Instructions to use BestWishYsh/ConsisID-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BestWishYsh/ConsisID-preview with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BestWishYsh/ConsisID-preview", 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
Update transformer/config.json
Browse files- transformer/config.json +1 -1
transformer/config.json
CHANGED
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"LFE_num_querie": 32,
|
| 23 |
"LFE_output_dim": 2048,
|
| 24 |
"LFE_ff_mult": 4,
|
| 25 |
-
"LFE_num_scale" 5,
|
| 26 |
"local_face_scale": 1.0,
|
| 27 |
"max_text_seq_length": 226,
|
| 28 |
"norm_elementwise_affine": true,
|
|
|
|
| 22 |
"LFE_num_querie": 32,
|
| 23 |
"LFE_output_dim": 2048,
|
| 24 |
"LFE_ff_mult": 4,
|
| 25 |
+
"LFE_num_scale": 5,
|
| 26 |
"local_face_scale": 1.0,
|
| 27 |
"max_text_seq_length": 226,
|
| 28 |
"norm_elementwise_affine": true,
|