Text-to-Video
Diffusers
Safetensors
English
MotifVideoPipeline
image-to-video
video-generation
diffusion-transformer
Instructions to use smithcooly2k/Motif-Video-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use smithcooly2k/Motif-Video-2B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("smithcooly2k/Motif-Video-2B", dtype=torch.bfloat16, device_map="cuda") prompt = "A vibrant blue jay perches gracefully on a slender branch, its feathers shimmering in the soft morning light. The bird's keen eyes scan the surroundings, capturing the essence of the tranquil forest. It flutters its wings briefly, showcasing the intricate patterns of blue, white, and black on its plumage. The background reveals a lush canopy of green leaves, with rays of sunlight filtering through, creating a dappled effect on the forest floor. The blue jay then tilts its head, emitting a melodious call that echoes through the serene woodland, adding a touch of magic to the peaceful scene." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
File size: 3,596 Bytes
ef28144 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 | {
"architectures": [
"T5Gemma2Encoder"
],
"attention_dropout": 0.0,
"boi_token_index": 255999,
"dropout_rate": 0.0,
"dtype": "bfloat16",
"eoi_token_index": 256000,
"image_token_index": 256001,
"initializer_range": 0.02,
"mm_tokens_per_image": 256,
"model_type": "t5gemma2_encoder",
"text_config": {
"_sliding_window_pattern": 6,
"add_cross_attention": false,
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"dropout_rate": 0.0,
"dtype": "bfloat16",
"eos_token_id": 1,
"final_logit_softcapping": null,
"finetuning_task": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 10240,
"is_decoder": false,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention"
],
"max_position_embeddings": 131072,
"model_type": "t5gemma2_text",
"num_attention_heads": 8,
"num_hidden_layers": 34,
"num_key_value_heads": 4,
"pad_token_id": 0,
"prefix": null,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"factor": 8.0,
"rope_theta": 1000000,
"rope_type": "linear"
},
"sliding_attention": {
"rope_theta": 10000,
"rope_type": "default"
}
},
"sep_token_id": null,
"sliding_window": 1024,
"task_specific_params": null,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"use_bidirectional_attention": false,
"use_cache": true,
"vocab_size": 262144
},
"tie_word_embeddings": true,
"transformers_version": "5.5.4",
"vision_config": {
"add_cross_attention": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"dropout_rate": 0.0,
"dtype": "bfloat16",
"eos_token_id": null,
"finetuning_task": null,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"image_size": 896,
"intermediate_size": 4304,
"is_decoder": false,
"layer_norm_eps": 1e-06,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 27,
"pad_token_id": null,
"patch_size": 14,
"prefix": null,
"sep_token_id": null,
"task_specific_params": null,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"vision_use_head": false,
"vocab_size": 262144
},
"vocab_size": 262144
} |