Instructions to use echarlaix/tiny-random-stable-diffusion-xl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use echarlaix/tiny-random-stable-diffusion-xl with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("echarlaix/tiny-random-stable-diffusion-xl", 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
what is it?
#1
by bghira - opened
is this a small model made by the generative-models training kit?
it should be a part of the internal testing pipe
def test_inference(self):
model_id = "hf-internal-testing/tiny-stable-diffusion-xl-pipe"
pipeline = self.MODEL_CLASS.from_pretrained(model_id)
with tempfile.TemporaryDirectory() as tmp_dir:
pipeline.save_pretrained(tmp_dir)
pipeline = self.MODEL_CLASS.from_pretrained(tmp_dir)
do check: https://raw.githubusercontent.com/huggingface/optimum-intel/main/tests/openvino/utils_tests.py
Hi @ptx0, this is a small SDXL model randomly initialized that we are using for the optimum tests, added as hf-internal-testing/tiny-stable-diffusion-xl-pipe didn't exist at the time but the latter can be used instead
echarlaix changed discussion status to closed