Instructions to use dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir CogVideoX-Fun-V1.5-5b-InP-mlx dgrauet/CogVideoX-Fun-V1.5-5b-InP-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
| { | |
| "model_type": "cogvideox-fun-inpaint", | |
| "source": "alibaba-pai/CogVideoX-Fun-V1.5-5b-InP", | |
| "transformer": { | |
| "_class_name": "CogVideoXTransformer3DModel", | |
| "_diffusers_version": "0.32.0.dev0", | |
| "activation_fn": "gelu-approximate", | |
| "attention_bias": true, | |
| "attention_head_dim": 64, | |
| "dropout": 0.0, | |
| "flip_sin_to_cos": true, | |
| "freq_shift": 0, | |
| "in_channels": 33, | |
| "max_text_seq_length": 226, | |
| "norm_elementwise_affine": true, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 48, | |
| "num_layers": 42, | |
| "out_channels": 16, | |
| "patch_bias": false, | |
| "patch_size": 2, | |
| "patch_size_t": 2, | |
| "sample_frames": 85, | |
| "sample_height": 384, | |
| "sample_width": 680, | |
| "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": false, | |
| "use_rotary_positional_embeddings": true, | |
| "add_noise_in_inpaint_model": true | |
| }, | |
| "text_encoder": { | |
| "_name_or_path": "google/t5-v1_1-xxl", | |
| "architectures": [ | |
| "T5EncoderModel" | |
| ], | |
| "classifier_dropout": 0.0, | |
| "d_ff": 10240, | |
| "d_kv": 64, | |
| "d_model": 4096, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "num_decoder_layers": 24, | |
| "num_heads": 64, | |
| "num_layers": 24, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.4", | |
| "use_cache": true, | |
| "vocab_size": 32128 | |
| }, | |
| "vae": { | |
| "_class_name": "AutoencoderKLCogVideoX", | |
| "_diffusers_version": "0.31.0.dev0", | |
| "act_fn": "silu", | |
| "block_out_channels": [ | |
| 128, | |
| 256, | |
| 256, | |
| 512 | |
| ], | |
| "down_block_types": [ | |
| "CogVideoXDownBlock3D", | |
| "CogVideoXDownBlock3D", | |
| "CogVideoXDownBlock3D", | |
| "CogVideoXDownBlock3D" | |
| ], | |
| "force_upcast": true, | |
| "in_channels": 3, | |
| "latent_channels": 16, | |
| "latents_mean": null, | |
| "latents_std": null, | |
| "layers_per_block": 3, | |
| "norm_eps": 1e-06, | |
| "norm_num_groups": 32, | |
| "out_channels": 3, | |
| "sample_height": 480, | |
| "sample_width": 720, | |
| "scaling_factor": 0.7, | |
| "shift_factor": null, | |
| "temporal_compression_ratio": 4, | |
| "up_block_types": [ | |
| "CogVideoXUpBlock3D", | |
| "CogVideoXUpBlock3D", | |
| "CogVideoXUpBlock3D", | |
| "CogVideoXUpBlock3D" | |
| ], | |
| "use_post_quant_conv": false, | |
| "use_quant_conv": false | |
| } | |
| } |