Image-Text-to-Video
Diffusers
Safetensors
English
world-model
world-simulation
text-to-video
image-to-video
diffusion-transformer
Instructions to use IFM/PAN2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use IFM/PAN2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("IFM/PAN2", 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 transformer/config.json from IFM/PAN2: direct link, hf CLI and curl.
- Browser
- Download file 495 Bytes
-
https://huggingface.co/IFM/PAN2/resolve/main/transformer/config.json
- Command line
-
hf download hf://IFM/PAN2/transformer/config.json
-
curl -L -o config.json https://huggingface.co/IFM/PAN2/resolve/main/transformer/config.json
495 Bytes
| { | |
| "_class_name": "PAN2Transformer3DModel", | |
| "_diffusers_version": "0.41.0.dev0", | |
| "attention_head_dim": 128, | |
| "context_mlp_ratio": 4.0, | |
| "in_channels": 97, | |
| "mlp_ratio": 8.0, | |
| "num_attention_heads": 32, | |
| "num_layers": 44, | |
| "num_refiner_layers": 4, | |
| "out_channels": 48, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "refiner_mlp_ratio": 4.0, | |
| "rope_axes_dim": [ | |
| 16, | |
| 56, | |
| 56 | |
| ], | |
| "rope_temporal_scale": 0.6666666666666666, | |
| "rope_theta": 256.0, | |
| "text_embed_dim": 4096 | |
| } | |