raesan-mix
raesan-mix
12 stars
Version: v4.1
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
saturation
Adjust saturation
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
Output
https://files.tungsten.run/uploads/2f6e3c751d0e47dd917872a9465fe6a3/00000-1315008262.webp
https://files.tungsten.run/uploads/34a711e894424950936885c301c855aa/00001-1315008263.webp
https://files.tungsten.run/uploads/92ad50c7f3f1490094bfb99b36dc3f32/00002-1315008264.webp
https://files.tungsten.run/uploads/7a005c5b75734967b177d05f5609669e/00003-1315008265.webp
This example was created by evevalentine2017
Finished in 99.8 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/kl-f8-anime2_fp16.safetensors Full prompt: aakurumi, long hair, twintails, hairband, heterochromia, medium breasts, cleavage, black choker, red ribbon, bare shoulders, gothic, red dress, red bow, detached sleeves, 2k, (Masterpiece), photorealistic, photorealism, 8k, best quality, (ultra-detailed), 1 girl, <lora:CHAR-TokisakiKurumi:1.2>, look looking at viewer, Look at it head-on Full negative prompt: (worst quality:1.4, low quality:1.4, normal quality:1.4), lowres, blurry, monochrome, zombie, (interlocked fingers:1.2), 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:01<00:54, 1.83s/it] 6%|▋ | 2/31 [00:03<00:54, 1.88s/it] 10%|▉ | 3/31 [00:05<00:53, 1.91s/it] 13%|█▎ | 4/31 [00:07<00:50, 1.89s/it] 16%|█▌ | 5/31 [00:09<00:49, 1.91s/it] 19%|█▉ | 6/31 [00:11<00:46, 1.87s/it] 23%|██▎ | 7/31 [00:13<00:44, 1.87s/it] 26%|██▌ | 8/31 [00:14<00:41, 1.82s/it] 29%|██▉ | 9/31 [00:16<00:39, 1.79s/it] 32%|███▏ | 10/31 [00:18<00:37, 1.81s/it] 35%|███▌ | 11/31 [00:20<00:35, 1.80s/it] 39%|███▊ | 12/31 [00:21<00:33, 1.77s/it] 42%|████▏ | 13/31 [00:23<00:32, 1.78s/it] 45%|████▌ | 14/31 [00:25<00:30, 1.81s/it] 48%|████▊ | 15/31 [00:27<00:28, 1.81s/it] 52%|█████▏ | 16/31 [00:29<00:27, 1.83s/it] 55%|█████▍ | 17/31 [00:31<00:25, 1.82s/it] 58%|█████▊ | 18/31 [00:32<00:23, 1.79s/it] 61%|██████▏ | 19/31 [00:34<00:21, 1.82s/it] 65%|██████▍ | 20/31 [00:36<00:20, 1.85s/it] 68%|██████▊ | 21/31 [00:38<00:17, 1.78s/it] 71%|███████ | 22/31 [00:39<00:15, 1.76s/it] 74%|███████▍ | 23/31 [00:41<00:14, 1.82s/it] 77%|███████▋ | 24/31 [00:43<00:12, 1.83s/it] 81%|████████ | 25/31 [00:45<00:11, 1.84s/it] 84%|████████▍ | 26/31 [00:47<00:09, 1.80s/it] 87%|████████▋ | 27/31 [00:48<00:07, 1.76s/it] 90%|█████████ | 28/31 [00:50<00:04, 1.66s/it] 94%|█████████▎| 29/31 [00:51<00:03, 1.58s/it] 97%|█████████▋| 30/31 [00:52<00:01, 1.36s/it] 100%|██████████| 31/31 [00:53<00:00, 1.13s/it] 100%|██████████| 31/31 [00:53<00:00, 1.72s/it] Decoding latents in cuda:0... done in 0.95s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.5ms Speed: 3.6ms preprocess, 7.5ms inference, 26.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:10, 1.25it/s] 14%|█▍ | 2/14 [00:01<00:07, 1.61it/s] 21%|██▏ | 3/14 [00:01<00:06, 1.70it/s] 29%|██▊ | 4/14 [00:02<00:05, 1.88it/s] 36%|███▌ | 5/14 [00:02<00:04, 1.88it/s] 43%|████▎ | 6/14 [00:03<00:04, 1.83it/s] 50%|█████ | 7/14 [00:03<00:03, 1.96it/s] 57%|█████▋ | 8/14 [00:04<00:03, 1.96it/s] 64%|██████▍ | 9/14 [00:04<00:02, 2.06it/s] 71%|███████▏ | 10/14 [00:05<00:01, 2.10it/s] 79%|███████▊ | 11/14 [00:05<00:01, 2.26it/s] 86%|████████▌ | 12/14 [00:06<00:00, 2.23it/s] 93%|█████████▎| 13/14 [00:06<00:00, 2.46it/s] 100%|██████████| 14/14 [00:06<00:00, 2.83it/s] 100%|██████████| 14/14 [00:06<00:00, 2.12it/s] Decoding latents in cuda:0... done in 0.22s Move latents to cpu... done in 0.01s 0: 640x640 (no detections), 10.5ms Speed: 3.4ms preprocess, 10.5ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.1ms Speed: 2.6ms preprocess, 7.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:05, 2.24it/s] 14%|█▍ | 2/14 [00:00<00:05, 2.21it/s] 21%|██▏ | 3/14 [00:01<00:05, 1.95it/s] 29%|██▊ | 4/14 [00:01<00:04, 2.09it/s] 36%|███▌ | 5/14 [00:02<00:04, 2.00it/s] 43%|████▎ | 6/14 [00:03<00:04, 1.87it/s] 50%|█████ | 7/14 [00:03<00:03, 1.86it/s] 57%|█████▋ | 8/14 [00:04<00:03, 1.91it/s] 64%|██████▍ | 9/14 [00:04<00:02, 1.89it/s] 71%|███████▏ | 10/14 [00:05<00:02, 1.95it/s] 79%|███████▊ | 11/14 [00:05<00:01, 2.15it/s] 86%|████████▌ | 12/14 [00:05<00:00, 2.17it/s] 93%|█████████▎| 13/14 [00:06<00:00, 2.38it/s] 100%|██████████| 14/14 [00:06<00:00, 2.72it/s] 100%|██████████| 14/14 [00:06<00:00, 2.16it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 10.5ms Speed: 3.5ms preprocess, 10.5ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:07, 1.71it/s] 14%|█▍ | 2/14 [00:01<00:06, 1.77it/s] 21%|██▏ | 3/14 [00:01<00:05, 1.85it/s] 29%|██▊ | 4/14 [00:02<00:04, 2.02it/s] 36%|███▌ | 5/14 [00:02<00:04, 1.98it/s] 43%|████▎ | 6/14 [00:03<00:04, 1.97it/s] 50%|█████ | 7/14 [00:03<00:03, 1.93it/s] 57%|█████▋ | 8/14 [00:04<00:03, 1.85it/s] 64%|██████▍ | 9/14 [00:04<00:02, 1.98it/s] 71%|███████▏ | 10/14 [00:05<00:01, 2.12it/s] 79%|███████▊ | 11/14 [00:05<00:01, 2.31it/s] 86%|████████▌ | 12/14 [00:05<00:00, 2.23it/s] 93%|█████████▎| 13/14 [00:06<00:00, 2.41it/s] 100%|██████████| 14/14 [00:06<00:00, 2.80it/s] 100%|██████████| 14/14 [00:06<00:00, 2.17it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 11.0ms Speed: 3.8ms preprocess, 11.0ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:07, 1.68it/s] 14%|█▍ | 2/14 [00:01<00:07, 1.71it/s] 21%|██▏ | 3/14 [00:01<00:05, 1.90it/s] 29%|██▊ | 4/14 [00:02<00:05, 1.84it/s] 36%|███▌ | 5/14 [00:02<00:04, 1.84it/s] 43%|████▎ | 6/14 [00:03<00:04, 1.83it/s] 50%|█████ | 7/14 [00:03<00:03, 1.92it/s] 57%|█████▋ | 8/14 [00:04<00:03, 1.86it/s] 64%|██████▍ | 9/14 [00:04<00:02, 1.90it/s] 71%|███████▏ | 10/14 [00:05<00:01, 2.06it/s] 79%|███████▊ | 11/14 [00:05<00:01, 2.24it/s] 86%|████████▌ | 12/14 [00:05<00:00, 2.34it/s] 93%|█████████▎| 13/14 [00:06<00:00, 2.68it/s] 100%|██████████| 14/14 [00:06<00:00, 3.15it/s] 100%|██████████| 14/14 [00:06<00:00, 2.18it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 6.7ms Speed: 2.8ms preprocess, 6.7ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. 0: 640x640 1 face, 7.2ms Speed: 2.6ms preprocess, 7.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:05, 2.29it/s] 14%|█▍ | 2/14 [00:00<00:05, 2.26it/s] 21%|██▏ | 3/14 [00:01<00:04, 2.21it/s] 29%|██▊ | 4/14 [00:01<00:04, 2.27it/s] 36%|███▌ | 5/14 [00:02<00:03, 2.30it/s] 43%|████▎ | 6/14 [00:02<00:03, 2.26it/s] 50%|█████ | 7/14 [00:03<00:03, 2.28it/s] 57%|█████▋ | 8/14 [00:03<00:02, 2.26it/s] 64%|██████▍ | 9/14 [00:03<00:02, 2.31it/s] 71%|███████▏ | 10/14 [00:04<00:01, 2.37it/s] 79%|███████▊ | 11/14 [00:04<00:01, 2.49it/s] 86%|████████▌ | 12/14 [00:05<00:00, 2.51it/s] 93%|█████████▎| 13/14 [00:05<00:00, 2.82it/s] 100%|██████████| 14/14 [00:05<00:00, 3.28it/s] 100%|██████████| 14/14 [00:05<00:00, 2.53it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.0ms Speed: 2.7ms preprocess, 7.0ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 4 with 2nd settings. Uploading outputs... Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
saturation
Adjust saturation
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
https://files.tungsten.run/uploads/2f6e3c751d0e47dd917872a9465fe6a3/00000-1315008262.webp
https://files.tungsten.run/uploads/34a711e894424950936885c301c855aa/00001-1315008263.webp
https://files.tungsten.run/uploads/92ad50c7f3f1490094bfb99b36dc3f32/00002-1315008264.webp
https://files.tungsten.run/uploads/7a005c5b75734967b177d05f5609669e/00003-1315008265.webp
This example was created by evevalentine2017
Finished in 99.8 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/kl-f8-anime2_fp16.safetensors Full prompt: aakurumi, long hair, twintails, hairband, heterochromia, medium breasts, cleavage, black choker, red ribbon, bare shoulders, gothic, red dress, red bow, detached sleeves, 2k, (Masterpiece), photorealistic, photorealism, 8k, best quality, (ultra-detailed), 1 girl, <lora:CHAR-TokisakiKurumi:1.2>, look looking at viewer, Look at it head-on Full negative prompt: (worst quality:1.4, low quality:1.4, normal quality:1.4), lowres, blurry, monochrome, zombie, (interlocked fingers:1.2), 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:01<00:54, 1.83s/it] 6%|▋ | 2/31 [00:03<00:54, 1.88s/it] 10%|▉ | 3/31 [00:05<00:53, 1.91s/it] 13%|█▎ | 4/31 [00:07<00:50, 1.89s/it] 16%|█▌ | 5/31 [00:09<00:49, 1.91s/it] 19%|█▉ | 6/31 [00:11<00:46, 1.87s/it] 23%|██▎ | 7/31 [00:13<00:44, 1.87s/it] 26%|██▌ | 8/31 [00:14<00:41, 1.82s/it] 29%|██▉ | 9/31 [00:16<00:39, 1.79s/it] 32%|███▏ | 10/31 [00:18<00:37, 1.81s/it] 35%|███▌ | 11/31 [00:20<00:35, 1.80s/it] 39%|███▊ | 12/31 [00:21<00:33, 1.77s/it] 42%|████▏ | 13/31 [00:23<00:32, 1.78s/it] 45%|████▌ | 14/31 [00:25<00:30, 1.81s/it] 48%|████▊ | 15/31 [00:27<00:28, 1.81s/it] 52%|█████▏ | 16/31 [00:29<00:27, 1.83s/it] 55%|█████▍ | 17/31 [00:31<00:25, 1.82s/it] 58%|█████▊ | 18/31 [00:32<00:23, 1.79s/it] 61%|██████▏ | 19/31 [00:34<00:21, 1.82s/it] 65%|██████▍ | 20/31 [00:36<00:20, 1.85s/it] 68%|██████▊ | 21/31 [00:38<00:17, 1.78s/it] 71%|███████ | 22/31 [00:39<00:15, 1.76s/it] 74%|███████▍ | 23/31 [00:41<00:14, 1.82s/it] 77%|███████▋ | 24/31 [00:43<00:12, 1.83s/it] 81%|████████ | 25/31 [00:45<00:11, 1.84s/it] 84%|████████▍ | 26/31 [00:47<00:09, 1.80s/it] 87%|████████▋ | 27/31 [00:48<00:07, 1.76s/it] 90%|█████████ | 28/31 [00:50<00:04, 1.66s/it] 94%|█████████▎| 29/31 [00:51<00:03, 1.58s/it] 97%|█████████▋| 30/31 [00:52<00:01, 1.36s/it] 100%|██████████| 31/31 [00:53<00:00, 1.13s/it] 100%|██████████| 31/31 [00:53<00:00, 1.72s/it] Decoding latents in cuda:0... done in 0.95s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.5ms Speed: 3.6ms preprocess, 7.5ms inference, 26.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:10, 1.25it/s] 14%|█▍ | 2/14 [00:01<00:07, 1.61it/s] 21%|██▏ | 3/14 [00:01<00:06, 1.70it/s] 29%|██▊ | 4/14 [00:02<00:05, 1.88it/s] 36%|███▌ | 5/14 [00:02<00:04, 1.88it/s] 43%|████▎ | 6/14 [00:03<00:04, 1.83it/s] 50%|█████ | 7/14 [00:03<00:03, 1.96it/s] 57%|█████▋ | 8/14 [00:04<00:03, 1.96it/s] 64%|██████▍ | 9/14 [00:04<00:02, 2.06it/s] 71%|███████▏ | 10/14 [00:05<00:01, 2.10it/s] 79%|███████▊ | 11/14 [00:05<00:01, 2.26it/s] 86%|████████▌ | 12/14 [00:06<00:00, 2.23it/s] 93%|█████████▎| 13/14 [00:06<00:00, 2.46it/s] 100%|██████████| 14/14 [00:06<00:00, 2.83it/s] 100%|██████████| 14/14 [00:06<00:00, 2.12it/s] Decoding latents in cuda:0... done in 0.22s Move latents to cpu... done in 0.01s 0: 640x640 (no detections), 10.5ms Speed: 3.4ms preprocess, 10.5ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.1ms Speed: 2.6ms preprocess, 7.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:05, 2.24it/s] 14%|█▍ | 2/14 [00:00<00:05, 2.21it/s] 21%|██▏ | 3/14 [00:01<00:05, 1.95it/s] 29%|██▊ | 4/14 [00:01<00:04, 2.09it/s] 36%|███▌ | 5/14 [00:02<00:04, 2.00it/s] 43%|████▎ | 6/14 [00:03<00:04, 1.87it/s] 50%|█████ | 7/14 [00:03<00:03, 1.86it/s] 57%|█████▋ | 8/14 [00:04<00:03, 1.91it/s] 64%|██████▍ | 9/14 [00:04<00:02, 1.89it/s] 71%|███████▏ | 10/14 [00:05<00:02, 1.95it/s] 79%|███████▊ | 11/14 [00:05<00:01, 2.15it/s] 86%|████████▌ | 12/14 [00:05<00:00, 2.17it/s] 93%|█████████▎| 13/14 [00:06<00:00, 2.38it/s] 100%|██████████| 14/14 [00:06<00:00, 2.72it/s] 100%|██████████| 14/14 [00:06<00:00, 2.16it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 10.5ms Speed: 3.5ms preprocess, 10.5ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:07, 1.71it/s] 14%|█▍ | 2/14 [00:01<00:06, 1.77it/s] 21%|██▏ | 3/14 [00:01<00:05, 1.85it/s] 29%|██▊ | 4/14 [00:02<00:04, 2.02it/s] 36%|███▌ | 5/14 [00:02<00:04, 1.98it/s] 43%|████▎ | 6/14 [00:03<00:04, 1.97it/s] 50%|█████ | 7/14 [00:03<00:03, 1.93it/s] 57%|█████▋ | 8/14 [00:04<00:03, 1.85it/s] 64%|██████▍ | 9/14 [00:04<00:02, 1.98it/s] 71%|███████▏ | 10/14 [00:05<00:01, 2.12it/s] 79%|███████▊ | 11/14 [00:05<00:01, 2.31it/s] 86%|████████▌ | 12/14 [00:05<00:00, 2.23it/s] 93%|█████████▎| 13/14 [00:06<00:00, 2.41it/s] 100%|██████████| 14/14 [00:06<00:00, 2.80it/s] 100%|██████████| 14/14 [00:06<00:00, 2.17it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 11.0ms Speed: 3.8ms preprocess, 11.0ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:07, 1.68it/s] 14%|█▍ | 2/14 [00:01<00:07, 1.71it/s] 21%|██▏ | 3/14 [00:01<00:05, 1.90it/s] 29%|██▊ | 4/14 [00:02<00:05, 1.84it/s] 36%|███▌ | 5/14 [00:02<00:04, 1.84it/s] 43%|████▎ | 6/14 [00:03<00:04, 1.83it/s] 50%|█████ | 7/14 [00:03<00:03, 1.92it/s] 57%|█████▋ | 8/14 [00:04<00:03, 1.86it/s] 64%|██████▍ | 9/14 [00:04<00:02, 1.90it/s] 71%|███████▏ | 10/14 [00:05<00:01, 2.06it/s] 79%|███████▊ | 11/14 [00:05<00:01, 2.24it/s] 86%|████████▌ | 12/14 [00:05<00:00, 2.34it/s] 93%|█████████▎| 13/14 [00:06<00:00, 2.68it/s] 100%|██████████| 14/14 [00:06<00:00, 3.15it/s] 100%|██████████| 14/14 [00:06<00:00, 2.18it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 6.7ms Speed: 2.8ms preprocess, 6.7ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. 0: 640x640 1 face, 7.2ms Speed: 2.6ms preprocess, 7.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:05, 2.29it/s] 14%|█▍ | 2/14 [00:00<00:05, 2.26it/s] 21%|██▏ | 3/14 [00:01<00:04, 2.21it/s] 29%|██▊ | 4/14 [00:01<00:04, 2.27it/s] 36%|███▌ | 5/14 [00:02<00:03, 2.30it/s] 43%|████▎ | 6/14 [00:02<00:03, 2.26it/s] 50%|█████ | 7/14 [00:03<00:03, 2.28it/s] 57%|█████▋ | 8/14 [00:03<00:02, 2.26it/s] 64%|██████▍ | 9/14 [00:03<00:02, 2.31it/s] 71%|███████▏ | 10/14 [00:04<00:01, 2.37it/s] 79%|███████▊ | 11/14 [00:04<00:01, 2.49it/s] 86%|████████▌ | 12/14 [00:05<00:00, 2.51it/s] 93%|█████████▎| 13/14 [00:05<00:00, 2.82it/s] 100%|██████████| 14/14 [00:05<00:00, 3.28it/s] 100%|██████████| 14/14 [00:05<00:00, 2.53it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.0ms Speed: 2.7ms preprocess, 7.0ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 4 with 2nd settings. Uploading outputs... Finished.