readme updates
Browse files
README.md
CHANGED
|
@@ -2,6 +2,43 @@
|
|
| 2 |
language: en
|
| 3 |
tags:
|
| 4 |
- stable-diffusion
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
-
# SDXL-Base on AMD NPU
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
language: en
|
| 3 |
tags:
|
| 4 |
- stable-diffusion
|
| 5 |
+
- sdxl
|
| 6 |
+
pipeline_tag: text-to-image
|
| 7 |
+
license: openrail++
|
| 8 |
+
license_link: LICENSE
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# 🚀 SDXL-Base on AMD NPU
|
| 12 |
+
|
| 13 |
+
"SDXL is a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet backbone, achieved by significantly increasing the number of attention blocks and including a second text encoder." ([stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0))
|
| 14 |
+
|
| 15 |
+
This version of the model has been optimized to run on AMD NPUs.
|
| 16 |
+
|
| 17 |
+
For more information, refer to the original model card under [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0).
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
| Model Details | Description |
|
| 22 |
+
| ----------- | ----------- |
|
| 23 |
+
| Person or organization developing model | [AMD](https://hf.co/amd) |
|
| 24 |
+
| Original model authors | [Stability AI](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) |
|
| 25 |
+
| Model date | February 2026 |
|
| 26 |
+
| Model version | 1.7.0 |
|
| 27 |
+
| Model type | Diffusion-based text-to-image generation model |
|
| 28 |
+
| Information about training algorithms, parameters, fairness constraints or other applied approaches, and features | This is a model that can be used to generate and modify images based on text prompts. |
|
| 29 |
+
| License | [CreativeML Open RAIL++-M License](LICENSE) |
|
| 30 |
+
| Where to send questions or comments about the model | [Community Tab](https://hf.co/amd/sdxl-base-amdnpu/discussions) and [AMD Developer Community Discord](https://discord.gg/amd-dev) |
|
| 31 |
+
|
| 32 |
+
## ⚡ Intended Use
|
| 33 |
+
|
| 34 |
+
#### Getting Started
|
| 35 |
+
|
| 36 |
+
To get started with this model, visit [github.com/amd/sd-sandbox](https://github.com/amd/sd-sandbox).
|
| 37 |
+
|
| 38 |
+
## ⚓ Ethical Considerations
|
| 39 |
+
|
| 40 |
+
AMD is committed to conducting our business in a fair, ethical and honest manner and in compliance with all applicable laws, rules and regulations. You can find out more at the [AMD Ethics and Compliance](https://www.amd.com/en/corporate/corporate-responsibility/ethics-and-compliance.html) page.
|
| 41 |
+
|
| 42 |
+
## ⚠️ Caveats and Recommendations
|
| 43 |
+
|
| 44 |
+
Please visit the original model card for more details: [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0).
|