Habana Gaudi
How to use Stable Diffusion on Habana Gaudi
π Diffusers is compatible with Habana Gaudi through π Optimum Habana.
Requirements
Optimum Habana 1.6 or later, here is how to install it.
SynapseAI 1.10.
Inference Pipeline
To generate images with Stable Diffusion 1 and 2 on Gaudi, you need to instantiate two instances:
A pipeline with
GaudiStableDiffusionPipeline
. This pipeline supports text-to-image generation.A scheduler with
GaudiDDIMScheduler
. This scheduler has been optimized for Habana Gaudi.
When initializing the pipeline, you have to specify use_habana=True
to deploy it on HPUs. Furthermore, in order to get the fastest possible generations you should enable HPU graphs with use_hpu_graphs=True
. Finally, you will need to specify a Gaudi configuration which can be downloaded from the Hugging Face Hub.
Copied
from optimum.habana import GaudiConfig
from optimum.habana.diffusers import GaudiDDIMScheduler, GaudiStableDiffusionPipeline
model_name = "stabilityai/stable-diffusion-2-base"
scheduler = GaudiDDIMScheduler.from_pretrained(model_name, subfolder="scheduler")
pipeline = GaudiStableDiffusionPipeline.from_pretrained(
model_name,
scheduler=scheduler,
use_habana=True,
use_hpu_graphs=True,
gaudi_config="Habana/stable-diffusion-2",
)
You can then call the pipeline to generate images by batches from one or several prompts:
Copied
outputs = pipeline(
prompt=[
"High quality photo of an astronaut riding a horse in space",
"Face of a yellow cat, high resolution, sitting on a park bench",
],
num_images_per_prompt=10,
batch_size=4,
)
For more information, check out Optimum Habanaβs documentation and the example provided in the official Github repository.
Benchmark
Here are the latencies for Habana first-generation Gaudi and Gaudi2 with the Habana/stable-diffusion and Habana/stable-diffusion-2 Gaudi configurations (mixed precision bf16/fp32):
Stable Diffusion v1.5 (512x512 resolution):
first-generation Gaudi
3.80s
0.308 images/s
Gaudi2
1.33s
1.081 images/s
Stable Diffusion v2.1 (768x768 resolution):
first-generation Gaudi
10.2s
0.108 images/s (batch size = 4)
Gaudi2
3.17s
0.379 images/s (batch size = 8)
Last updated