{
	"dataset_params": {
		"image_path": "data/CelebAMask-HQ",
		"image_channels": 3,
		"image_size": 256,
		"name": "celebhq"
	},
	"diffusion_params": {
		"num_timesteps": 1000,
		"beta_start": 0.00085,
		"beta_end": 0.012
	},
	"ldm_params": {
		"down_channels": [256, 384, 512, 768],
		"mid_channels": [768, 512],
		"down_sample": [true, true, true],
		"attn_down": [true, true, true],
		"time_emb_dim": 512,
		"norm_channels": 32,
		"num_heads": 16,
		"conv_out_channels": 128,
		"num_down_layers": 2,
		"num_mid_layers": 2,
		"num_up_layers": 2,
		"condition_config": {
			"condition_types": ["text", "image"],
			"text_condition_config": {
				"text_embed_model": "clip",
				"train_text_embed_model": false,
				"text_embed_dim": 512,
				"cond_drop_prob": 0.1
			},
			"image_condition_config": {
				"image_condition_input_channels": 18,
				"image_condition_output_channels": 3,
				"image_condition_h": 512,
				"image_condition_w": 512,
				"cond_drop_prob": 0.1
			}
		}
	},
	"autoencoder_params": {
		"z_channels": 4,
		"codebook_size": 8192,
		"down_channels": [64, 128, 256, 256],
		"mid_channels": [256, 256],
		"down_sample": [true, true, true],
		"attn_down": [false, false, false],
		"norm_channels": 32,
		"num_heads": 4,
		"num_down_layers": 2,
		"num_mid_layers": 2,
		"num_up_layers": 2
	},
	"train_params": {
		"task_name": "celebhq",
		"num_samples": 1,
		"num_grid_rows": 1,
		"cf_guidance_scale": 1.0,
		"ldm_ckpt_name": "ddpm_ckpt_class_cond.pth",
		"vqvae_autoencoder_ckpt_name": "vqvae_autoencoder_ckpt.pth",
		"vqvae_latent_dir_name": "vqvae_latents"
	}
}