Instructions to use SsharvienKumar/SWoMo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SsharvienKumar/SWoMo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SsharvienKumar/SWoMo", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_class_name": "ControlNetModel", | |
| "_diffusers_version": "0.21.2", | |
| "_name_or_path": "./checkpoints/Cataract-1k/video_diffusion/surgsimbridge_training_img_graph_vid_cataract1k-2026-04-15T07-35-15/checkpoints/checkpoint-145000", | |
| "act_fn": "silu", | |
| "addition_embed_type": null, | |
| "addition_embed_type_num_heads": 64, | |
| "addition_time_embed_dim": null, | |
| "attention_head_dim": [ | |
| 5, | |
| 10, | |
| 20, | |
| 20 | |
| ], | |
| "attention_type": "default", | |
| "augment_temporal_attention": true, | |
| "block_out_channels": [ | |
| 320, | |
| 640, | |
| 1280, | |
| 1280 | |
| ], | |
| "class_embed_type": "identity", | |
| "class_embeddings_concat": true, | |
| "conditioning_channels": 3, | |
| "conditioning_embedding_out_channels": [ | |
| 16, | |
| 32, | |
| 96, | |
| 256 | |
| ], | |
| "conv_in_kernel": 3, | |
| "cross_attention_dim": 1024, | |
| "cross_attention_norm": null, | |
| "down_block_types": [ | |
| "CrossAttnDownBlock2D", | |
| "CrossAttnDownBlock2D", | |
| "CrossAttnDownBlock2D", | |
| "DownBlock2D" | |
| ], | |
| "downsample_padding": 1, | |
| "dropout": 0.0, | |
| "dual_cross_attention": false, | |
| "encoder_hid_dim": null, | |
| "encoder_hid_dim_type": null, | |
| "first_frame_condition_mode": "concat", | |
| "flip_sin_to_cos": true, | |
| "freq_shift": 0, | |
| "global_pool_conditions": false, | |
| "in_channels": 4, | |
| "layers_per_block": 2, | |
| "mid_block_only_cross_attention": null, | |
| "mid_block_scale_factor": 1, | |
| "mid_block_type": "UNetMidBlock2DCrossAttn", | |
| "n_frames": 16, | |
| "n_temp_heads": 8, | |
| "norm_eps": 1e-05, | |
| "norm_num_groups": 32, | |
| "num_attention_heads": null, | |
| "num_class_embeds": null, | |
| "only_cross_attention": false, | |
| "projection_class_embeddings_input_dim": null, | |
| "resnet_out_scale_factor": 1.0, | |
| "resnet_skip_time_act": false, | |
| "resnet_time_scale_shift": "default", | |
| "temp_pos_embedding": "rotary", | |
| "time_cond_proj_dim": null, | |
| "time_embedding_act_fn": null, | |
| "time_embedding_dim": 512, | |
| "time_embedding_type": "positional", | |
| "timestep_post_act": null, | |
| "transformer_layers_per_block": 1, | |
| "upcast_attention": false, | |
| "use_frame_stride_condition": false, | |
| "use_linear_projection": true, | |
| "use_temporal": true | |
| } | |