File size: 5,501 Bytes
f2ab299 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 |
model:
target: SUPIR.models.SUPIR_model.SUPIRModel
params:
ae_dtype: bf16
diffusion_dtype: fp16
scale_factor: 0.13025
disable_first_stage_autocast: True
network_wrapper: sgm.modules.diffusionmodules.wrappers.ControlWrapper
denoiser_config:
target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiserWithControl
params:
num_idx: 1000
weighting_config:
target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
scaling_config:
target: sgm.modules.diffusionmodules.denoiser_scaling.EpsScaling
discretization_config:
target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
control_stage_config:
target: SUPIR.modules.SUPIR_v0.GLVControl
params:
adm_in_channels: 2816
num_classes: sequential
use_checkpoint: True
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [4, 2]
num_res_blocks: 2
channel_mult: [1, 2, 4]
num_head_channels: 64
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: [1, 2, 10] # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
# transformer_depth: [1, 1, 4]
context_dim: 2048
spatial_transformer_attn_type: softmax-xformers
legacy: False
input_upscale: 1
network_config:
target: SUPIR.modules.SUPIR_v0.LightGLVUNet
params:
mode: XL-base
project_type: ZeroSFT
project_channel_scale: 2
adm_in_channels: 2816
num_classes: sequential
use_checkpoint: True
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [4, 2]
num_res_blocks: 2
channel_mult: [1, 2, 4]
num_head_channels: 64
use_spatial_transformer: True
use_linear_in_transformer: True
transformer_depth: [1, 2, 10] # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
context_dim: 2048
spatial_transformer_attn_type: softmax-xformers
legacy: False
conditioner_config:
target: sgm.modules.GeneralConditionerWithControl
params:
emb_models:
# crossattn cond
- is_trainable: False
input_key: txt
target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
params:
layer: hidden
layer_idx: 11
# crossattn and vector cond
- is_trainable: False
input_key: txt
target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
params:
arch: ViT-bigG-14
version: laion2b_s39b_b160k
freeze: True
layer: penultimate
always_return_pooled: True
legacy: False
# vector cond
- is_trainable: False
input_key: original_size_as_tuple
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
params:
outdim: 256 # multiplied by two
# vector cond
- is_trainable: False
input_key: crop_coords_top_left
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
params:
outdim: 256 # multiplied by two
# vector cond
- is_trainable: False
input_key: target_size_as_tuple
target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
params:
outdim: 256 # multiplied by two
first_stage_config:
target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
params:
ckpt_path: ~
embed_dim: 4
monitor: val/rec_loss
ddconfig:
attn_type: vanilla-xformers
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult: [ 1, 2, 4, 4 ]
num_res_blocks: 2
attn_resolutions: [ ]
dropout: 0.0
lossconfig:
target: torch.nn.Identity
sampler_config:
target: sgm.modules.diffusionmodules.sampling.TiledRestoreEDMSampler
params:
num_steps: 100
restore_cfg: 4.0
s_churn: 0
s_noise: 1.003
tile_size: 128
tile_stride: 64
discretization_config:
target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
guider_config:
target: sgm.modules.diffusionmodules.guiders.LinearCFG
params:
scale: 7.5
scale_min: 4.0
p_p:
'Cinematic, High Contrast, highly detailed, taken using a Canon EOS R camera,
hyper detailed photo - realistic maximum detail, 32k, Color Grading, ultra HD, extreme meticulous detailing,
skin pore detailing, hyper sharpness, perfect without deformations.'
n_p:
'painting, oil painting, illustration, drawing, art, sketch, oil painting, cartoon, CG Style, 3D render,
unreal engine, blurring, dirty, messy, worst quality, low quality, frames, watermark, signature,
jpeg artifacts, deformed, lowres, over-smooth'
SDXL_CKPT: yushan777/SUPIR/sd_xl_base_1.0_0.9vae.safetensors
SUPIR_CKPT_F: yushan777/SUPIR/SUPIR-v0F.ckpt
SUPIR_CKPT_Q: yushan777/SUPIR/SUPIR-v0Q.ckpt
SUPIR_CKPT: ~
|