Repository navigation
Archâspecific options
Bellow are all arch-specific options. The values listed here are the defaults. You don't need to change any of those values and should use the default template configuration files, unless you have a specific user-case.
Note
If you want to train a monochrome model, you need to switch the input and output number of channels to 1, as well as use the color = "y" option on your configuration file (for both dataset and the validation). This does not work with OTF, only paired and single. Also note that some losses will not work on those conditions (such as color_opt) and some networks can expect more channels to work properly (such as DAT and OmniSR).
Important
The option flash_attn breaks compatibility with official code. Take this into consideration in case you want to deploy your model on third-party software such as chaiNNer.
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
Bellow are supported discriminators and their parameters.
type = "metagan"
in_ch = 3
n_class = 1
dims = [48, 96, 192, 288]
blocks = [3, 3, 9, 3]
downs = [4, 4, 2, 2]
se_mode = "SSE"
mlp_ratio = 2.0
attention = true
attn_drop = 0
proj_drop = 0
head_dim = 32
drop = 0.2
sigmoid = false[network_d]
type = "ea2fpn"
class_num = 6
encoder_channels = [512, 256, 128, 64]
pyramid_channels = 64
segmentation_channels = 64
dropout = 0.2Note
The discriminator ea2fpn uses learning rate of 1e-4 with GAN weight of 0.1. Different settings may result in incorrect convergence or NaN.
[network_d]
type = "unet"
num_in_ch = 3
num_feat = 64
skip_connection = trueNote
The discriminator unet uses learning rate of 1e-4 and GAN weight of 0.1. Different settings may result in incorrect convergence or NaN.
[network_d]
type = "dunet"
in_ch = 3
dim = 64Note
The discriminator dunet uses learning rate of 1e-4 and GAN weight of 0.1. Different settings may result in incorrect convergence or NaN.
[network_d]
type = "patchgan"
num_in_ch = 3
num_feat = 64
num_layers = 3
max_nf_mult = 8
use_sigmoid = false
use_sn = true
#norm_type = # NoneNote
The discriminator patchgan uses learning rate of 1e-4 and GAN weight of 0.1. Different settings may result in incorrect convergence or NaN.
Bellow are supported generators and their parameters.
[network_g]
type = "asid"
#type = "asid_d8"
num_in_ch = 3
num_out_ch = 3
num_feat = 48
res_num = 3
block_num = 1
window_size = 8
flash_attn = true
d8 = false
pe = false
bias = true
drop = 0.0Note
ASID is not fully compatible with original implementation.
[network_g]
type = "atd" # "atd_light"
norm = false
img_size = 96
patch_size = 1
in_chans = 3
embed_dim = 210
depths = [ 6, 6, 6, 6, 6, 6 ]
num_heads = [ 6, 6, 6, 6, 6, 6 ]
window_size = 16
category_size = 256
num_tokens = 128
reducted_dim = 20
convffn_kernel_size = 5
mlp_ratio = 2.0
qkv_bias = true
norm_layer = "nn.LayerNorm"
ape = false
patch_norm = true
img_range = 1.0
upsampler = "pixelshuffle"
resi_connection = "1conv"Note
By default, ATD is not fully compatible with original implementation. To make it compatible, use option norm: true.
type = "cfsr"
in_chans = 3
embed_dim = 48
depths = [6, 6]
dw_size = 9
mlp_ratio = 2.0
img_range = 1.0
upsampler = "pixelshuffledirect"
mean_norm = false[network_g]
type = "compact"
num_in_ch = 3
num_out_ch = 3
num_feat = 64
num_conv = 16
act_type = "prelu"[network_g]
type = "craft"
flash_attn = true
in_chans = 3
img_size = 64
window_size = 16
embed_dim = 48
depths = [ 2, 2, 2, 2 ]
num_heads = [ 6, 6, 6, 6 ]
split_size_0 = 4
split_size_1 = 16
mlp_ratio = 2.0
qkv_bias = true
#qk_scale = # None
img_range = 1.0
resi_connection = "1conv"Note
The option flash_attn: true makes it incompatible with official implementation.
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
[network_g]
type = "cugan"
in_channels = 3
out_channels = 3
pro = true[network_g]
type = "dat_small"
#type = "dat_medium"
#type = "dat_2"
img_size = 64
in_chans = 3
embed_dim = 180
split_size = [ 2, 4 ]
depth = [ 2, 2, 2, 2 ]
num_heads = [ 2, 2, 2, 2 ]
expansion_factor = 4
qkv_bias = true
#qk_scale = # None
drop_rate = 0.0
attn_drop_rate = 0.0
drop_path_rate = 0.1
use_chk = false
img_range = 1.0
resi_connection = "1conv"
upsampler = "pixelshuffle"Note
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
type = "dct"
img_size = 64
in_chans = 3
embed_dim = 80
depth = [20]
num_heads = [8]
expansion_factor = 4.0
qkv_bias = true
drop_rate = 0
attn_drop_rate = 0
drop_path_rate = 0.1
act_layer = "nn.GELU"
norm_layer = "nn.LayerNorm"
img_range = 1.0
resi_connection = "3conv"
upsampler = "pixelshuffledirect"[network_g]
type = "dctlsa"
in_nc = 3
out_nc = 3
nf = 55
num_modules = 6
num_head = 5Note
Added Dropout to DCTLSA may not be compatible with official implementation.
[network_g]
type = "ditn"
patch_size = 8
inp_channels = 3
dim = 60
ITL_blocks = 4
SAL_blocks = 4
UFONE_blocks = 1
ffn_expansion_factor = 2.0
bias = false
LayerNorm_type = "WithBias"[network_g]
type = "drct"
#type = "drct_l"
#type = "drct_s"
img_size = 64
patch_size = 1
in_chans = 3
embed_dim = 180
depths = [ 6, 6, 6, 6, 6, 6 ]
num_heads = [ 6, 6, 6, 6, 6, 6 ]
window_size = 16
compress_ratio = 3
squeeze_factor = 30
conv_scale = 0.01
overlap_ratio = 0.5
mlp_ratio = 2.0
qkv_bias = true
#qk_scale = # None
drop_rate = 0.0
attn_drop_rate = 0.0
drop_path_rate = 0.1
norm_layer = "nn.LayerNorm"
ape = false
patch_norm = true
img_range = 1.0
upsampler = "pixelshuffle"
resi_connection = "1conv"
gc = 32Note
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
[network_g]
type = "esc"
#type = `esc_light`
#type = `esc_large`
#type = `esc_fp`
dim = 64
pdim = 16
kernel_size = 13
n_blocks = 5
conv_blocks = 5
window_size = 32
num_heads = 4
exp_ratio = 1.25
attn_type = "sdpa" # "flex", "naive"
is_fp = false
use_dysample = true
realsr = truetype = "flexnet"
type = "metaflexnet"
inp_channels = 3
out_channels = 3
dim = 64
num_blocks = [6,6,6,6,6,6]
window_size = 8
hidden_rate = 4
channel_norm = false
attn_drop = 0
proj_drop = 0
pipeline_type = "linear"
upsampler = "ps"
flash_attn = truetype = "hasn"
in_channels = 3
out_channels = 3
feature_channels = 52[network_g]
type = "hat_m"
#type = "hat_s"
#type = "hat_l"
window_size = 16
img_size = 64
patch_size = 1
in_chans = 3
embed_dim = 96
depths = [ 6, 6, 6, 6 ]
num_heads = [ 6, 6, 6, 6 ]
compress_ratio = 3
squeeze_factor = 30
conv_scale = 0.01
overlap_ratio = 0.5
mlp_ratio = 4.0
qkv_bias = true
#qk_scale = # None
drop_rate = 0.0
attn_drop_rate = 0.0
drop_path_rate = 0.1
ape = false
patch_norm = true
img_range = 1.0
upsampler = "pixelshuffle"
resi_connection = "1conv"Note
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
[network_g]
type = "hit_srf"
#type = "hit_srf_medium"
#type = "hit_srf_large"
img_size = 64
patch_size = 1
in_chans = 3
embed_dim = 60
depths = [6, 6, 6, 6]
num_heads = [6, 6, 6, 6]
base_win_size = [8, 8]
mlp_ratio = 2.0
drop_rate = 0.0
value_drop_rate = 0.0
drop_path_rate = 0.0
ape = false
patch_norm = true
use_checkpoint = false
img_range = 1.0
upsampler="pixelshuffledirect"
resi_connection = "1conv"
hier_win_ratios = [0.5, 1, 2, 4, 6, 8]Note
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
type = "hma"
#type = "hma_medium"
#type = "hma_large"
img_size = 64
patch_size = 1
in_chans = 3
embed_dim = 60
depths = [6, 6, 6, 6]
num_heads = [6, 6, 6, 6]
window_size = 8
interval_size = 4
mlp_ratio = 2.0
qkv_bias = true
#qk_scale= # None
drop_rate = 0.0
attn_drop_rate = 0.0
drop_path_rate = 0.1
ape = false
patch_norm = true
img_range = 1.0
upsampler = "pixelshuffle"
resi_connection = "1convNote
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
type = "krgn"
n_colors = 3
n_feats = 64
n_resgroups = 9
act = "lrelu"
rgb_range = 1.0
dilation = 3type = "lmlt"
#type = "lmlt_tiny"
#type = "lmlt_large"
dim = 60
n_blocks = 8
ffn_scale = 2.0
window_size = 8
drop_rate = 0
attn_drop_rate = 0
drop_path_rate = 0type = "man"
#type = "man_tiny"
#type = "man_light"
n_resblocks = 36
n_resgroups = 1
n_colors = 3
n_feats = 180
res_scale = 1.0type = "mosrv2"
in_ch = 3
scale = 4
n_block = 24
dim = 64
upsampler = "pixelshuffledirect" # "conv", "pixelshuffle", "nearest+conv", "dysample
expansion_ratio = 1.5
mid_dim = 32
unshuffle_mod = truetype = "moesr"
in_ch = 3
out_ch = 3
dim = 64
n_blocks = 9
n_block = 4
expansion_factor = 2.6
expansion_msg = 1.5
upsampler = "pixelshuffledirect"
upsample_dim = 64[network_g]
type = "msdan"
channels = 48
num_DFEB = 8[network_g]
type = "omnisr"
upsampling = 4 # value required, no defaults
window_size = 8 # value required, no defaults
num_in_ch = 3
num_out_ch = 3
num_feat = 64
res_num = 5
block_num = 1
bias = true
pe = true
ffn_bias = truetype = "plainusr"
type = "plainusr_ultra"
type = "plainusr_large"
n_feat = 64
im_feat = [64, 48, 32]
attn_feat = 16[network_g]
type = "plksr"
#type = "plksr_tiny"
dim = 64
n_blocks = 28
kernel_size = 17
split_ratio = 0.25
use_ea = true
ccm_type = "DCCM" # "CCM", "ICCM", "DCCM"
lk_type = "PLK" # "PLK", "SparsePLK", "RectSparsePLK"
sparse_kernels = [ 5, 5, 5, 5 ]
sparse_dilations = [ 1, 2, 3, 4 ]
with_idt = falseNote
The generator plksr uses learning rate of 5e-4 or lower. Different settings may result in incorrect convergence or NaN.
[network_g]
type = "realplksr"
#type = "realplksr_s"
#type = "realplksr_l"
dysample = false
dim = 64
n_blocks = 28
kernel_size = 17
split_ratio = 0.25
use_ea = true
norm_groups = 4
dropout = 0.0Note
The generator realplksr uses learning rate of 5e-4 or lower. Different settings may result in incorrect convergence or NaN.
[network_g]
type = "rcan"
n_resgroups = 10
n_resblocks = 20
n_feats = 64
kernel_size = 3
reduction = 16
n_colors = 3
norm = false[network_g]
type = "rgt"
#type = "rgt_s"
img_size = 64
in_chans = 3
embed_dim = 180
depth = [ 6, 6, 6, 6, 6, 6, 6, 6 ]
num_heads = [ 6, 6, 6, 6, 6, 6, 6, 6 ]
mlp_ratio = 2.0
qkv_bias = true
#qk_scale = # None
drop_rate = 0.0
attn_drop_rate = 0.0
drop_path_rate = 0.1
act_layer = "nn.GELU"
norm_layer = "nn.LayerNorm"
use_chk = false
img_range = 1.0
resi_connection = "1conv"
split_size = [ 8, 32 ]
c_ratio = 0.5Note
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
[network_g]
type = "eimn"
#type = "eimn_a"
#type = "eimn_l"
embed_dims = 64
depths = 1
mlp_ratios = 2.66
drop_rate = 0.0
drop_path_rate = 0.0
num_stages = 16
freeze_param = false
norm = "nn.BatchNorm2d"[network_g]
type = "esrgan"
num_in_ch = 3
num_out_ch = 3
num_feat = 64
num_block = 23
num_grow_ch = 32[network_g]
type = "grformer"
#type = "grformer_medium"
#type = "grformer_large"
img_size = 64
in_chans = 3
window_size = [8, 32]
embed_dim = 60
depths = [ 6, 6, 6, 6 ]
num_heads = [ 3, 3, 3, 3 ]
mlp_ratio = 2.0
qkv_bias = true
#qk_scale = # None
drop_rate = 0.0
attn_drop_rate = 0.0
drop_path_rate = 0.1
norm_layer = "nn.LayerNorm"
ape = false
patch_norm = true
img_range = 1.0[network_g]
type = "safmn"
#type = "safmn_l"
bcie = false
dim = 36
n_blocks = 8
ffn_scale = 2.0[network_g]
type = "span"
num_in_ch = 3
num_out_ch = 3
feature_channels = 48
bias = true
norm = false
img_range = 255 # only applied if norm = true
rgb_mean = [ 0.4488, 0.4371, 0.4040 ] # only applied if norm = trueNote
By default, SPAN is not fully compatible with original implementation. To make it compatible, use option norm: true.
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
[network_g]
type = "spanplus"
#type = "spanplus_sts"
#type = "spanplus_s"
#type = "spanplus_st"
num_in_ch = 3
num_out_ch = 3
blocks = [4]
feature_channels = 48
drop_rate = 0.0
upsampler = "dys" # "lp", "ps", "conv"- only 1x[network_g]
type = "srformer_light"
#type = "srformer_medium"
window_size = 16
img_size = 64
patch_size = 1.0
in_chans = 3
embed_dim = 60
depths = [ 6, 6, 6, 6 ]
num_heads = [ 6, 6, 6, 6 ]
mlp_ratio = 2.0
qkv_bias = true
#qk_scale = # None
drop_rate = 0.0
attn_drop_rate = 0.0
drop_path_rate = 0.1
ape = false
patch_norm = true
use_checkpoint = false
img_range = 1.0
upsampler = "pixelshuffledirect"
resi_connection = "1conv"Note
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.
[network_g]
type = "swinir_small"
#type = "swinir_medium"
#type = "swinir_large"
flash_attn = false
window_size = 8
img_size = 32
patch_size = 1
in_chans = 3
embed_dim = 60
depths = [ 6, 6, 6, 6 ]
num_heads = [ 6, 6, 6, 6 ]
mlp_ratio = 2
qkv_bias = true
#qk_scale = # None
drop_rate = 0.0
attn_drop_rate = 0.0
drop_path_rate = 0.1
ape = false
patch_norm = true
use_checkpoint = false
img_range = 1.0
upsampler = "pixelshuffle"
resi_connection = "1conv"Note
The option flash_attn: true makes it incompatible with official implementation.
rgb_mean has been modified to neutral values, to improve stability. If inference is done using ImageNet values, it may cause different results.