Instructions to use dataautogpt3/OpenDalleV1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dataautogpt3/OpenDalleV1.1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dataautogpt3/OpenDalleV1.1", dtype=torch.bfloat16, device_map="cuda") prompt = "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Vertical and horizontal images?
Hi! I am still learning, can someone explain how can I generate non 1:1 aspect ratio images? Is it possible with this model?
pipeline(prompt, width=whatever, height=whatever) # Both numbers have to be a multiple of 8
Hi! I am still learning, can someone explain how can I generate non 1:1 aspect ratio images? Is it possible with this model?
I highly recommend looking up "ComfyUI" and experimenting with it, specially when you are still learning and on first contacts.
Its much easier to prototype and experiment and do cool stuff with many different models in it,
then if you have a specific product idea or script/code idea, that's when you use python and diffusers library directly to build your specific use case.

