Image-to-Image
Transformers
Safetensors
English
janus_ddpm
feature-extraction
project:genesis
project:ArtIMis
type:model
science:materials
science:physics-simulation
risk:general
custom-code
custom_code
Instructions to use 90879c/Janus-first2last with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 90879c/Janus-first2last with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-to-image", model="90879c/Janus-first2last", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("90879c/Janus-first2last", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "JanusDDPMModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_janus_ddpm.JanusDDPMConfig", | |
| "AutoModel": "modeling_janus_ddpm.JanusDDPMModel" | |
| }, | |
| "base_channels": 64, | |
| "beta_end": 0.02, | |
| "beta_start": 0.0001, | |
| "direction": "first2last", | |
| "dtype": "float32", | |
| "field_name": "av_density", | |
| "img_size": [ | |
| 560, | |
| 200 | |
| ], | |
| "in_channels": 2, | |
| "model_name": "Janus-first2last", | |
| "model_type": "janus_ddpm", | |
| "num_timesteps": 1000, | |
| "out_channels": 1, | |
| "source_best_validation_loss": 0.0010155698441667482, | |
| "source_checkpoint_epoch": 533, | |
| "source_train_loss": 0.000961887405286814, | |
| "source_validation_loss": 0.0013378456623468083, | |
| "time_emb_dim": 256, | |
| "transformers_version": "5.2.0" | |
| } | |