Instructions to use JackeyH/VideoGen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use JackeyH/VideoGen with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("JackeyH/VideoGen", 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 scartch/config.json from JackeyH/VideoGen: direct link, hf CLI and curl.
- Browser
- Download file 1.4 kB
-
https://huggingface.co/JackeyH/VideoGen/resolve/main/scartch/config.json
- Command line
-
hf download hf://JackeyH/VideoGen/scartch/config.json
-
curl -L -o config.json https://huggingface.co/JackeyH/VideoGen/resolve/main/scartch/config.json
1.4 kB
| { | |
| "LFE_depth": 10, | |
| "LFE_dim_head": 64, | |
| "LFE_ff_mult": 4, | |
| "LFE_heads": 12, | |
| "LFE_id_dim": 1280, | |
| "LFE_num_heads": 16, | |
| "LFE_num_id_token": 5, | |
| "LFE_num_querie": 32, | |
| "LFE_num_scale": 5, | |
| "LFE_num_tokens": 32, | |
| "LFE_output_dim": 2048, | |
| "LFE_vit_dim": 1024, | |
| "_class_name": "ConsistentVideoTransformer3DModel", | |
| "_diffusers_version": "0.33.0.dev0", | |
| "activation_fn": "gelu-approximate", | |
| "attention_bias": true, | |
| "attention_head_dim": 64, | |
| "calculate_align_loss": "True", | |
| "cross_attn_dim_head": 128, | |
| "cross_attn_interval": 2, | |
| "cross_attn_num_heads": 16, | |
| "cross_text_interval": 2, | |
| "dropout": 0.0, | |
| "flip_sin_to_cos": true, | |
| "freq_shift": 0, | |
| "in_channels": 32, | |
| "is_kps": false, | |
| "is_textCA": "True", | |
| "is_train_face": true, | |
| "is_visionCA": "True", | |
| "local_face_scale": 1.0, | |
| "local_text_scale": 0.5, | |
| "max_text_seq_length": 226, | |
| "norm_elementwise_affine": true, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 48, | |
| "num_layers": 42, | |
| "out_channels": 16, | |
| "patch_size": 2, | |
| "patch_size_t": null, | |
| "sample_frames": 49, | |
| "sample_height": 60, | |
| "sample_width": 90, | |
| "spatial_interpolation_scale": 1.875, | |
| "temporal_compression_ratio": 4, | |
| "temporal_interpolation_scale": 1.0, | |
| "text_embed_dim": 4096, | |
| "time_embed_dim": 512, | |
| "timestep_activation_fn": "silu", | |
| "use_learned_positional_embeddings": true, | |
| "use_rotary_positional_embeddings": true | |
| } | |