Instructions to use phi-lab-rice/GRADE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use phi-lab-rice/GRADE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("phi-lab-rice/GRADE", 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
File size: 464 Bytes
f348660 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | training: {batch_size: 1, mixed_precision: fp16, seed: 42}
data:
smoke_eval_root: ../../../evaluation_dataset/Smoke-Eval
resolution: {height: 288, width: 512}
scale_factor: 0.001
max_depth_m: 11.2
num_frames: 1
num_workers: 0
pretrained:
radar_model: ../../../checkpoints/grade/radar.safetensors
unet: ../../../checkpoints/grade/diffusion.safetensors
diffusion: {num_train_timesteps: 1000}
inference: {frame_skip: 1, batch_size: 1, num_workers: 0}
|