tungsten-logo
Sign In
Dark Magic with Dark Arts SDXL
dark-arts-sdxl:v1.0
evevalentine2017
evevalentine2017
·
Mar 2
349
Input
prompt
Specify things to see in the output
Horror-themed create for me a vision of an evil magician practicing dark magic and necromancy in an ancient abandoned cathedral, (solo), hyperrealistic art cinematic film still photography in the style of detailed hyperrealism photoshoot, RAW, color graded portra 400 film, remarkable color, realistic dull skin noise, thorough, analog style, highest quality, skin pores, sharp focus, dappled lighting, film grain, photographed on a Sony A7R IV, 18mm F/1.7 cine lens, (highly detailed, intricately detailed), 8k, HDR, eerie, unsettling, dark, spooky, suspenseful, grim, highly detailed
negative_prompt
Specify things to not see in the output
green colors, humans, cheerful, bright, vibrant, light-hearted, cute, nsfw, imperfect hand, deformed hand, imperfect fingers, deformed fingers, bad proportions,(((nudity))), lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, blurry, rendered, CGI, jpg artifacts, video noise, imperfect hand, deformed hand
num_outputs
Number of output images
3
width
Output image width
1024
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.
164851643
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++ 3M SDE Exponential
samping_steps
Number of denoising steps
50
cfg_scale
Scale for classifier-free guidance
5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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/0d651ce11f194faca08fba3aa7c2622a/00000-164851643.webp
https://files.tungsten.run/uploads/cf99e7ae92af432cb5a3921c62de7bfc/00001-164851644.webp
https://files.tungsten.run/uploads/53ee5c0ae64c408cb9a4893b3fe19df3/00002-164851645.webp
Finished in 192.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Horror-themed create for me a vision of an evil magician practicing dark magic and necromancy in an ancient abandoned cathedral, (solo), hyperrealistic art cinematic film still photography in the style of detailed hyperrealism photoshoot, RAW, color graded portra 400 film, remarkable color, realistic dull skin noise, thorough, analog style, highest quality, skin pores, sharp focus, dappled lighting, film grain, photographed on a Sony A7R IV, 18mm F/1.7 cine lens, (highly detailed, intricately detailed), 8k, HDR, eerie, unsettling, dark, spooky, suspenseful, grim, highly detailed Full negative prompt: green colors, humans, cheerful, bright, vibrant, light-hearted, cute, nsfw, imperfect hand, deformed hand, imperfect fingers, deformed fingers, bad proportions,(((nudity))), lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, blurry, rendered, CGI, jpg artifacts, video noise, imperfect hand, deformed hand 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:02<01:53, 2.31s/it] 4%|▍ | 2/50 [00:04<02:00, 2.50s/it] 6%|▌ | 3/50 [00:07<02:03, 2.63s/it] 8%|▊ | 4/50 [00:10<02:02, 2.65s/it] 10%|█ | 5/50 [00:13<02:00, 2.67s/it] 12%|█▏ | 6/50 [00:16<02:00, 2.74s/it] 14%|█▍ | 7/50 [00:18<01:59, 2.78s/it] 16%|█▌ | 8/50 [00:21<01:58, 2.82s/it] 18%|█▊ | 9/50 [00:24<01:54, 2.79s/it] 20%|██ | 10/50 [00:27<01:50, 2.76s/it] 22%|██▏ | 11/50 [00:29<01:45, 2.70s/it] 24%|██▍ | 12/50 [00:32<01:46, 2.79s/it] 26%|██▌ | 13/50 [00:35<01:41, 2.73s/it] 28%|██▊ | 14/50 [00:38<01:38, 2.74s/it] 30%|███ | 15/50 [00:40<01:34, 2.71s/it] 32%|███▏ | 16/50 [00:43<01:31, 2.71s/it] 34%|███▍ | 17/50 [00:46<01:28, 2.68s/it] 36%|███▌ | 18/50 [00:48<01:26, 2.69s/it] 38%|███▊ | 19/50 [00:51<01:22, 2.68s/it] 40%|████ | 20/50 [00:54<01:20, 2.69s/it] 42%|████▏ | 21/50 [00:56<01:18, 2.70s/it] 44%|████▍ | 22/50 [00:59<01:14, 2.66s/it] 46%|████▌ | 23/50 [01:02<01:12, 2.69s/it] 48%|████▊ | 24/50 [01:04<01:09, 2.66s/it] 50%|█████ | 25/50 [01:07<01:06, 2.67s/it] 52%|█████▏ | 26/50 [01:10<01:03, 2.65s/it] 54%|█████▍ | 27/50 [01:12<00:59, 2.58s/it] 56%|█████▌ | 28/50 [01:15<00:57, 2.63s/it] 58%|█████▊ | 29/50 [01:17<00:55, 2.62s/it] 60%|██████ | 30/50 [01:20<00:54, 2.71s/it] 62%|██████▏ | 31/50 [01:23<00:50, 2.64s/it] 64%|██████▍ | 32/50 [01:25<00:46, 2.57s/it] 66%|██████▌ | 33/50 [01:28<00:44, 2.64s/it] 68%|██████▊ | 34/50 [01:30<00:41, 2.58s/it] 70%|███████ | 35/50 [01:33<00:37, 2.53s/it] 72%|███████▏ | 36/50 [01:35<00:34, 2.45s/it] 74%|███████▍ | 37/50 [01:38<00:32, 2.46s/it] 76%|███████▌ | 38/50 [01:40<00:29, 2.43s/it] 78%|███████▊ | 39/50 [01:42<00:26, 2.39s/it] 80%|████████ | 40/50 [01:44<00:23, 2.31s/it] 82%|████████▏ | 41/50 [01:47<00:20, 2.28s/it] 84%|████████▍ | 42/50 [01:49<00:18, 2.26s/it] 86%|████████▌ | 43/50 [01:51<00:16, 2.34s/it] 88%|████████▊ | 44/50 [01:53<00:13, 2.29s/it] 90%|█████████ | 45/50 [01:56<00:11, 2.30s/it] 92%|█████████▏| 46/50 [01:58<00:09, 2.31s/it] 94%|█████████▍| 47/50 [02:00<00:07, 2.33s/it] 96%|█████████▌| 48/50 [02:02<00:04, 2.24s/it] 98%|█████████▊| 49/50 [02:04<00:02, 2.00s/it] 100%|██████████| 50/50 [02:05<00:00, 1.80s/it] 100%|██████████| 50/50 [02:05<00:00, 2.52s/it] Decoding latents in cuda:0... done in 2.38s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.8ms Speed: 3.3ms preprocess, 7.8ms inference, 23.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:20, 1.08it/s] 9%|▊ | 2/23 [00:01<00:18, 1.12it/s] 13%|█▎ | 3/23 [00:02<00:17, 1.17it/s] 17%|█▋ | 4/23 [00:03<00:15, 1.22it/s] 22%|██▏ | 5/23 [00:04<00:14, 1.25it/s] 26%|██▌ | 6/23 [00:05<00:14, 1.20it/s] 30%|███ | 7/23 [00:05<00:12, 1.24it/s] 35%|███▍ | 8/23 [00:06<00:11, 1.26it/s] 39%|███▉ | 9/23 [00:07<00:10, 1.30it/s] 43%|████▎ | 10/23 [00:08<00:10, 1.28it/s] 48%|████▊ | 11/23 [00:08<00:09, 1.30it/s] 52%|█████▏ | 12/23 [00:09<00:08, 1.33it/s] 57%|█████▋ | 13/23 [00:10<00:07, 1.38it/s] 61%|██████ | 14/23 [00:10<00:06, 1.40it/s] 65%|██████▌ | 15/23 [00:11<00:05, 1.40it/s] 70%|██████▉ | 16/23 [00:12<00:05, 1.35it/s] 74%|███████▍ | 17/23 [00:13<00:04, 1.37it/s] 78%|███████▊ | 18/23 [00:13<00:03, 1.37it/s] 83%|████████▎ | 19/23 [00:14<00:02, 1.38it/s] 87%|████████▋ | 20/23 [00:15<00:02, 1.35it/s] 91%|█████████▏| 21/23 [00:15<00:01, 1.42it/s] 96%|█████████▌| 22/23 [00:16<00:00, 1.60it/s] 100%|██████████| 23/23 [00:16<00:00, 1.80it/s] 100%|██████████| 23/23 [00:16<00:00, 1.37it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.8ms Speed: 3.1ms preprocess, 7.8ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:19, 1.12it/s] 9%|▊ | 2/23 [00:01<00:17, 1.18it/s] 13%|█▎ | 3/23 [00:02<00:16, 1.18it/s] 17%|█▋ | 4/23 [00:03<00:15, 1.22it/s] 22%|██▏ | 5/23 [00:04<00:14, 1.26it/s] 26%|██▌ | 6/23 [00:04<00:13, 1.22it/s] 30%|███ | 7/23 [00:05<00:12, 1.24it/s] 35%|███▍ | 8/23 [00:06<00:12, 1.25it/s] 39%|███▉ | 9/23 [00:07<00:10, 1.30it/s] 43%|████▎ | 10/23 [00:08<00:10, 1.29it/s] 48%|████▊ | 11/23 [00:08<00:09, 1.30it/s] 52%|█████▏ | 12/23 [00:09<00:08, 1.32it/s] 57%|█████▋ | 13/23 [00:10<00:07, 1.38it/s] 61%|██████ | 14/23 [00:10<00:06, 1.40it/s] 65%|██████▌ | 15/23 [00:11<00:05, 1.40it/s] 70%|██████▉ | 16/23 [00:12<00:05, 1.34it/s] 74%|███████▍ | 17/23 [00:13<00:04, 1.38it/s] 78%|███████▊ | 18/23 [00:13<00:03, 1.37it/s] 83%|████████▎ | 19/23 [00:14<00:02, 1.35it/s] 87%|████████▋ | 20/23 [00:15<00:02, 1.33it/s] 91%|█████████▏| 21/23 [00:15<00:01, 1.40it/s] 96%|█████████▌| 22/23 [00:16<00:00, 1.58it/s] 100%|██████████| 23/23 [00:16<00:00, 1.75it/s] 100%|██████████| 23/23 [00:16<00:00, 1.37it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.9ms Speed: 3.5ms preprocess, 7.9ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:19, 1.13it/s] 9%|▊ | 2/23 [00:01<00:18, 1.16it/s] 13%|█▎ | 3/23 [00:02<00:16, 1.18it/s] 17%|█▋ | 4/23 [00:03<00:15, 1.22it/s] 22%|██▏ | 5/23 [00:04<00:14, 1.25it/s] 26%|██▌ | 6/23 [00:04<00:14, 1.21it/s] 30%|███ | 7/23 [00:05<00:12, 1.23it/s] 35%|███▍ | 8/23 [00:06<00:12, 1.24it/s] 39%|███▉ | 9/23 [00:07<00:10, 1.28it/s] 43%|████▎ | 10/23 [00:08<00:10, 1.28it/s] 48%|████▊ | 11/23 [00:08<00:09, 1.29it/s] 52%|█████▏ | 12/23 [00:09<00:08, 1.31it/s] 57%|█████▋ | 13/23 [00:10<00:07, 1.36it/s] 61%|██████ | 14/23 [00:10<00:06, 1.38it/s] 65%|██████▌ | 15/23 [00:11<00:05, 1.40it/s] 70%|██████▉ | 16/23 [00:12<00:05, 1.36it/s] 74%|███████▍ | 17/23 [00:13<00:04, 1.40it/s] 78%|███████▊ | 18/23 [00:13<00:03, 1.39it/s] 83%|████████▎ | 19/23 [00:14<00:02, 1.38it/s] 87%|████████▋ | 20/23 [00:15<00:02, 1.36it/s] 91%|█████████▏| 21/23 [00:15<00:01, 1.42it/s] 96%|█████████▌| 22/23 [00:16<00:00, 1.60it/s] 100%|██████████| 23/23 [00:16<00:00, 1.80it/s] 100%|██████████| 23/23 [00:16<00:00, 1.37it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt
Specify things to see in the output
Horror-themed create for me a vision of an evil magician practicing dark magic and necromancy in an ancient abandoned cathedral, (solo), hyperrealistic art cinematic film still photography in the style of detailed hyperrealism photoshoot, RAW, color graded portra 400 film, remarkable color, realistic dull skin noise, thorough, analog style, highest quality, skin pores, sharp focus, dappled lighting, film grain, photographed on a Sony A7R IV, 18mm F/1.7 cine lens, (highly detailed, intricately detailed), 8k, HDR, eerie, unsettling, dark, spooky, suspenseful, grim, highly detailed
negative_prompt
Specify things to not see in the output
green colors, humans, cheerful, bright, vibrant, light-hearted, cute, nsfw, imperfect hand, deformed hand, imperfect fingers, deformed fingers, bad proportions,(((nudity))), lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, blurry, rendered, CGI, jpg artifacts, video noise, imperfect hand, deformed hand
num_outputs
Number of output images
3
width
Output image width
1024
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.
164851643
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++ 3M SDE Exponential
samping_steps
Number of denoising steps
50
cfg_scale
Scale for classifier-free guidance
5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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/0d651ce11f194faca08fba3aa7c2622a/00000-164851643.webp
https://files.tungsten.run/uploads/cf99e7ae92af432cb5a3921c62de7bfc/00001-164851644.webp
https://files.tungsten.run/uploads/53ee5c0ae64c408cb9a4893b3fe19df3/00002-164851645.webp
Finished in 192.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Horror-themed create for me a vision of an evil magician practicing dark magic and necromancy in an ancient abandoned cathedral, (solo), hyperrealistic art cinematic film still photography in the style of detailed hyperrealism photoshoot, RAW, color graded portra 400 film, remarkable color, realistic dull skin noise, thorough, analog style, highest quality, skin pores, sharp focus, dappled lighting, film grain, photographed on a Sony A7R IV, 18mm F/1.7 cine lens, (highly detailed, intricately detailed), 8k, HDR, eerie, unsettling, dark, spooky, suspenseful, grim, highly detailed Full negative prompt: green colors, humans, cheerful, bright, vibrant, light-hearted, cute, nsfw, imperfect hand, deformed hand, imperfect fingers, deformed fingers, bad proportions,(((nudity))), lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, blurry, rendered, CGI, jpg artifacts, video noise, imperfect hand, deformed hand 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:02<01:53, 2.31s/it] 4%|▍ | 2/50 [00:04<02:00, 2.50s/it] 6%|▌ | 3/50 [00:07<02:03, 2.63s/it] 8%|▊ | 4/50 [00:10<02:02, 2.65s/it] 10%|█ | 5/50 [00:13<02:00, 2.67s/it] 12%|█▏ | 6/50 [00:16<02:00, 2.74s/it] 14%|█▍ | 7/50 [00:18<01:59, 2.78s/it] 16%|█▌ | 8/50 [00:21<01:58, 2.82s/it] 18%|█▊ | 9/50 [00:24<01:54, 2.79s/it] 20%|██ | 10/50 [00:27<01:50, 2.76s/it] 22%|██▏ | 11/50 [00:29<01:45, 2.70s/it] 24%|██▍ | 12/50 [00:32<01:46, 2.79s/it] 26%|██▌ | 13/50 [00:35<01:41, 2.73s/it] 28%|██▊ | 14/50 [00:38<01:38, 2.74s/it] 30%|███ | 15/50 [00:40<01:34, 2.71s/it] 32%|███▏ | 16/50 [00:43<01:31, 2.71s/it] 34%|███▍ | 17/50 [00:46<01:28, 2.68s/it] 36%|███▌ | 18/50 [00:48<01:26, 2.69s/it] 38%|███▊ | 19/50 [00:51<01:22, 2.68s/it] 40%|████ | 20/50 [00:54<01:20, 2.69s/it] 42%|████▏ | 21/50 [00:56<01:18, 2.70s/it] 44%|████▍ | 22/50 [00:59<01:14, 2.66s/it] 46%|████▌ | 23/50 [01:02<01:12, 2.69s/it] 48%|████▊ | 24/50 [01:04<01:09, 2.66s/it] 50%|█████ | 25/50 [01:07<01:06, 2.67s/it] 52%|█████▏ | 26/50 [01:10<01:03, 2.65s/it] 54%|█████▍ | 27/50 [01:12<00:59, 2.58s/it] 56%|█████▌ | 28/50 [01:15<00:57, 2.63s/it] 58%|█████▊ | 29/50 [01:17<00:55, 2.62s/it] 60%|██████ | 30/50 [01:20<00:54, 2.71s/it] 62%|██████▏ | 31/50 [01:23<00:50, 2.64s/it] 64%|██████▍ | 32/50 [01:25<00:46, 2.57s/it] 66%|██████▌ | 33/50 [01:28<00:44, 2.64s/it] 68%|██████▊ | 34/50 [01:30<00:41, 2.58s/it] 70%|███████ | 35/50 [01:33<00:37, 2.53s/it] 72%|███████▏ | 36/50 [01:35<00:34, 2.45s/it] 74%|███████▍ | 37/50 [01:38<00:32, 2.46s/it] 76%|███████▌ | 38/50 [01:40<00:29, 2.43s/it] 78%|███████▊ | 39/50 [01:42<00:26, 2.39s/it] 80%|████████ | 40/50 [01:44<00:23, 2.31s/it] 82%|████████▏ | 41/50 [01:47<00:20, 2.28s/it] 84%|████████▍ | 42/50 [01:49<00:18, 2.26s/it] 86%|████████▌ | 43/50 [01:51<00:16, 2.34s/it] 88%|████████▊ | 44/50 [01:53<00:13, 2.29s/it] 90%|█████████ | 45/50 [01:56<00:11, 2.30s/it] 92%|█████████▏| 46/50 [01:58<00:09, 2.31s/it] 94%|█████████▍| 47/50 [02:00<00:07, 2.33s/it] 96%|█████████▌| 48/50 [02:02<00:04, 2.24s/it] 98%|█████████▊| 49/50 [02:04<00:02, 2.00s/it] 100%|██████████| 50/50 [02:05<00:00, 1.80s/it] 100%|██████████| 50/50 [02:05<00:00, 2.52s/it] Decoding latents in cuda:0... done in 2.38s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.8ms Speed: 3.3ms preprocess, 7.8ms inference, 23.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:20, 1.08it/s] 9%|▊ | 2/23 [00:01<00:18, 1.12it/s] 13%|█▎ | 3/23 [00:02<00:17, 1.17it/s] 17%|█▋ | 4/23 [00:03<00:15, 1.22it/s] 22%|██▏ | 5/23 [00:04<00:14, 1.25it/s] 26%|██▌ | 6/23 [00:05<00:14, 1.20it/s] 30%|███ | 7/23 [00:05<00:12, 1.24it/s] 35%|███▍ | 8/23 [00:06<00:11, 1.26it/s] 39%|███▉ | 9/23 [00:07<00:10, 1.30it/s] 43%|████▎ | 10/23 [00:08<00:10, 1.28it/s] 48%|████▊ | 11/23 [00:08<00:09, 1.30it/s] 52%|█████▏ | 12/23 [00:09<00:08, 1.33it/s] 57%|█████▋ | 13/23 [00:10<00:07, 1.38it/s] 61%|██████ | 14/23 [00:10<00:06, 1.40it/s] 65%|██████▌ | 15/23 [00:11<00:05, 1.40it/s] 70%|██████▉ | 16/23 [00:12<00:05, 1.35it/s] 74%|███████▍ | 17/23 [00:13<00:04, 1.37it/s] 78%|███████▊ | 18/23 [00:13<00:03, 1.37it/s] 83%|████████▎ | 19/23 [00:14<00:02, 1.38it/s] 87%|████████▋ | 20/23 [00:15<00:02, 1.35it/s] 91%|█████████▏| 21/23 [00:15<00:01, 1.42it/s] 96%|█████████▌| 22/23 [00:16<00:00, 1.60it/s] 100%|██████████| 23/23 [00:16<00:00, 1.80it/s] 100%|██████████| 23/23 [00:16<00:00, 1.37it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.8ms Speed: 3.1ms preprocess, 7.8ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:19, 1.12it/s] 9%|▊ | 2/23 [00:01<00:17, 1.18it/s] 13%|█▎ | 3/23 [00:02<00:16, 1.18it/s] 17%|█▋ | 4/23 [00:03<00:15, 1.22it/s] 22%|██▏ | 5/23 [00:04<00:14, 1.26it/s] 26%|██▌ | 6/23 [00:04<00:13, 1.22it/s] 30%|███ | 7/23 [00:05<00:12, 1.24it/s] 35%|███▍ | 8/23 [00:06<00:12, 1.25it/s] 39%|███▉ | 9/23 [00:07<00:10, 1.30it/s] 43%|████▎ | 10/23 [00:08<00:10, 1.29it/s] 48%|████▊ | 11/23 [00:08<00:09, 1.30it/s] 52%|█████▏ | 12/23 [00:09<00:08, 1.32it/s] 57%|█████▋ | 13/23 [00:10<00:07, 1.38it/s] 61%|██████ | 14/23 [00:10<00:06, 1.40it/s] 65%|██████▌ | 15/23 [00:11<00:05, 1.40it/s] 70%|██████▉ | 16/23 [00:12<00:05, 1.34it/s] 74%|███████▍ | 17/23 [00:13<00:04, 1.38it/s] 78%|███████▊ | 18/23 [00:13<00:03, 1.37it/s] 83%|████████▎ | 19/23 [00:14<00:02, 1.35it/s] 87%|████████▋ | 20/23 [00:15<00:02, 1.33it/s] 91%|█████████▏| 21/23 [00:15<00:01, 1.40it/s] 96%|█████████▌| 22/23 [00:16<00:00, 1.58it/s] 100%|██████████| 23/23 [00:16<00:00, 1.75it/s] 100%|██████████| 23/23 [00:16<00:00, 1.37it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.9ms Speed: 3.5ms preprocess, 7.9ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:19, 1.13it/s] 9%|▊ | 2/23 [00:01<00:18, 1.16it/s] 13%|█▎ | 3/23 [00:02<00:16, 1.18it/s] 17%|█▋ | 4/23 [00:03<00:15, 1.22it/s] 22%|██▏ | 5/23 [00:04<00:14, 1.25it/s] 26%|██▌ | 6/23 [00:04<00:14, 1.21it/s] 30%|███ | 7/23 [00:05<00:12, 1.23it/s] 35%|███▍ | 8/23 [00:06<00:12, 1.24it/s] 39%|███▉ | 9/23 [00:07<00:10, 1.28it/s] 43%|████▎ | 10/23 [00:08<00:10, 1.28it/s] 48%|████▊ | 11/23 [00:08<00:09, 1.29it/s] 52%|█████▏ | 12/23 [00:09<00:08, 1.31it/s] 57%|█████▋ | 13/23 [00:10<00:07, 1.36it/s] 61%|██████ | 14/23 [00:10<00:06, 1.38it/s] 65%|██████▌ | 15/23 [00:11<00:05, 1.40it/s] 70%|██████▉ | 16/23 [00:12<00:05, 1.36it/s] 74%|███████▍ | 17/23 [00:13<00:04, 1.40it/s] 78%|███████▊ | 18/23 [00:13<00:03, 1.39it/s] 83%|████████▎ | 19/23 [00:14<00:02, 1.38it/s] 87%|████████▋ | 20/23 [00:15<00:02, 1.36it/s] 91%|█████████▏| 21/23 [00:15<00:01, 1.42it/s] 96%|█████████▌| 22/23 [00:16<00:00, 1.60it/s] 100%|██████████| 23/23 [00:16<00:00, 1.80it/s] 100%|██████████| 23/23 [00:16<00:00, 1.37it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s Uploading outputs... Finished.