ComfyUI/comfy/clip_vision_siglip_384.json

14 lines
314 B
JSON

{
"num_channels": 3,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"image_size": 384,
"intermediate_size": 4304,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"patch_size": 14,
"image_mean": [0.5, 0.5, 0.5],
"image_std": [0.5, 0.5, 0.5]
}