| 8 |
-
"ffn_dim":
|
| 9 |
"freq_dim": 256,
|
| 10 |
"image_dim": null,
|
| 11 |
"in_channels": 16,
|
| 12 |
-
"num_attention_heads":
|
| 13 |
-
"num_layers":
|
| 14 |
"out_channels": 16,
|
| 15 |
"patch_size": [
|
| 16 |
1,
|
|
|
|
| 5 |
"attention_head_dim": 128,
|
| 6 |
"cross_attn_norm": true,
|
| 7 |
"eps": 1e-06,
|
| 8 |
+
"ffn_dim": 8960,
|
| 9 |
"freq_dim": 256,
|
| 10 |
"image_dim": null,
|
| 11 |
"in_channels": 16,
|
| 12 |
+
"num_attention_heads": 12,
|
| 13 |
+
"num_layers": 30,
|
| 14 |
"out_channels": 16,
|
| 15 |
"patch_size": [
|
| 16 |
1,
|