Instructions to use tiny-random/moss-image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tiny-random/moss-image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tiny-random/moss-image", 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
Download scheduler/scheduler_config.json from tiny-random/moss-image: direct link, hf CLI and curl.
- Browser
- Download file 494 Bytes
-
https://huggingface.co/tiny-random/moss-image/resolve/main/scheduler/scheduler_config.json
- Command line
-
hf download hf://tiny-random/moss-image/scheduler/scheduler_config.json
-
curl -L -o scheduler_config.json https://huggingface.co/tiny-random/moss-image/resolve/main/scheduler/scheduler_config.json
494 Bytes
| { | |
| "_class_name": "MOSSImageScheduler", | |
| "_diffusers_version": "0.38.0", | |
| "base_image_seq_len": 256, | |
| "base_shift": 0.5, | |
| "invert_sigmas": false, | |
| "max_image_seq_len": 4096, | |
| "max_shift": 1.15, | |
| "num_train_timesteps": 1000, | |
| "shift": 5.0, | |
| "shift_terminal": null, | |
| "stochastic_sampling": false, | |
| "time_shift_type": "exponential", | |
| "training_shift": 1.0, | |
| "use_beta_sigmas": false, | |
| "use_dynamic_shifting": false, | |
| "use_exponential_sigmas": false, | |
| "use_karras_sigmas": false | |
| } | |