Exported with
optimum-cli export neuron --model PixArt-alpha/PixArt-XL-2-512x512 --batch_size 1 --height 512 --width 512 --num_images_per_prompt 1 --torch_dtype bfloat16 --sequence_length 120 pixart_alpha_neuron_512/
Inference
from optimum.neuron import NeuronPixArtAlphaPipeline
neuron_model = NeuronPixArtAlphaPipeline.from_pretrained(save_directory)
prompt = "Mario got caught in a McDonald's while eating hamburgers with pickles."
image = neuron_model(prompt=prompt).images[0]
image.save("out.png")
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.