vta-ldm / configs /diffusion_model_config_large.json
fffiloni's picture
Upload 130 files
c673f60 verified
raw
history blame
943 Bytes
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.10.0.dev0",
"act_fn": "silu",
"attention_head_dim": [
5,
10,
20,
20
],
"block_out_channels": [
320,
640,
640,
1280
],
"center_input_sample": false,
"cross_attention_dim": 1024,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"dual_cross_attention": false,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 8,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_class_embeds": null,
"only_cross_attention": false,
"out_channels": 8,
"sample_size": [32, 2],
"up_block_types": [
"UpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D"
],
"use_linear_projection": true,
"upcast_attention": true
}