Skip to content

Commit 25e2bba

Browse files
committed
Update readme
1 parent 06dd649 commit 25e2bba

File tree

1 file changed

+2
-4
lines changed

1 file changed

+2
-4
lines changed

Readme.md

+2-4
Original file line numberDiff line numberDiff line change
@@ -284,7 +284,7 @@ Fast SD now supports AI PC with Intel® Core™ Ultra Processors. [To learn more
284284

285285
For GPU mode `set device=GPU` and run webui. FastSD GPU benchmark on AI PC as shown below.
286286

287-
![FastSD AIPC Arc GPU benchmark](https://raw.githubusercontent.com/rupeshs/fastsdcpu/main/docs/images/ARCGPU.png)
287+
![FastSD AI PC Arc GPU benchmark](https://raw.githubusercontent.com/rupeshs/fastsdcpu/main/docs/images/ARCGPU.png)
288288

289289
### NPU
290290
FastSD CPU now supports power efficient NPU (Neural Processing Unit) that comes with Intel Core Ultra processors.
@@ -295,14 +295,12 @@ Supports following modes on NPU :
295295
- Image to image
296296
- Image variations
297297

298-
To run model in NPU follow these steps (Please make sure that your AIPC's NPU driver is latest):
298+
To run model in NPU follow these steps (Please make sure that your AI PC's NPU driver is the latest):
299299
- Start webui
300300
- Select LCM-OpenVINO mode
301301
- Select the models settings tab and select OpenVINO model `sd15-lcm-square-openvino-int8`
302302
- Now it will run on the NPU
303303

304-
305-
306304
This is heterogeneous computing since text encoder and Unet will use NPU and VAE will use GPU for processing. Thanks to OpenVINO.
307305

308306
Please note that tiny auto encoder will not work in NPU mode.

0 commit comments

Comments
 (0)