Instructions to use Shitao/OmniGen-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Shitao/OmniGen-v1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Shitao/OmniGen-v1", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Missing `model_index.json`
#10
by jhj0517 - opened
Hi, Thanks for the wonderful model,
I'm trying to quantize the model but it seems like model_index.json is missing:
pipe = DiffusionPipeline.from_pretrained("Shitao/OmniGen-v1", torch_dtype=torch.float16).to("cuda")
I got:
Entry Not Found for url: https://huggingface.co/Shitao/OmniGen-v1/resolve/main/model_index.json.
Can you please add it? According to the documentation,
The model_index.json follows the example format:
{
"_class_name": "StableDiffusionPipeline",
"_diffusers_version": "0.6.0",
"feature_extractor": [
"transformers",
"CLIPImageProcessor"
],
"safety_checker": [
"stable_diffusion",
"StableDiffusionSafetyChecker"
],
"scheduler": [
"diffusers",
"PNDMScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}