tungsten-logo
Sign In
Hooded Cutie with Aurora SDXL
aurora-sdxl:v1.0
evevalentine2017
evevalentine2017
·
Mar 15
389
Input
prompt
Specify things to see in the output
fcNeg, Edgy and mysterious: A 1024px close-up of an enigmatic figure donning a hoodie embodies the essence of an edgy teen assassin. This female assassin, inspired by the ominous and thrilling style of Apex Legends, exudes a captivating aura. Apt for a profile picture or avatar image, this headshot, with a hint of trigger anime artstyle, is tailor-made for Discord profiles, esports logos, or even as a game logo. The cyberpunk undertones add an extra layer of intrigue, making this unknown artstyle a perfect choice for those seeking a striking and mysterious visual identity.
negative_prompt
Specify things to not see in the output
Unrealistic AND fake, anime, pixar, ugly, bad art, imperfections, cartoony, malformed, noisy, open mouth, (blur), (guassian blur), paintings, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast text, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
1714589370
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ SDE
samping_steps
Number of denoising steps
50
cfg_scale
Scale for classifier-free guidance
7.5
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
None
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.
false
Output
https://files.tungsten.run/uploads/429ca8d2b10549a7afa2edfae022c1b6/00000-1714589370.webp
https://files.tungsten.run/uploads/df0b5f6144dc487db4029a7663138c0e/00001-1714589371.webp
https://files.tungsten.run/uploads/5f61242a756e420e95152e11f0368216/00002-1714589372.webp
Finished in 304.7 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: fcNeg, Edgy and mysterious: A 1024px close-up of an enigmatic figure donning a hoodie embodies the essence of an edgy teen assassin. This female assassin, inspired by the ominous and thrilling style of Apex Legends, exudes a captivating aura. Apt for a profile picture or avatar image, this headshot, with a hint of trigger anime artstyle, is tailor-made for Discord profiles, esports logos, or even as a game logo. The cyberpunk undertones add an extra layer of intrigue, making this unknown artstyle a perfect choice for those seeking a striking and mysterious visual identity. Full negative prompt: Unrealistic AND fake, anime, pixar, ugly, bad art, imperfections, cartoony, malformed, noisy, open mouth, (blur), (guassian blur), paintings, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast text, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:02<02:26, 2.98s/it] 4%|▍ | 2/50 [00:06<02:45, 3.44s/it] 6%|▌ | 3/50 [00:10<02:57, 3.77s/it] 8%|▊ | 4/50 [00:14<02:55, 3.82s/it] 10%|█ | 5/50 [00:18<02:53, 3.86s/it] 12%|█▏ | 6/50 [00:23<03:01, 4.12s/it] 14%|█▍ | 7/50 [00:27<02:58, 4.16s/it] 16%|█▌ | 8/50 [00:31<02:51, 4.09s/it] 18%|█▊ | 9/50 [00:35<02:45, 4.04s/it] 20%|██ | 10/50 [00:39<02:37, 3.95s/it] 22%|██▏ | 11/50 [00:43<02:35, 3.98s/it] 24%|██▍ | 12/50 [00:47<02:31, 4.00s/it] 26%|██▌ | 13/50 [00:50<02:24, 3.91s/it] 28%|██▊ | 14/50 [00:55<02:22, 3.96s/it] 30%|███ | 15/50 [00:59<02:18, 3.95s/it] 32%|███▏ | 16/50 [01:02<02:13, 3.92s/it] 34%|███▍ | 17/50 [01:06<02:01, 3.69s/it] 36%|███▌ | 18/50 [01:09<01:58, 3.70s/it] 38%|███▊ | 19/50 [01:13<01:55, 3.73s/it] 40%|████ | 20/50 [01:17<01:51, 3.73s/it] 42%|████▏ | 21/50 [01:20<01:44, 3.62s/it] 44%|████▍ | 22/50 [01:24<01:41, 3.64s/it] 46%|████▌ | 23/50 [01:28<01:38, 3.66s/it] 48%|████▊ | 24/50 [01:31<01:35, 3.68s/it] 50%|█████ | 25/50 [01:35<01:28, 3.56s/it] 52%|█████▏ | 26/50 [01:38<01:25, 3.56s/it] 54%|█████▍ | 27/50 [01:42<01:23, 3.61s/it] 56%|█████▌ | 28/50 [01:46<01:20, 3.66s/it] 58%|█████▊ | 29/50 [01:49<01:12, 3.45s/it] 60%|██████ | 30/50 [01:52<01:06, 3.32s/it] 62%|██████▏ | 31/50 [01:54<01:00, 3.19s/it] 64%|██████▍ | 32/50 [01:58<00:58, 3.26s/it] 66%|██████▌ | 33/50 [02:01<00:52, 3.11s/it] 68%|██████▊ | 34/50 [02:04<00:52, 3.28s/it] 70%|███████ | 35/50 [02:08<00:52, 3.49s/it] 72%|███████▏ | 36/50 [02:11<00:46, 3.36s/it] 74%|███████▍ | 37/50 [02:15<00:42, 3.30s/it] 76%|███████▌ | 38/50 [02:18<00:38, 3.24s/it] 78%|███████▊ | 39/50 [02:21<00:34, 3.18s/it] 80%|████████ | 40/50 [02:24<00:33, 3.33s/it] 82%|████████▏ | 41/50 [02:27<00:29, 3.23s/it] 84%|████████▍ | 42/50 [02:30<00:25, 3.21s/it] 86%|████████▌ | 43/50 [02:34<00:22, 3.20s/it] 88%|████████▊ | 44/50 [02:37<00:19, 3.17s/it] 90%|█████████ | 45/50 [02:40<00:16, 3.31s/it] 92%|█████████▏| 46/50 [02:44<00:13, 3.44s/it] 94%|█████████▍| 47/50 [02:47<00:09, 3.30s/it] 96%|█████████▌| 48/50 [02:50<00:06, 3.28s/it] 98%|█████████▊| 49/50 [02:53<00:03, 3.11s/it] 100%|██████████| 50/50 [02:54<00:00, 2.44s/it] 100%|██████████| 50/50 [02:54<00:00, 3.49s/it] Decoding latents in cuda:0... done in 1.71s Move latents to cpu... done in 0.03s 0: 640x480 1 face, 167.0ms Speed: 3.6ms preprocess, 167.0ms inference, 24.7ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:02<00:44, 2.01s/it] 9%|▊ | 2/23 [00:03<00:36, 1.75s/it] 13%|█▎ | 3/23 [00:05<00:33, 1.69s/it] 17%|█▋ | 4/23 [00:06<00:31, 1.64s/it] 22%|██▏ | 5/23 [00:08<00:30, 1.67s/it] 26%|██▌ | 6/23 [00:10<00:27, 1.64s/it] 30%|███ | 7/23 [00:11<00:27, 1.72s/it] 35%|███▍ | 8/23 [00:13<00:26, 1.78s/it] 39%|███▉ | 9/23 [00:15<00:24, 1.73s/it] 43%|████▎ | 10/23 [00:17<00:22, 1.70s/it] 48%|████▊ | 11/23 [00:18<00:20, 1.71s/it] 52%|█████▏ | 12/23 [00:20<00:18, 1.67s/it] 57%|█████▋ | 13/23 [00:22<00:17, 1.71s/it] 61%|██████ | 14/23 [00:23<00:15, 1.70s/it] 65%|██████▌ | 15/23 [00:25<00:13, 1.68s/it] 70%|██████▉ | 16/23 [00:27<00:11, 1.66s/it] 74%|███████▍ | 17/23 [00:28<00:09, 1.65s/it] 78%|███████▊ | 18/23 [00:30<00:08, 1.69s/it] 83%|████████▎ | 19/23 [00:32<00:06, 1.71s/it] 87%|████████▋ | 20/23 [00:33<00:05, 1.68s/it] 91%|█████████▏| 21/23 [00:35<00:03, 1.68s/it] 96%|█████████▌| 22/23 [00:37<00:01, 1.64s/it] 100%|██████████| 23/23 [00:37<00:00, 1.33s/it] 100%|██████████| 23/23 [00:37<00:00, 1.64s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.7ms Speed: 2.5ms preprocess, 8.7ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:01<00:41, 1.90s/it] 9%|▊ | 2/23 [00:03<00:36, 1.72s/it] 13%|█▎ | 3/23 [00:05<00:33, 1.68s/it] 17%|█▋ | 4/23 [00:06<00:31, 1.64s/it] 22%|██▏ | 5/23 [00:08<00:30, 1.69s/it] 26%|██▌ | 6/23 [00:10<00:27, 1.64s/it] 30%|███ | 7/23 [00:11<00:27, 1.71s/it] 35%|███▍ | 8/23 [00:13<00:26, 1.77s/it] 39%|███▉ | 9/23 [00:15<00:24, 1.72s/it] 43%|████▎ | 10/23 [00:17<00:22, 1.71s/it] 48%|████▊ | 11/23 [00:18<00:20, 1.71s/it] 52%|█████▏ | 12/23 [00:20<00:18, 1.69s/it] 57%|█████▋ | 13/23 [00:22<00:17, 1.76s/it] 61%|██████ | 14/23 [00:24<00:15, 1.73s/it] 65%|██████▌ | 15/23 [00:25<00:13, 1.71s/it] 70%|██████▉ | 16/23 [00:27<00:11, 1.70s/it] 74%|███████▍ | 17/23 [00:29<00:10, 1.69s/it] 78%|███████▊ | 18/23 [00:30<00:08, 1.74s/it] 83%|████████▎ | 19/23 [00:32<00:07, 1.76s/it] 87%|████████▋ | 20/23 [00:34<00:05, 1.73s/it] 91%|█████████▏| 21/23 [00:36<00:03, 1.74s/it] 96%|█████████▌| 22/23 [00:37<00:01, 1.69s/it] 100%|██████████| 23/23 [00:38<00:00, 1.37s/it] 100%|██████████| 23/23 [00:38<00:00, 1.67s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.2ms Speed: 2.3ms preprocess, 8.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:01<00:41, 1.89s/it] 9%|▊ | 2/23 [00:03<00:35, 1.70s/it] 13%|█▎ | 3/23 [00:05<00:33, 1.69s/it] 17%|█▋ | 4/23 [00:06<00:31, 1.65s/it] 22%|██▏ | 5/23 [00:08<00:31, 1.73s/it] 26%|██▌ | 6/23 [00:10<00:29, 1.71s/it] 30%|███ | 7/23 [00:12<00:28, 1.75s/it] 35%|███▍ | 8/23 [00:14<00:27, 1.82s/it] 39%|███▉ | 9/23 [00:15<00:24, 1.76s/it] 43%|████▎ | 10/23 [00:17<00:22, 1.74s/it] 48%|████▊ | 11/23 [00:19<00:20, 1.72s/it] 52%|█████▏ | 12/23 [00:20<00:18, 1.70s/it] 57%|█████▋ | 13/23 [00:22<00:17, 1.78s/it] 61%|██████ | 14/23 [00:24<00:15, 1.75s/it] 65%|██████▌ | 15/23 [00:26<00:13, 1.72s/it] 70%|██████▉ | 16/23 [00:27<00:11, 1.71s/it] 74%|███████▍ | 17/23 [00:29<00:10, 1.71s/it] 78%|███████▊ | 18/23 [00:31<00:08, 1.75s/it] 83%|████████▎ | 19/23 [00:33<00:07, 1.77s/it] 87%|████████▋ | 20/23 [00:34<00:05, 1.76s/it] 91%|█████████▏| 21/23 [00:36<00:03, 1.74s/it] 96%|█████████▌| 22/23 [00:38<00:01, 1.69s/it] 100%|██████████| 23/23 [00:38<00:00, 1.39s/it] 100%|██████████| 23/23 [00:38<00:00, 1.69s/it] Decoding latents in cuda:0... done in 0.56s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt
Specify things to see in the output
fcNeg, Edgy and mysterious: A 1024px close-up of an enigmatic figure donning a hoodie embodies the essence of an edgy teen assassin. This female assassin, inspired by the ominous and thrilling style of Apex Legends, exudes a captivating aura. Apt for a profile picture or avatar image, this headshot, with a hint of trigger anime artstyle, is tailor-made for Discord profiles, esports logos, or even as a game logo. The cyberpunk undertones add an extra layer of intrigue, making this unknown artstyle a perfect choice for those seeking a striking and mysterious visual identity.
negative_prompt
Specify things to not see in the output
Unrealistic AND fake, anime, pixar, ugly, bad art, imperfections, cartoony, malformed, noisy, open mouth, (blur), (guassian blur), paintings, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast text, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
1714589370
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ SDE
samping_steps
Number of denoising steps
50
cfg_scale
Scale for classifier-free guidance
7.5
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
None
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.
false
https://files.tungsten.run/uploads/429ca8d2b10549a7afa2edfae022c1b6/00000-1714589370.webp
https://files.tungsten.run/uploads/df0b5f6144dc487db4029a7663138c0e/00001-1714589371.webp
https://files.tungsten.run/uploads/5f61242a756e420e95152e11f0368216/00002-1714589372.webp
Finished in 304.7 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: fcNeg, Edgy and mysterious: A 1024px close-up of an enigmatic figure donning a hoodie embodies the essence of an edgy teen assassin. This female assassin, inspired by the ominous and thrilling style of Apex Legends, exudes a captivating aura. Apt for a profile picture or avatar image, this headshot, with a hint of trigger anime artstyle, is tailor-made for Discord profiles, esports logos, or even as a game logo. The cyberpunk undertones add an extra layer of intrigue, making this unknown artstyle a perfect choice for those seeking a striking and mysterious visual identity. Full negative prompt: Unrealistic AND fake, anime, pixar, ugly, bad art, imperfections, cartoony, malformed, noisy, open mouth, (blur), (guassian blur), paintings, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast text, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:02<02:26, 2.98s/it] 4%|▍ | 2/50 [00:06<02:45, 3.44s/it] 6%|▌ | 3/50 [00:10<02:57, 3.77s/it] 8%|▊ | 4/50 [00:14<02:55, 3.82s/it] 10%|█ | 5/50 [00:18<02:53, 3.86s/it] 12%|█▏ | 6/50 [00:23<03:01, 4.12s/it] 14%|█▍ | 7/50 [00:27<02:58, 4.16s/it] 16%|█▌ | 8/50 [00:31<02:51, 4.09s/it] 18%|█▊ | 9/50 [00:35<02:45, 4.04s/it] 20%|██ | 10/50 [00:39<02:37, 3.95s/it] 22%|██▏ | 11/50 [00:43<02:35, 3.98s/it] 24%|██▍ | 12/50 [00:47<02:31, 4.00s/it] 26%|██▌ | 13/50 [00:50<02:24, 3.91s/it] 28%|██▊ | 14/50 [00:55<02:22, 3.96s/it] 30%|███ | 15/50 [00:59<02:18, 3.95s/it] 32%|███▏ | 16/50 [01:02<02:13, 3.92s/it] 34%|███▍ | 17/50 [01:06<02:01, 3.69s/it] 36%|███▌ | 18/50 [01:09<01:58, 3.70s/it] 38%|███▊ | 19/50 [01:13<01:55, 3.73s/it] 40%|████ | 20/50 [01:17<01:51, 3.73s/it] 42%|████▏ | 21/50 [01:20<01:44, 3.62s/it] 44%|████▍ | 22/50 [01:24<01:41, 3.64s/it] 46%|████▌ | 23/50 [01:28<01:38, 3.66s/it] 48%|████▊ | 24/50 [01:31<01:35, 3.68s/it] 50%|█████ | 25/50 [01:35<01:28, 3.56s/it] 52%|█████▏ | 26/50 [01:38<01:25, 3.56s/it] 54%|█████▍ | 27/50 [01:42<01:23, 3.61s/it] 56%|█████▌ | 28/50 [01:46<01:20, 3.66s/it] 58%|█████▊ | 29/50 [01:49<01:12, 3.45s/it] 60%|██████ | 30/50 [01:52<01:06, 3.32s/it] 62%|██████▏ | 31/50 [01:54<01:00, 3.19s/it] 64%|██████▍ | 32/50 [01:58<00:58, 3.26s/it] 66%|██████▌ | 33/50 [02:01<00:52, 3.11s/it] 68%|██████▊ | 34/50 [02:04<00:52, 3.28s/it] 70%|███████ | 35/50 [02:08<00:52, 3.49s/it] 72%|███████▏ | 36/50 [02:11<00:46, 3.36s/it] 74%|███████▍ | 37/50 [02:15<00:42, 3.30s/it] 76%|███████▌ | 38/50 [02:18<00:38, 3.24s/it] 78%|███████▊ | 39/50 [02:21<00:34, 3.18s/it] 80%|████████ | 40/50 [02:24<00:33, 3.33s/it] 82%|████████▏ | 41/50 [02:27<00:29, 3.23s/it] 84%|████████▍ | 42/50 [02:30<00:25, 3.21s/it] 86%|████████▌ | 43/50 [02:34<00:22, 3.20s/it] 88%|████████▊ | 44/50 [02:37<00:19, 3.17s/it] 90%|█████████ | 45/50 [02:40<00:16, 3.31s/it] 92%|█████████▏| 46/50 [02:44<00:13, 3.44s/it] 94%|█████████▍| 47/50 [02:47<00:09, 3.30s/it] 96%|█████████▌| 48/50 [02:50<00:06, 3.28s/it] 98%|█████████▊| 49/50 [02:53<00:03, 3.11s/it] 100%|██████████| 50/50 [02:54<00:00, 2.44s/it] 100%|██████████| 50/50 [02:54<00:00, 3.49s/it] Decoding latents in cuda:0... done in 1.71s Move latents to cpu... done in 0.03s 0: 640x480 1 face, 167.0ms Speed: 3.6ms preprocess, 167.0ms inference, 24.7ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:02<00:44, 2.01s/it] 9%|▊ | 2/23 [00:03<00:36, 1.75s/it] 13%|█▎ | 3/23 [00:05<00:33, 1.69s/it] 17%|█▋ | 4/23 [00:06<00:31, 1.64s/it] 22%|██▏ | 5/23 [00:08<00:30, 1.67s/it] 26%|██▌ | 6/23 [00:10<00:27, 1.64s/it] 30%|███ | 7/23 [00:11<00:27, 1.72s/it] 35%|███▍ | 8/23 [00:13<00:26, 1.78s/it] 39%|███▉ | 9/23 [00:15<00:24, 1.73s/it] 43%|████▎ | 10/23 [00:17<00:22, 1.70s/it] 48%|████▊ | 11/23 [00:18<00:20, 1.71s/it] 52%|█████▏ | 12/23 [00:20<00:18, 1.67s/it] 57%|█████▋ | 13/23 [00:22<00:17, 1.71s/it] 61%|██████ | 14/23 [00:23<00:15, 1.70s/it] 65%|██████▌ | 15/23 [00:25<00:13, 1.68s/it] 70%|██████▉ | 16/23 [00:27<00:11, 1.66s/it] 74%|███████▍ | 17/23 [00:28<00:09, 1.65s/it] 78%|███████▊ | 18/23 [00:30<00:08, 1.69s/it] 83%|████████▎ | 19/23 [00:32<00:06, 1.71s/it] 87%|████████▋ | 20/23 [00:33<00:05, 1.68s/it] 91%|█████████▏| 21/23 [00:35<00:03, 1.68s/it] 96%|█████████▌| 22/23 [00:37<00:01, 1.64s/it] 100%|██████████| 23/23 [00:37<00:00, 1.33s/it] 100%|██████████| 23/23 [00:37<00:00, 1.64s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.7ms Speed: 2.5ms preprocess, 8.7ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:01<00:41, 1.90s/it] 9%|▊ | 2/23 [00:03<00:36, 1.72s/it] 13%|█▎ | 3/23 [00:05<00:33, 1.68s/it] 17%|█▋ | 4/23 [00:06<00:31, 1.64s/it] 22%|██▏ | 5/23 [00:08<00:30, 1.69s/it] 26%|██▌ | 6/23 [00:10<00:27, 1.64s/it] 30%|███ | 7/23 [00:11<00:27, 1.71s/it] 35%|███▍ | 8/23 [00:13<00:26, 1.77s/it] 39%|███▉ | 9/23 [00:15<00:24, 1.72s/it] 43%|████▎ | 10/23 [00:17<00:22, 1.71s/it] 48%|████▊ | 11/23 [00:18<00:20, 1.71s/it] 52%|█████▏ | 12/23 [00:20<00:18, 1.69s/it] 57%|█████▋ | 13/23 [00:22<00:17, 1.76s/it] 61%|██████ | 14/23 [00:24<00:15, 1.73s/it] 65%|██████▌ | 15/23 [00:25<00:13, 1.71s/it] 70%|██████▉ | 16/23 [00:27<00:11, 1.70s/it] 74%|███████▍ | 17/23 [00:29<00:10, 1.69s/it] 78%|███████▊ | 18/23 [00:30<00:08, 1.74s/it] 83%|████████▎ | 19/23 [00:32<00:07, 1.76s/it] 87%|████████▋ | 20/23 [00:34<00:05, 1.73s/it] 91%|█████████▏| 21/23 [00:36<00:03, 1.74s/it] 96%|█████████▌| 22/23 [00:37<00:01, 1.69s/it] 100%|██████████| 23/23 [00:38<00:00, 1.37s/it] 100%|██████████| 23/23 [00:38<00:00, 1.67s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.2ms Speed: 2.3ms preprocess, 8.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:01<00:41, 1.89s/it] 9%|▊ | 2/23 [00:03<00:35, 1.70s/it] 13%|█▎ | 3/23 [00:05<00:33, 1.69s/it] 17%|█▋ | 4/23 [00:06<00:31, 1.65s/it] 22%|██▏ | 5/23 [00:08<00:31, 1.73s/it] 26%|██▌ | 6/23 [00:10<00:29, 1.71s/it] 30%|███ | 7/23 [00:12<00:28, 1.75s/it] 35%|███▍ | 8/23 [00:14<00:27, 1.82s/it] 39%|███▉ | 9/23 [00:15<00:24, 1.76s/it] 43%|████▎ | 10/23 [00:17<00:22, 1.74s/it] 48%|████▊ | 11/23 [00:19<00:20, 1.72s/it] 52%|█████▏ | 12/23 [00:20<00:18, 1.70s/it] 57%|█████▋ | 13/23 [00:22<00:17, 1.78s/it] 61%|██████ | 14/23 [00:24<00:15, 1.75s/it] 65%|██████▌ | 15/23 [00:26<00:13, 1.72s/it] 70%|██████▉ | 16/23 [00:27<00:11, 1.71s/it] 74%|███████▍ | 17/23 [00:29<00:10, 1.71s/it] 78%|███████▊ | 18/23 [00:31<00:08, 1.75s/it] 83%|████████▎ | 19/23 [00:33<00:07, 1.77s/it] 87%|████████▋ | 20/23 [00:34<00:05, 1.76s/it] 91%|█████████▏| 21/23 [00:36<00:03, 1.74s/it] 96%|█████████▌| 22/23 [00:38<00:01, 1.69s/it] 100%|██████████| 23/23 [00:38<00:00, 1.39s/it] 100%|██████████| 23/23 [00:38<00:00, 1.69s/it] Decoding latents in cuda:0... done in 0.56s Move latents to cpu... done in 0.0s Uploading outputs... Finished.