Instructions to use nousr/robo-diffusion-2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nousr/robo-diffusion-2-base with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nousr/robo-diffusion-2-base", 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
- Draw Things
- DiffusionBee
Adding `safetensors` variant of this model
#9
by Sakabatou - opened
No description provided.
Where to put the safetensors model sir?
@Sakabatou is safetensors simply a safety precaution? Will this let users use this model with AUTOMATIC1111?
@Sakabatou is safetensors simply a safety precaution? Will this let users use this model with AUTOMATIC1111?
The point is not so much in the "precaution." Safetensors are loaded much faster into WebUI, which is especially noticeable when switching between different models (almost 3 times faster when switching between weights). And yes, this format is fully supported by Automation1111 WebUI and all similar things. In fact, now Safetensors must become the only format of SD-models for all, forget about CKPT.