tungsten-logo
Sign In
Cyberpunk Girl with Art Universe
art-universe:v8.0
evevalentine2017
evevalentine2017
·
Jan 6
367
Input
prompt
Specify things to see in the output
photo RAW,(Masterpiece, Best Quality, 1 (black skin) girl, blue eyes, 3d model, in the style of surreal cyberpunk iconography, steelpunk, photobashing, dieselpunk. leica r8, 8k, UHD, HDR), masterpiece, best quality, highly detailed, soft lighting, beautiful detailed, insanely intricate details, intricate details, perfect lighting, incredible detail, hypermaximalistic, natural balance color, 8k, ultra detailed, beautiful and aesthetic, extremely detailed, elegant, atmospheric
negative_prompt
Specify things to not see in the output
more than 2 legs, nipples, nsfw, frame, canvas, low quality, medium quality, easynegative, watermark, text, username, 3d, frame, ng_deepnegative_v1_75t, bad-hands-5, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale))
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
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
saturation
Adjust saturation
-0.95
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
1977020541
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++ 2M SDE Karras
samping_steps
Number of denoising steps
28
cfg_scale
Scale for classifier-free guidance
6
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)
easynegative.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
ng_deepnegative_v1_75t.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-hands-5.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
Output
https://files.tungsten.run/uploads/b77c04ab1b3645739359c239a082a1ff/00000-1977020541.webp
https://files.tungsten.run/uploads/5083c05dc7584d04a3161d897348d792/00001-1977020542.webp
https://files.tungsten.run/uploads/1e4caff7d69a487d8f0d85ec523392de/00002-1977020543.webp
https://files.tungsten.run/uploads/59c5c464173b467fbce7e4b9dfe77775/00003-1977020544.webp
Finished in 92.4 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: photo RAW,(Masterpiece, Best Quality, 1 (black skin) girl, blue eyes, 3d model, in the style of surreal cyberpunk iconography, steelpunk, photobashing, dieselpunk. leica r8, 8k, UHD, HDR), masterpiece, best quality, highly detailed, soft lighting, beautiful detailed, insanely intricate details, intricate details, perfect lighting, incredible detail, hypermaximalistic, natural balance color, 8k, ultra detailed, beautiful and aesthetic, extremely detailed, elegant, atmospheric, <lora:add_saturation:-0.95> Full negative prompt: more than 2 legs, nipples, nsfw, frame, canvas, low quality, medium quality, easynegative, watermark, text, username, 3d, frame, ng_deepnegative_v1_75t, bad-hands-5, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:47, 1.75s/it] 7%|▋ | 2/28 [00:03<00:47, 1.83s/it] 11%|█ | 3/28 [00:05<00:46, 1.86s/it] 14%|█▍ | 4/28 [00:07<00:45, 1.90s/it] 18%|█▊ | 5/28 [00:09<00:45, 1.98s/it] 21%|██▏ | 6/28 [00:11<00:42, 1.93s/it] 25%|██▌ | 7/28 [00:13<00:41, 1.96s/it] 29%|██▊ | 8/28 [00:15<00:39, 1.96s/it] 32%|███▏ | 9/28 [00:17<00:36, 1.92s/it] 36%|███▌ | 10/28 [00:19<00:35, 1.97s/it] 39%|███▉ | 11/28 [00:21<00:33, 1.99s/it] 43%|████▎ | 12/28 [00:23<00:31, 1.99s/it] 46%|████▋ | 13/28 [00:25<00:30, 2.00s/it] 50%|█████ | 14/28 [00:27<00:28, 2.01s/it] 54%|█████▎ | 15/28 [00:29<00:26, 2.05s/it] 57%|█████▋ | 16/28 [00:31<00:23, 1.93s/it] 61%|██████ | 17/28 [00:32<00:20, 1.84s/it] 64%|██████▍ | 18/28 [00:34<00:18, 1.86s/it] 68%|██████▊ | 19/28 [00:36<00:16, 1.79s/it] 71%|███████▏ | 20/28 [00:38<00:13, 1.74s/it] 75%|███████▌ | 21/28 [00:39<00:12, 1.76s/it] 79%|███████▊ | 22/28 [00:41<00:10, 1.71s/it] 82%|████████▏ | 23/28 [00:43<00:08, 1.73s/it] 86%|████████▌ | 24/28 [00:44<00:06, 1.65s/it] 89%|████████▉ | 25/28 [00:46<00:04, 1.61s/it] 93%|█████████▎| 26/28 [00:47<00:03, 1.63s/it] 96%|█████████▋| 27/28 [00:48<00:01, 1.46s/it] 100%|██████████| 28/28 [00:49<00:00, 1.22s/it] 100%|██████████| 28/28 [00:49<00:00, 1.77s/it] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.0ms preprocess, 7.8ms inference, 23.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:06, 1.79it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.29it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.41it/s] 31%|███ | 4/13 [00:01<00:03, 2.43it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.51it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.45it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.46it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.42it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.56it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.60it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.61it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.92it/s] 100%|██████████| 13/13 [00:04<00:00, 3.43it/s] 100%|██████████| 13/13 [00:04<00:00, 2.68it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.1ms Speed: 2.7ms preprocess, 7.1ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.47it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.72it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.64it/s] 31%|███ | 4/13 [00:01<00:03, 2.63it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.60it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.52it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.58it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.49it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.61it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.66it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.65it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.96it/s] 100%|██████████| 13/13 [00:04<00:00, 3.57it/s] 100%|██████████| 13/13 [00:04<00:00, 2.82it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.50it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.75it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.68it/s] 31%|███ | 4/13 [00:01<00:03, 2.65it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.60it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.49it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.55it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.46it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.60it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.66it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.63it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.91it/s] 100%|██████████| 13/13 [00:04<00:00, 3.53it/s] 100%|██████████| 13/13 [00:04<00:00, 2.80it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 2.5ms preprocess, 7.5ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.45it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.73it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.67it/s] 31%|███ | 4/13 [00:01<00:03, 2.64it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.66it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.55it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.56it/s] 62%|██████▏ | 8/13 [00:03<00:01, 2.50it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.64it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.68it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.67it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.95it/s] 100%|██████████| 13/13 [00:04<00:00, 3.56it/s] 100%|██████████| 13/13 [00:04<00:00, 2.83it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 6.9ms Speed: 2.6ms preprocess, 6.9ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 8.1ms Speed: 2.8ms preprocess, 8.1ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.51it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.72it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.66it/s] 31%|███ | 4/13 [00:01<00:03, 2.65it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.64it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.54it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.57it/s] 62%|██████▏ | 8/13 [00:03<00:01, 2.52it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.65it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.67it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.66it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.98it/s] 100%|██████████| 13/13 [00:04<00:00, 3.59it/s] 100%|██████████| 13/13 [00:04<00:00, 2.84it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 6.8ms Speed: 2.7ms preprocess, 6.8ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. 0: 640x640 1 face, 7.0ms Speed: 2.5ms preprocess, 7.0ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.40it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.62it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.60it/s] 31%|███ | 4/13 [00:01<00:03, 2.59it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.58it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.48it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.52it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.46it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.60it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.66it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.63it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.93it/s] 100%|██████████| 13/13 [00:04<00:00, 3.55it/s] 100%|██████████| 13/13 [00:04<00:00, 2.79it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 2.7ms preprocess, 7.2ms 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
photo RAW,(Masterpiece, Best Quality, 1 (black skin) girl, blue eyes, 3d model, in the style of surreal cyberpunk iconography, steelpunk, photobashing, dieselpunk. leica r8, 8k, UHD, HDR), masterpiece, best quality, highly detailed, soft lighting, beautiful detailed, insanely intricate details, intricate details, perfect lighting, incredible detail, hypermaximalistic, natural balance color, 8k, ultra detailed, beautiful and aesthetic, extremely detailed, elegant, atmospheric
negative_prompt
Specify things to not see in the output
more than 2 legs, nipples, nsfw, frame, canvas, low quality, medium quality, easynegative, watermark, text, username, 3d, frame, ng_deepnegative_v1_75t, bad-hands-5, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale))
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
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
saturation
Adjust saturation
-0.95
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
1977020541
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++ 2M SDE Karras
samping_steps
Number of denoising steps
28
cfg_scale
Scale for classifier-free guidance
6
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)
easynegative.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
ng_deepnegative_v1_75t.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-hands-5.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/b77c04ab1b3645739359c239a082a1ff/00000-1977020541.webp
https://files.tungsten.run/uploads/5083c05dc7584d04a3161d897348d792/00001-1977020542.webp
https://files.tungsten.run/uploads/1e4caff7d69a487d8f0d85ec523392de/00002-1977020543.webp
https://files.tungsten.run/uploads/59c5c464173b467fbce7e4b9dfe77775/00003-1977020544.webp
Finished in 92.4 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: photo RAW,(Masterpiece, Best Quality, 1 (black skin) girl, blue eyes, 3d model, in the style of surreal cyberpunk iconography, steelpunk, photobashing, dieselpunk. leica r8, 8k, UHD, HDR), masterpiece, best quality, highly detailed, soft lighting, beautiful detailed, insanely intricate details, intricate details, perfect lighting, incredible detail, hypermaximalistic, natural balance color, 8k, ultra detailed, beautiful and aesthetic, extremely detailed, elegant, atmospheric, <lora:add_saturation:-0.95> Full negative prompt: more than 2 legs, nipples, nsfw, frame, canvas, low quality, medium quality, easynegative, watermark, text, username, 3d, frame, ng_deepnegative_v1_75t, bad-hands-5, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:47, 1.75s/it] 7%|▋ | 2/28 [00:03<00:47, 1.83s/it] 11%|█ | 3/28 [00:05<00:46, 1.86s/it] 14%|█▍ | 4/28 [00:07<00:45, 1.90s/it] 18%|█▊ | 5/28 [00:09<00:45, 1.98s/it] 21%|██▏ | 6/28 [00:11<00:42, 1.93s/it] 25%|██▌ | 7/28 [00:13<00:41, 1.96s/it] 29%|██▊ | 8/28 [00:15<00:39, 1.96s/it] 32%|███▏ | 9/28 [00:17<00:36, 1.92s/it] 36%|███▌ | 10/28 [00:19<00:35, 1.97s/it] 39%|███▉ | 11/28 [00:21<00:33, 1.99s/it] 43%|████▎ | 12/28 [00:23<00:31, 1.99s/it] 46%|████▋ | 13/28 [00:25<00:30, 2.00s/it] 50%|█████ | 14/28 [00:27<00:28, 2.01s/it] 54%|█████▎ | 15/28 [00:29<00:26, 2.05s/it] 57%|█████▋ | 16/28 [00:31<00:23, 1.93s/it] 61%|██████ | 17/28 [00:32<00:20, 1.84s/it] 64%|██████▍ | 18/28 [00:34<00:18, 1.86s/it] 68%|██████▊ | 19/28 [00:36<00:16, 1.79s/it] 71%|███████▏ | 20/28 [00:38<00:13, 1.74s/it] 75%|███████▌ | 21/28 [00:39<00:12, 1.76s/it] 79%|███████▊ | 22/28 [00:41<00:10, 1.71s/it] 82%|████████▏ | 23/28 [00:43<00:08, 1.73s/it] 86%|████████▌ | 24/28 [00:44<00:06, 1.65s/it] 89%|████████▉ | 25/28 [00:46<00:04, 1.61s/it] 93%|█████████▎| 26/28 [00:47<00:03, 1.63s/it] 96%|█████████▋| 27/28 [00:48<00:01, 1.46s/it] 100%|██████████| 28/28 [00:49<00:00, 1.22s/it] 100%|██████████| 28/28 [00:49<00:00, 1.77s/it] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.0ms preprocess, 7.8ms inference, 23.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:06, 1.79it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.29it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.41it/s] 31%|███ | 4/13 [00:01<00:03, 2.43it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.51it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.45it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.46it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.42it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.56it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.60it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.61it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.92it/s] 100%|██████████| 13/13 [00:04<00:00, 3.43it/s] 100%|██████████| 13/13 [00:04<00:00, 2.68it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.1ms Speed: 2.7ms preprocess, 7.1ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.47it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.72it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.64it/s] 31%|███ | 4/13 [00:01<00:03, 2.63it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.60it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.52it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.58it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.49it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.61it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.66it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.65it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.96it/s] 100%|██████████| 13/13 [00:04<00:00, 3.57it/s] 100%|██████████| 13/13 [00:04<00:00, 2.82it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.50it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.75it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.68it/s] 31%|███ | 4/13 [00:01<00:03, 2.65it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.60it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.49it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.55it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.46it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.60it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.66it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.63it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.91it/s] 100%|██████████| 13/13 [00:04<00:00, 3.53it/s] 100%|██████████| 13/13 [00:04<00:00, 2.80it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 2.5ms preprocess, 7.5ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.45it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.73it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.67it/s] 31%|███ | 4/13 [00:01<00:03, 2.64it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.66it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.55it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.56it/s] 62%|██████▏ | 8/13 [00:03<00:01, 2.50it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.64it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.68it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.67it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.95it/s] 100%|██████████| 13/13 [00:04<00:00, 3.56it/s] 100%|██████████| 13/13 [00:04<00:00, 2.83it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 6.9ms Speed: 2.6ms preprocess, 6.9ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 8.1ms Speed: 2.8ms preprocess, 8.1ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.51it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.72it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.66it/s] 31%|███ | 4/13 [00:01<00:03, 2.65it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.64it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.54it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.57it/s] 62%|██████▏ | 8/13 [00:03<00:01, 2.52it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.65it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.67it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.66it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.98it/s] 100%|██████████| 13/13 [00:04<00:00, 3.59it/s] 100%|██████████| 13/13 [00:04<00:00, 2.84it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 6.8ms Speed: 2.7ms preprocess, 6.8ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. 0: 640x640 1 face, 7.0ms Speed: 2.5ms preprocess, 7.0ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.40it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.62it/s] 23%|██▎ | 3/13 [00:01<00:03, 2.60it/s] 31%|███ | 4/13 [00:01<00:03, 2.59it/s] 38%|███▊ | 5/13 [00:01<00:03, 2.58it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.48it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.52it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.46it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.60it/s] 77%|███████▋ | 10/13 [00:03<00:01, 2.66it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.63it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.93it/s] 100%|██████████| 13/13 [00:04<00:00, 3.55it/s] 100%|██████████| 13/13 [00:04<00:00, 2.79it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 2.7ms preprocess, 7.2ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 4 with 2nd settings. Uploading outputs... Finished.