tungsten-logo
Sign In
Colors Explosion with AI-OS
ai-os:v1.0
evevalentine2017
evevalentine2017
·
12/25/2023
361
Input
prompt
Specify things to see in the output
Dynamic abstract background with a blonde girl at its center, immersed in energetic splashes of color and bold strokes. (Dynamic abstraction:1.4), (Energetic mood:1.2), (Bold color strokes:1.3), Dynamic, Vibrant. Inspired by the styles of Jackson Pollock and Wassily Kandinsky. 4K UHD image, Cinematic view, Photorealistic, High-definition, Intricate, Sharp, Ultra-detailed, Crisp, cowboy shot, volumetric light, shiny skin, glossy skin, <lora:add_detail:0.8>, <lora:FaceBeauty_qinglong_V3:1.5>
negative_prompt
Specify things to not see in the output
((nipples)), ((portrait)), nsfw, (photorealistic:1.2) and (3d rendering:1.2) and (worst quality:2) and (low quality:2) and (normal quality:2) and (bad anatomy) and (depth of field:1.4) and (bokeh:1.4) and (blurry:1.4), bad-hands-5
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
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0.45
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
1110424535
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 Karras
samping_steps
Number of denoising steps
51
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
ClearVAE_V2.3_fp16.pt
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
add_detail.safetensors
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
FaceBeauty_qinglong_V3.safetensors
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)
bad-hands-5.pt
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/7494b5173ab44f6db93d3a6dce96b4eb/00000-1110424535.webp
https://files.tungsten.run/uploads/34feef51deb0449bb764e0455370fa0b/00001-1110424536.webp
https://files.tungsten.run/uploads/a054e5a087044d388f035b7e99252d62/00002-1110424537.webp
https://files.tungsten.run/uploads/0cb27f7484084945bfc6b3b08f67b8d6/00003-1110424538.webp
Finished in 72.1 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/ClearVAE_V2.3_fp16.pt Full prompt: Dynamic abstract background with a blonde girl at its center, immersed in energetic splashes of color and bold strokes. (Dynamic abstraction:1.4), (Energetic mood:1.2), (Bold color strokes:1.3), Dynamic, Vibrant. Inspired by the styles of Jackson Pollock and Wassily Kandinsky. 4K UHD image, Cinematic view, Photorealistic, High-definition, Intricate, Sharp, Ultra-detailed, Crisp, cowboy shot, volumetric light, shiny skin, glossy skin, <lora:FaceBeauty_qinglong_V3:1.5>, <lora:add_saturation:0.45> Full negative prompt: ((nipples)), ((portrait)), nsfw, (photorealistic:1.2) and (3d rendering:1.2) and (worst quality:2) and (low quality:2) and (normal quality:2) and (bad anatomy) and (depth of field:1.4) and (bokeh:1.4) and (blurry:1.4), bad-hands-5 0%| | 0/51 [00:00<?, ?it/s] 2%|▏ | 1/51 [00:01<01:03, 1.26s/it] 4%|▍ | 2/51 [00:01<00:43, 1.13it/s] 6%|▌ | 3/51 [00:02<00:36, 1.32it/s] 8%|▊ | 4/51 [00:03<00:33, 1.42it/s] 10%|▉ | 5/51 [00:03<00:30, 1.49it/s] 12%|█▏ | 6/51 [00:04<00:29, 1.53it/s] 14%|█▎ | 7/51 [00:04<00:28, 1.56it/s] 16%|█▌ | 8/51 [00:05<00:27, 1.58it/s] 18%|█▊ | 9/51 [00:06<00:26, 1.59it/s] 20%|█▉ | 10/51 [00:06<00:25, 1.60it/s] 22%|██▏ | 11/51 [00:07<00:24, 1.61it/s] 24%|██▎ | 12/51 [00:08<00:24, 1.61it/s] 25%|██▌ | 13/51 [00:08<00:23, 1.61it/s] 27%|██▋ | 14/51 [00:09<00:23, 1.60it/s] 29%|██▉ | 15/51 [00:09<00:22, 1.61it/s] 31%|███▏ | 16/51 [00:10<00:21, 1.61it/s] 33%|███▎ | 17/51 [00:11<00:21, 1.61it/s] 35%|███▌ | 18/51 [00:11<00:20, 1.61it/s] 37%|███▋ | 19/51 [00:12<00:19, 1.61it/s] 39%|███▉ | 20/51 [00:13<00:19, 1.61it/s] 41%|████ | 21/51 [00:13<00:18, 1.61it/s] 43%|████▎ | 22/51 [00:14<00:18, 1.61it/s] 45%|████▌ | 23/51 [00:14<00:17, 1.60it/s] 47%|████▋ | 24/51 [00:15<00:16, 1.60it/s] 49%|████▉ | 25/51 [00:16<00:16, 1.60it/s] 51%|█████ | 26/51 [00:16<00:15, 1.59it/s] 53%|█████▎ | 27/51 [00:17<00:15, 1.60it/s] 55%|█████▍ | 28/51 [00:18<00:14, 1.60it/s] 57%|█████▋ | 29/51 [00:18<00:13, 1.61it/s] 59%|█████▉ | 30/51 [00:19<00:13, 1.61it/s] 61%|██████ | 31/51 [00:19<00:12, 1.61it/s] 63%|██████▎ | 32/51 [00:20<00:11, 1.60it/s] 65%|██████▍ | 33/51 [00:21<00:11, 1.60it/s] 67%|██████▋ | 34/51 [00:21<00:10, 1.60it/s] 69%|██████▊ | 35/51 [00:22<00:10, 1.60it/s] 71%|███████ | 36/51 [00:23<00:09, 1.60it/s] 73%|███████▎ | 37/51 [00:23<00:08, 1.60it/s] 75%|███████▍ | 38/51 [00:24<00:08, 1.60it/s] 76%|███████▋ | 39/51 [00:24<00:07, 1.60it/s] 78%|███████▊ | 40/51 [00:25<00:06, 1.60it/s] 80%|████████ | 41/51 [00:26<00:06, 1.60it/s] 82%|████████▏ | 42/51 [00:26<00:05, 1.60it/s] 84%|████████▍ | 43/51 [00:27<00:05, 1.60it/s] 86%|████████▋ | 44/51 [00:28<00:04, 1.60it/s] 88%|████████▊ | 45/51 [00:28<00:03, 1.59it/s] 90%|█████████ | 46/51 [00:29<00:03, 1.59it/s] 92%|█████████▏| 47/51 [00:29<00:02, 1.60it/s] 94%|█████████▍| 48/51 [00:30<00:01, 1.59it/s] 96%|█████████▌| 49/51 [00:31<00:01, 1.60it/s] 98%|█████████▊| 50/51 [00:31<00:00, 1.59it/s] 100%|██████████| 51/51 [00:32<00:00, 1.59it/s] 100%|██████████| 51/51 [00:32<00:00, 1.57it/s] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.0ms Speed: 4.9ms preprocess, 8.0ms inference, 33.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:10, 2.56it/s] 7%|▋ | 2/29 [00:00<00:07, 3.62it/s] 10%|█ | 3/29 [00:00<00:06, 4.05it/s] 14%|█▍ | 4/29 [00:00<00:05, 4.42it/s] 17%|█▋ | 5/29 [00:01<00:05, 4.56it/s] 21%|██ | 6/29 [00:01<00:04, 4.73it/s] 24%|██▍ | 7/29 [00:01<00:04, 4.86it/s] 28%|██▊ | 8/29 [00:01<00:04, 4.77it/s] 31%|███ | 9/29 [00:02<00:04, 4.88it/s] 34%|███▍ | 10/29 [00:02<00:03, 4.93it/s] 38%|███▊ | 11/29 [00:02<00:03, 4.97it/s] 41%|████▏ | 12/29 [00:02<00:03, 5.00it/s] 45%|████▍ | 13/29 [00:02<00:03, 4.95it/s] 48%|████▊ | 14/29 [00:02<00:03, 4.99it/s] 52%|█████▏ | 15/29 [00:03<00:02, 5.01it/s] 55%|█████▌ | 16/29 [00:03<00:03, 4.20it/s] 59%|█████▊ | 17/29 [00:03<00:02, 4.41it/s] 62%|██████▏ | 18/29 [00:03<00:02, 4.40it/s] 66%|██████▌ | 19/29 [00:04<00:02, 4.56it/s] 69%|██████▉ | 20/29 [00:04<00:01, 4.70it/s] 72%|███████▏ | 21/29 [00:04<00:01, 4.80it/s] 76%|███████▌ | 22/29 [00:04<00:01, 4.87it/s] 79%|███████▉ | 23/29 [00:04<00:01, 4.83it/s] 83%|████████▎ | 24/29 [00:05<00:01, 4.90it/s] 86%|████████▌ | 25/29 [00:05<00:00, 4.92it/s] 90%|████████▉ | 26/29 [00:05<00:00, 4.93it/s] 93%|█████████▎| 27/29 [00:05<00:00, 4.95it/s] 97%|█████████▋| 28/29 [00:05<00:00, 4.85it/s] 100%|██████████| 29/29 [00:06<00:00, 4.91it/s] 100%|██████████| 29/29 [00:06<00:00, 4.70it/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: 3.1ms preprocess, 7.5ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:05, 4.77it/s] 7%|▋ | 2/29 [00:00<00:05, 4.95it/s] 10%|█ | 3/29 [00:00<00:05, 4.99it/s] 14%|█▍ | 4/29 [00:00<00:04, 5.03it/s] 17%|█▋ | 5/29 [00:00<00:04, 5.04it/s] 21%|██ | 6/29 [00:01<00:04, 4.93it/s] 24%|██▍ | 7/29 [00:01<00:04, 4.97it/s] 28%|██▊ | 8/29 [00:01<00:04, 4.98it/s] 31%|███ | 9/29 [00:01<00:04, 4.88it/s] 34%|███▍ | 10/29 [00:02<00:03, 4.91it/s] 38%|███▊ | 11/29 [00:02<00:03, 4.93it/s] 41%|████▏ | 12/29 [00:02<00:03, 4.97it/s] 45%|████▍ | 13/29 [00:02<00:03, 4.99it/s] 48%|████▊ | 14/29 [00:02<00:03, 4.92it/s] 52%|█████▏ | 15/29 [00:03<00:02, 4.96it/s] 55%|█████▌ | 16/29 [00:03<00:02, 5.00it/s] 59%|█████▊ | 17/29 [00:03<00:02, 5.03it/s] 62%|██████▏ | 18/29 [00:03<00:02, 5.05it/s] 66%|██████▌ | 19/29 [00:03<00:02, 4.95it/s] 69%|██████▉ | 20/29 [00:04<00:01, 4.98it/s] 72%|███████▏ | 21/29 [00:04<00:01, 5.00it/s] 76%|███████▌ | 22/29 [00:04<00:01, 5.01it/s] 79%|███████▉ | 23/29 [00:04<00:01, 5.01it/s] 83%|████████▎ | 24/29 [00:04<00:01, 4.84it/s] 86%|████████▌ | 25/29 [00:05<00:00, 4.90it/s] 90%|████████▉ | 26/29 [00:05<00:00, 4.95it/s] 93%|█████████▎| 27/29 [00:05<00:00, 4.99it/s] 97%|█████████▋| 28/29 [00:05<00:00, 5.01it/s] 100%|██████████| 29/29 [00:05<00:00, 4.89it/s] 100%|██████████| 29/29 [00:05<00:00, 4.96it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.2ms Speed: 3.2ms preprocess, 7.2ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:06, 4.64it/s] 7%|▋ | 2/29 [00:00<00:05, 4.86it/s] 10%|█ | 3/29 [00:00<00:05, 4.94it/s] 14%|█▍ | 4/29 [00:00<00:05, 4.86it/s] 17%|█▋ | 5/29 [00:01<00:04, 4.92it/s] 21%|██ | 6/29 [00:01<00:04, 4.96it/s] 24%|██▍ | 7/29 [00:01<00:04, 4.98it/s] 28%|██▊ | 8/29 [00:01<00:04, 5.01it/s] 31%|███ | 9/29 [00:01<00:03, 5.04it/s] 34%|███▍ | 10/29 [00:02<00:03, 4.88it/s] 38%|███▊ | 11/29 [00:02<00:03, 4.94it/s] 41%|████▏ | 12/29 [00:02<00:03, 4.98it/s] 45%|████▍ | 13/29 [00:02<00:03, 5.01it/s] 48%|████▊ | 14/29 [00:02<00:02, 5.04it/s] 52%|█████▏ | 15/29 [00:03<00:02, 4.91it/s] 55%|█████▌ | 16/29 [00:03<00:02, 4.87it/s] 59%|█████▊ | 17/29 [00:03<00:02, 4.86it/s] 62%|██████▏ | 18/29 [00:03<00:02, 4.90it/s] 66%|██████▌ | 19/29 [00:03<00:02, 4.93it/s] 69%|██████▉ | 20/29 [00:04<00:01, 4.77it/s] 72%|███████▏ | 21/29 [00:04<00:01, 4.80it/s] 76%|███████▌ | 22/29 [00:04<00:01, 4.90it/s] 79%|███████▉ | 23/29 [00:04<00:01, 4.96it/s] 83%|████████▎ | 24/29 [00:04<00:01, 5.00it/s] 86%|████████▌ | 25/29 [00:05<00:00, 4.80it/s] 90%|████████▉ | 26/29 [00:05<00:00, 4.85it/s] 93%|█████████▎| 27/29 [00:05<00:00, 4.89it/s] 97%|█████████▋| 28/29 [00:05<00:00, 4.95it/s] 100%|██████████| 29/29 [00:05<00:00, 4.98it/s] 100%|██████████| 29/29 [00:05<00:00, 4.92it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.2ms Speed: 3.0ms preprocess, 7.2ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:05, 4.96it/s] 7%|▋ | 2/29 [00:00<00:05, 5.02it/s] 10%|█ | 3/29 [00:00<00:05, 5.05it/s] 14%|█▍ | 4/29 [00:00<00:04, 5.05it/s] 17%|█▋ | 5/29 [00:01<00:04, 4.85it/s] 21%|██ | 6/29 [00:01<00:04, 4.91it/s] 24%|██▍ | 7/29 [00:01<00:04, 4.94it/s] 28%|██▊ | 8/29 [00:01<00:04, 4.97it/s] 31%|███ | 9/29 [00:01<00:04, 4.96it/s] 34%|███▍ | 10/29 [00:02<00:03, 4.92it/s] 38%|███▊ | 11/29 [00:02<00:03, 4.96it/s] 41%|████▏ | 12/29 [00:02<00:03, 4.99it/s] 45%|████▍ | 13/29 [00:02<00:03, 5.01it/s] 48%|████▊ | 14/29 [00:02<00:02, 5.03it/s] 52%|█████▏ | 15/29 [00:03<00:02, 5.01it/s] 55%|█████▌ | 16/29 [00:03<00:02, 4.99it/s] 59%|█████▊ | 17/29 [00:03<00:02, 5.03it/s] 62%|██████▏ | 18/29 [00:03<00:02, 5.05it/s] 66%|██████▌ | 19/29 [00:03<00:01, 5.07it/s] 69%|██████▉ | 20/29 [00:03<00:01, 5.08it/s] 72%|███████▏ | 21/29 [00:04<00:01, 4.93it/s] 76%|███████▌ | 22/29 [00:04<00:01, 4.96it/s] 79%|███████▉ | 23/29 [00:04<00:01, 4.97it/s] 83%|████████▎ | 24/29 [00:04<00:01, 4.99it/s] 86%|████████▌ | 25/29 [00:05<00:00, 4.99it/s] 90%|████████▉ | 26/29 [00:05<00:00, 4.92it/s] 93%|█████████▎| 27/29 [00:05<00:00, 4.97it/s] 97%|█████████▋| 28/29 [00:05<00:00, 4.95it/s] 100%|██████████| 29/29 [00:05<00:00, 4.99it/s] 100%|██████████| 29/29 [00:05<00:00, 4.98it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt
Specify things to see in the output
Dynamic abstract background with a blonde girl at its center, immersed in energetic splashes of color and bold strokes. (Dynamic abstraction:1.4), (Energetic mood:1.2), (Bold color strokes:1.3), Dynamic, Vibrant. Inspired by the styles of Jackson Pollock and Wassily Kandinsky. 4K UHD image, Cinematic view, Photorealistic, High-definition, Intricate, Sharp, Ultra-detailed, Crisp, cowboy shot, volumetric light, shiny skin, glossy skin, <lora:add_detail:0.8>, <lora:FaceBeauty_qinglong_V3:1.5>
negative_prompt
Specify things to not see in the output
((nipples)), ((portrait)), nsfw, (photorealistic:1.2) and (3d rendering:1.2) and (worst quality:2) and (low quality:2) and (normal quality:2) and (bad anatomy) and (depth of field:1.4) and (bokeh:1.4) and (blurry:1.4), bad-hands-5
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
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0.45
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
1110424535
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 Karras
samping_steps
Number of denoising steps
51
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
ClearVAE_V2.3_fp16.pt
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
add_detail.safetensors
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
FaceBeauty_qinglong_V3.safetensors
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)
bad-hands-5.pt
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/7494b5173ab44f6db93d3a6dce96b4eb/00000-1110424535.webp
https://files.tungsten.run/uploads/34feef51deb0449bb764e0455370fa0b/00001-1110424536.webp
https://files.tungsten.run/uploads/a054e5a087044d388f035b7e99252d62/00002-1110424537.webp
https://files.tungsten.run/uploads/0cb27f7484084945bfc6b3b08f67b8d6/00003-1110424538.webp
Finished in 72.1 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/ClearVAE_V2.3_fp16.pt Full prompt: Dynamic abstract background with a blonde girl at its center, immersed in energetic splashes of color and bold strokes. (Dynamic abstraction:1.4), (Energetic mood:1.2), (Bold color strokes:1.3), Dynamic, Vibrant. Inspired by the styles of Jackson Pollock and Wassily Kandinsky. 4K UHD image, Cinematic view, Photorealistic, High-definition, Intricate, Sharp, Ultra-detailed, Crisp, cowboy shot, volumetric light, shiny skin, glossy skin, <lora:FaceBeauty_qinglong_V3:1.5>, <lora:add_saturation:0.45> Full negative prompt: ((nipples)), ((portrait)), nsfw, (photorealistic:1.2) and (3d rendering:1.2) and (worst quality:2) and (low quality:2) and (normal quality:2) and (bad anatomy) and (depth of field:1.4) and (bokeh:1.4) and (blurry:1.4), bad-hands-5 0%| | 0/51 [00:00<?, ?it/s] 2%|▏ | 1/51 [00:01<01:03, 1.26s/it] 4%|▍ | 2/51 [00:01<00:43, 1.13it/s] 6%|▌ | 3/51 [00:02<00:36, 1.32it/s] 8%|▊ | 4/51 [00:03<00:33, 1.42it/s] 10%|▉ | 5/51 [00:03<00:30, 1.49it/s] 12%|█▏ | 6/51 [00:04<00:29, 1.53it/s] 14%|█▎ | 7/51 [00:04<00:28, 1.56it/s] 16%|█▌ | 8/51 [00:05<00:27, 1.58it/s] 18%|█▊ | 9/51 [00:06<00:26, 1.59it/s] 20%|█▉ | 10/51 [00:06<00:25, 1.60it/s] 22%|██▏ | 11/51 [00:07<00:24, 1.61it/s] 24%|██▎ | 12/51 [00:08<00:24, 1.61it/s] 25%|██▌ | 13/51 [00:08<00:23, 1.61it/s] 27%|██▋ | 14/51 [00:09<00:23, 1.60it/s] 29%|██▉ | 15/51 [00:09<00:22, 1.61it/s] 31%|███▏ | 16/51 [00:10<00:21, 1.61it/s] 33%|███▎ | 17/51 [00:11<00:21, 1.61it/s] 35%|███▌ | 18/51 [00:11<00:20, 1.61it/s] 37%|███▋ | 19/51 [00:12<00:19, 1.61it/s] 39%|███▉ | 20/51 [00:13<00:19, 1.61it/s] 41%|████ | 21/51 [00:13<00:18, 1.61it/s] 43%|████▎ | 22/51 [00:14<00:18, 1.61it/s] 45%|████▌ | 23/51 [00:14<00:17, 1.60it/s] 47%|████▋ | 24/51 [00:15<00:16, 1.60it/s] 49%|████▉ | 25/51 [00:16<00:16, 1.60it/s] 51%|█████ | 26/51 [00:16<00:15, 1.59it/s] 53%|█████▎ | 27/51 [00:17<00:15, 1.60it/s] 55%|█████▍ | 28/51 [00:18<00:14, 1.60it/s] 57%|█████▋ | 29/51 [00:18<00:13, 1.61it/s] 59%|█████▉ | 30/51 [00:19<00:13, 1.61it/s] 61%|██████ | 31/51 [00:19<00:12, 1.61it/s] 63%|██████▎ | 32/51 [00:20<00:11, 1.60it/s] 65%|██████▍ | 33/51 [00:21<00:11, 1.60it/s] 67%|██████▋ | 34/51 [00:21<00:10, 1.60it/s] 69%|██████▊ | 35/51 [00:22<00:10, 1.60it/s] 71%|███████ | 36/51 [00:23<00:09, 1.60it/s] 73%|███████▎ | 37/51 [00:23<00:08, 1.60it/s] 75%|███████▍ | 38/51 [00:24<00:08, 1.60it/s] 76%|███████▋ | 39/51 [00:24<00:07, 1.60it/s] 78%|███████▊ | 40/51 [00:25<00:06, 1.60it/s] 80%|████████ | 41/51 [00:26<00:06, 1.60it/s] 82%|████████▏ | 42/51 [00:26<00:05, 1.60it/s] 84%|████████▍ | 43/51 [00:27<00:05, 1.60it/s] 86%|████████▋ | 44/51 [00:28<00:04, 1.60it/s] 88%|████████▊ | 45/51 [00:28<00:03, 1.59it/s] 90%|█████████ | 46/51 [00:29<00:03, 1.59it/s] 92%|█████████▏| 47/51 [00:29<00:02, 1.60it/s] 94%|█████████▍| 48/51 [00:30<00:01, 1.59it/s] 96%|█████████▌| 49/51 [00:31<00:01, 1.60it/s] 98%|█████████▊| 50/51 [00:31<00:00, 1.59it/s] 100%|██████████| 51/51 [00:32<00:00, 1.59it/s] 100%|██████████| 51/51 [00:32<00:00, 1.57it/s] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.0ms Speed: 4.9ms preprocess, 8.0ms inference, 33.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:10, 2.56it/s] 7%|▋ | 2/29 [00:00<00:07, 3.62it/s] 10%|█ | 3/29 [00:00<00:06, 4.05it/s] 14%|█▍ | 4/29 [00:00<00:05, 4.42it/s] 17%|█▋ | 5/29 [00:01<00:05, 4.56it/s] 21%|██ | 6/29 [00:01<00:04, 4.73it/s] 24%|██▍ | 7/29 [00:01<00:04, 4.86it/s] 28%|██▊ | 8/29 [00:01<00:04, 4.77it/s] 31%|███ | 9/29 [00:02<00:04, 4.88it/s] 34%|███▍ | 10/29 [00:02<00:03, 4.93it/s] 38%|███▊ | 11/29 [00:02<00:03, 4.97it/s] 41%|████▏ | 12/29 [00:02<00:03, 5.00it/s] 45%|████▍ | 13/29 [00:02<00:03, 4.95it/s] 48%|████▊ | 14/29 [00:02<00:03, 4.99it/s] 52%|█████▏ | 15/29 [00:03<00:02, 5.01it/s] 55%|█████▌ | 16/29 [00:03<00:03, 4.20it/s] 59%|█████▊ | 17/29 [00:03<00:02, 4.41it/s] 62%|██████▏ | 18/29 [00:03<00:02, 4.40it/s] 66%|██████▌ | 19/29 [00:04<00:02, 4.56it/s] 69%|██████▉ | 20/29 [00:04<00:01, 4.70it/s] 72%|███████▏ | 21/29 [00:04<00:01, 4.80it/s] 76%|███████▌ | 22/29 [00:04<00:01, 4.87it/s] 79%|███████▉ | 23/29 [00:04<00:01, 4.83it/s] 83%|████████▎ | 24/29 [00:05<00:01, 4.90it/s] 86%|████████▌ | 25/29 [00:05<00:00, 4.92it/s] 90%|████████▉ | 26/29 [00:05<00:00, 4.93it/s] 93%|█████████▎| 27/29 [00:05<00:00, 4.95it/s] 97%|█████████▋| 28/29 [00:05<00:00, 4.85it/s] 100%|██████████| 29/29 [00:06<00:00, 4.91it/s] 100%|██████████| 29/29 [00:06<00:00, 4.70it/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: 3.1ms preprocess, 7.5ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:05, 4.77it/s] 7%|▋ | 2/29 [00:00<00:05, 4.95it/s] 10%|█ | 3/29 [00:00<00:05, 4.99it/s] 14%|█▍ | 4/29 [00:00<00:04, 5.03it/s] 17%|█▋ | 5/29 [00:00<00:04, 5.04it/s] 21%|██ | 6/29 [00:01<00:04, 4.93it/s] 24%|██▍ | 7/29 [00:01<00:04, 4.97it/s] 28%|██▊ | 8/29 [00:01<00:04, 4.98it/s] 31%|███ | 9/29 [00:01<00:04, 4.88it/s] 34%|███▍ | 10/29 [00:02<00:03, 4.91it/s] 38%|███▊ | 11/29 [00:02<00:03, 4.93it/s] 41%|████▏ | 12/29 [00:02<00:03, 4.97it/s] 45%|████▍ | 13/29 [00:02<00:03, 4.99it/s] 48%|████▊ | 14/29 [00:02<00:03, 4.92it/s] 52%|█████▏ | 15/29 [00:03<00:02, 4.96it/s] 55%|█████▌ | 16/29 [00:03<00:02, 5.00it/s] 59%|█████▊ | 17/29 [00:03<00:02, 5.03it/s] 62%|██████▏ | 18/29 [00:03<00:02, 5.05it/s] 66%|██████▌ | 19/29 [00:03<00:02, 4.95it/s] 69%|██████▉ | 20/29 [00:04<00:01, 4.98it/s] 72%|███████▏ | 21/29 [00:04<00:01, 5.00it/s] 76%|███████▌ | 22/29 [00:04<00:01, 5.01it/s] 79%|███████▉ | 23/29 [00:04<00:01, 5.01it/s] 83%|████████▎ | 24/29 [00:04<00:01, 4.84it/s] 86%|████████▌ | 25/29 [00:05<00:00, 4.90it/s] 90%|████████▉ | 26/29 [00:05<00:00, 4.95it/s] 93%|█████████▎| 27/29 [00:05<00:00, 4.99it/s] 97%|█████████▋| 28/29 [00:05<00:00, 5.01it/s] 100%|██████████| 29/29 [00:05<00:00, 4.89it/s] 100%|██████████| 29/29 [00:05<00:00, 4.96it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.2ms Speed: 3.2ms preprocess, 7.2ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:06, 4.64it/s] 7%|▋ | 2/29 [00:00<00:05, 4.86it/s] 10%|█ | 3/29 [00:00<00:05, 4.94it/s] 14%|█▍ | 4/29 [00:00<00:05, 4.86it/s] 17%|█▋ | 5/29 [00:01<00:04, 4.92it/s] 21%|██ | 6/29 [00:01<00:04, 4.96it/s] 24%|██▍ | 7/29 [00:01<00:04, 4.98it/s] 28%|██▊ | 8/29 [00:01<00:04, 5.01it/s] 31%|███ | 9/29 [00:01<00:03, 5.04it/s] 34%|███▍ | 10/29 [00:02<00:03, 4.88it/s] 38%|███▊ | 11/29 [00:02<00:03, 4.94it/s] 41%|████▏ | 12/29 [00:02<00:03, 4.98it/s] 45%|████▍ | 13/29 [00:02<00:03, 5.01it/s] 48%|████▊ | 14/29 [00:02<00:02, 5.04it/s] 52%|█████▏ | 15/29 [00:03<00:02, 4.91it/s] 55%|█████▌ | 16/29 [00:03<00:02, 4.87it/s] 59%|█████▊ | 17/29 [00:03<00:02, 4.86it/s] 62%|██████▏ | 18/29 [00:03<00:02, 4.90it/s] 66%|██████▌ | 19/29 [00:03<00:02, 4.93it/s] 69%|██████▉ | 20/29 [00:04<00:01, 4.77it/s] 72%|███████▏ | 21/29 [00:04<00:01, 4.80it/s] 76%|███████▌ | 22/29 [00:04<00:01, 4.90it/s] 79%|███████▉ | 23/29 [00:04<00:01, 4.96it/s] 83%|████████▎ | 24/29 [00:04<00:01, 5.00it/s] 86%|████████▌ | 25/29 [00:05<00:00, 4.80it/s] 90%|████████▉ | 26/29 [00:05<00:00, 4.85it/s] 93%|█████████▎| 27/29 [00:05<00:00, 4.89it/s] 97%|█████████▋| 28/29 [00:05<00:00, 4.95it/s] 100%|██████████| 29/29 [00:05<00:00, 4.98it/s] 100%|██████████| 29/29 [00:05<00:00, 4.92it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.2ms Speed: 3.0ms preprocess, 7.2ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/29 [00:00<?, ?it/s] 3%|▎ | 1/29 [00:00<00:05, 4.96it/s] 7%|▋ | 2/29 [00:00<00:05, 5.02it/s] 10%|█ | 3/29 [00:00<00:05, 5.05it/s] 14%|█▍ | 4/29 [00:00<00:04, 5.05it/s] 17%|█▋ | 5/29 [00:01<00:04, 4.85it/s] 21%|██ | 6/29 [00:01<00:04, 4.91it/s] 24%|██▍ | 7/29 [00:01<00:04, 4.94it/s] 28%|██▊ | 8/29 [00:01<00:04, 4.97it/s] 31%|███ | 9/29 [00:01<00:04, 4.96it/s] 34%|███▍ | 10/29 [00:02<00:03, 4.92it/s] 38%|███▊ | 11/29 [00:02<00:03, 4.96it/s] 41%|████▏ | 12/29 [00:02<00:03, 4.99it/s] 45%|████▍ | 13/29 [00:02<00:03, 5.01it/s] 48%|████▊ | 14/29 [00:02<00:02, 5.03it/s] 52%|█████▏ | 15/29 [00:03<00:02, 5.01it/s] 55%|█████▌ | 16/29 [00:03<00:02, 4.99it/s] 59%|█████▊ | 17/29 [00:03<00:02, 5.03it/s] 62%|██████▏ | 18/29 [00:03<00:02, 5.05it/s] 66%|██████▌ | 19/29 [00:03<00:01, 5.07it/s] 69%|██████▉ | 20/29 [00:03<00:01, 5.08it/s] 72%|███████▏ | 21/29 [00:04<00:01, 4.93it/s] 76%|███████▌ | 22/29 [00:04<00:01, 4.96it/s] 79%|███████▉ | 23/29 [00:04<00:01, 4.97it/s] 83%|████████▎ | 24/29 [00:04<00:01, 4.99it/s] 86%|████████▌ | 25/29 [00:05<00:00, 4.99it/s] 90%|████████▉ | 26/29 [00:05<00:00, 4.92it/s] 93%|█████████▎| 27/29 [00:05<00:00, 4.97it/s] 97%|█████████▋| 28/29 [00:05<00:00, 4.95it/s] 100%|██████████| 29/29 [00:05<00:00, 4.99it/s] 100%|██████████| 29/29 [00:05<00:00, 4.98it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s Uploading outputs... Finished.