Instructions to use wangkanai/sdxl-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wangkanai/sdxl-fp16 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wangkanai/sdxl-fp16", 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 Settings
- Draw Things
- DiffusionBee
Add files using upload-large-folder tool
Browse files
README.md
CHANGED
|
@@ -6,12 +6,9 @@ tags:
|
|
| 6 |
- sdxl
|
| 7 |
- text-to-image
|
| 8 |
- image-generation
|
| 9 |
-
- stable-diffusion
|
| 10 |
-
- fp16
|
| 11 |
-
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
| 12 |
---
|
| 13 |
|
| 14 |
-
<!-- README Version: v1.
|
| 15 |
|
| 16 |
# Stable Diffusion XL FP16 Model Repository
|
| 17 |
|
|
@@ -185,6 +182,11 @@ image = pipe(
|
|
| 185 |
|
| 186 |
## Changelog
|
| 187 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 188 |
### v1.1 (2025-10-14)
|
| 189 |
- Updated YAML frontmatter format (metadata now precedes version header)
|
| 190 |
- Optimized tag ordering for better discoverability
|
|
|
|
| 6 |
- sdxl
|
| 7 |
- text-to-image
|
| 8 |
- image-generation
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
+
<!-- README Version: v1.2 -->
|
| 12 |
|
| 13 |
# Stable Diffusion XL FP16 Model Repository
|
| 14 |
|
|
|
|
| 182 |
|
| 183 |
## Changelog
|
| 184 |
|
| 185 |
+
### v1.2 (2025-10-14)
|
| 186 |
+
- Fixed YAML frontmatter: removed base_model fields (these are base models, not derived)
|
| 187 |
+
- Streamlined tags to essential categories only
|
| 188 |
+
- Improved metadata compliance with Hugging Face standards
|
| 189 |
+
|
| 190 |
### v1.1 (2025-10-14)
|
| 191 |
- Updated YAML frontmatter format (metadata now precedes version header)
|
| 192 |
- Optimized tag ordering for better discoverability
|