Instructions to use simpleipfs/custom_sdxl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use simpleipfs/custom_sdxl with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("simpleipfs/custom_sdxl", 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
Revert to fp16
Browse files
text_encoder_2/config.json
CHANGED
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"num_hidden_layers": 32,
|
| 19 |
"pad_token_id": 1,
|
| 20 |
"projection_dim": 1280,
|
| 21 |
-
"torch_dtype": "
|
| 22 |
"transformers_version": "4.40.0",
|
| 23 |
"vocab_size": 49408
|
| 24 |
}
|
|
|
|
| 18 |
"num_hidden_layers": 32,
|
| 19 |
"pad_token_id": 1,
|
| 20 |
"projection_dim": 1280,
|
| 21 |
+
"torch_dtype": "float16",
|
| 22 |
"transformers_version": "4.40.0",
|
| 23 |
"vocab_size": 49408
|
| 24 |
}
|