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
total newbie in distress
hi i'm totally new to this world and i can't make it work because i have an AMD GPU so if someone can send me to an introduction or a tutorial to diffusers and torch because i don't really understand the docs and if someone can tell me what accelerator i can use to make it work it will make my day. thanks to any response.
Are you running on a Mac? M1/M2?
i'm on kubuntu with a AMD Radeon RX 6600 XT, AMD Ryzen 5 PRO 4650G with Radeon Graphics and 32 Gb of ram.
Ah ok. Sorry - I misread your first comment. Im on an M1 Mac and have managed to get this model working now. I had to install Pytorch from source, however, from github to get that support. You may need to do the same for AMD:
https://pytorch.org/blog/experience-power-pytorch-2.0/
https://github.com/pytorch/pytorch#from-source
Avoid the CUDA stuff as thats NVIDIA frameworks. Ive also switched to using Conda for my python environments. Although occasionally I still have to drop into pip/3 to get things behaving. It's a fiddly bizness getting this stuff to work outside of the NVIDIA/CUDA pathways, but it is possible!