TASK_TYPE: inference_sr600_entrance
use_fp16: True
vldm_cfg: ''
round: 1
batch_size: 1
# For important input
test_list_path: data/text_list_for_t2v_share.txt
test_model: models/sr_step_110000_ema.pth

embedder: {
    'type': 'FrozenOpenCLIPTextVisualEmbedder',
    'layer': 'penultimate',
    'vit_resolution': [224, 224],
    'pretrained': 'i2vgen-xl/models/open_clip_pytorch_model.bin',
    'negative_prompt': 'worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting',
    'positive_prompt': ', cinematic, High Contrast, highly detailed, Unreal Engine 5, no blur, full length ultra-wide angle shot a cinematic scene, taken using a Canon EOS R camera, hyper detailed photo - realistic maximum detail, 32k, Color Grading, portrait Photography, ultra HD, extreme meticulous detailing, skin pore detailing, hyper sharpness, perfect without deformations, 4k render'
}
UNet: {
    'type': 'UNetSD_SR600',
    'in_dim': 4,
    'dim': 320,
    'y_dim': 1024,
    'context_dim': 1024,
    'out_dim': 4,
    'dim_mult': [1, 2, 4, 4],
    'num_heads': 8,
    'head_dim': 64,
    'num_res_blocks': 2,
    'attn_scales' :[1, 0.5, 0.25],
    'use_scale_shift_norm': True,
    'dropout': 0.1,
    'temporal_attn_times': 1,
    'temporal_attention': True,
    'use_checkpoint': True,
    'use_image_dataset': False,
    'use_sim_mask': False,
    'inpainting': True
}
Diffusion: {
    'type': 'DiffusionDDIMSR',
    'reverse_diffusion': {
      'schedule': 'cosine',
      'mean_type': 'v',
      'schedule_param':
      {
        'num_timesteps': 1000,
        'zero_terminal_snr': True
      }
    },
    'forward_diffusion': {
      'schedule': 'logsnr_cosine_interp',
      'mean_type': 'v',
      'schedule_param':
      {
        'num_timesteps': 1000,
        'zero_terminal_snr': True,
        'scale_min': 2.0,
        'scale_max': 4.0
      }
    }
}
batch_sizes: {
    "1": 256,
    "4": 96,
    "8": 48,
    "16": 32,
    "24": 24,
    "32": 10
}
visual_train: {
    'type': 'VisualTrainTextImageToVideo',
    'partial_keys': [
        # ['y', 'local_image', 'fps'],
        # ['image', 'local_image', 'fps'],
        ['y', 'image', 'local_image', 'fps']
    ],
    'use_offset_noise': True,
    'guide_scale': 9.0, 
}

chunk_size: 4
decoder_bs: 4
lr: 0.00003

noise_strength: 0.1
# classifier-free guidance
p_zero: 0.0
guide_scale: 3.0
num_steps: 1000000

use_zero_infer: True
viz_interval: 50        # 200
save_ckp_interval: 50   # 500

# Log
log_dir: "workspace/experiments"
log_interval: 1
seed: 6666

total_noise_levels: 700