tungsten-logo
Sign In
Curly Redheads with Hello World SDXL
hello-world-sdxl:v3.2
evevalentine2017
evevalentine2017
·
Jan 26
396
Input
prompt
Specify things to see in the output
full shot, point of view, ultra wide angle, fisheye lens, from below, 1 girl, sitting, long thin legs, wide hips, short blue skirt, white cropped tight shirt, white sneakers, flat chest, scarlet short wavy hairs, wicked, confused, sad, heavily blushing, bright red eyes, two legs, masterpiece, ultrasharp, dramatic lighting, analog film, raw photo, polaroid scan, fashion photoshoot, analog sharp grain, ultra sharp, faded, detailed skin, <lora:SDXL Detail:1>
negative_prompt
Specify things to not see in the output
(worst quality, low resolution, bad hands, open mouth), distorted, twisted, watermark, looking at the viewer
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
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
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
3000021533
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
Restart
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
4
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>
SDXL Detail.safetensors
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/dc0a7ded274c4e3a8f6054fbbde2d0c7/00000-3000021533.webp
https://files.tungsten.run/uploads/9f9de7e1096d444fa27ab817437f5f3c/00001-3000021534.webp
https://files.tungsten.run/uploads/c5afffc4b62c40f9a106a7b2990a17cf/00002-3000021535.webp
Finished in 227.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: full shot, point of view, ultra wide angle, fisheye lens, from below, 1 girl, sitting, long thin legs, wide hips, short blue skirt, white cropped tight shirt, white sneakers, flat chest, scarlet short wavy hairs, wicked, confused, sad, heavily blushing, bright red eyes, two legs, masterpiece, ultrasharp, dramatic lighting, analog film, raw photo, polaroid scan, fashion photoshoot, analog sharp grain, ultra sharp, faded, detailed skin, <lora:SDXL Detail:1> Full negative prompt: (worst quality, low resolution, bad hands, open mouth), distorted, twisted, watermark, looking at the viewer 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:54, 3.96s/it] 7%|▋ | 2/30 [00:06<01:27, 3.12s/it] 10%|█ | 3/30 [00:09<01:17, 2.86s/it] 13%|█▎ | 4/30 [00:11<01:11, 2.75s/it] 17%|█▋ | 5/30 [00:14<01:07, 2.68s/it] 20%|██ | 6/30 [00:16<01:03, 2.64s/it] 23%|██▎ | 7/30 [00:19<01:00, 2.62s/it] 27%|██▋ | 8/30 [00:21<00:57, 2.60s/it] 30%|███ | 9/30 [00:24<00:54, 2.59s/it] 33%|███▎ | 10/30 [00:27<00:51, 2.58s/it] 37%|███▋ | 11/30 [00:29<00:48, 2.57s/it] 40%|████ | 12/30 [00:32<00:46, 2.57s/it] 43%|████▎ | 13/30 [00:34<00:43, 2.56s/it] 47%|████▋ | 14/30 [00:37<00:40, 2.55s/it] 50%|█████ | 15/30 [00:39<00:38, 2.55s/it] 53%|█████▎ | 16/30 [00:42<00:35, 2.54s/it] 57%|█████▋ | 17/30 [00:44<00:32, 2.54s/it] 60%|██████ | 18/30 [00:47<00:30, 2.54s/it] 63%|██████▎ | 19/30 [00:49<00:27, 2.54s/it] 67%|██████▋ | 20/30 [00:52<00:25, 2.54s/it] 70%|███████ | 21/30 [00:54<00:22, 2.53s/it] 73%|███████▎ | 22/30 [00:57<00:20, 2.53s/it] 77%|███████▋ | 23/30 [00:59<00:17, 2.53s/it] 80%|████████ | 24/30 [01:02<00:15, 2.52s/it] 83%|████████▎ | 25/30 [01:05<00:12, 2.52s/it] 87%|████████▋ | 26/30 [01:07<00:10, 2.52s/it] 90%|█████████ | 27/30 [01:10<00:07, 2.52s/it] 93%|█████████▎| 28/30 [01:12<00:05, 2.52s/it] 97%|█████████▋| 29/30 [01:15<00:02, 2.52s/it] 100%|██████████| 30/30 [01:16<00:00, 2.14s/it] 100%|██████████| 30/30 [01:16<00:00, 2.54s/it] Decoding latents in cuda:0... done in 2.41s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 8.1ms Speed: 3.3ms preprocess, 8.1ms inference, 30.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:02<00:27, 2.10s/it] 14%|█▍ | 2/14 [00:04<00:29, 2.48s/it] 21%|██▏ | 3/14 [00:06<00:24, 2.20s/it] 29%|██▊ | 4/14 [00:07<00:18, 1.82s/it] 36%|███▌ | 5/14 [00:09<00:14, 1.62s/it] 43%|████▎ | 6/14 [00:10<00:11, 1.48s/it] 50%|█████ | 7/14 [00:11<00:09, 1.40s/it] 57%|█████▋ | 8/14 [00:12<00:08, 1.36s/it] 64%|██████▍ | 9/14 [00:14<00:06, 1.32s/it] 71%|███████▏ | 10/14 [00:15<00:05, 1.30s/it] 79%|███████▊ | 11/14 [00:16<00:03, 1.29s/it] 86%|████████▌ | 12/14 [00:17<00:02, 1.28s/it] 93%|█████████▎| 13/14 [00:19<00:01, 1.26s/it] 100%|██████████| 14/14 [00:19<00:00, 1.06s/it] 100%|██████████| 14/14 [00:19<00:00, 1.41s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.7ms Speed: 3.2ms preprocess, 7.7ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.28s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.28s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.27s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.28s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.27s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.26s/it] 50%|█████ | 7/14 [00:08<00:08, 1.26s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.27s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.26s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.27s/it] 79%|███████▊ | 11/14 [00:13<00:03, 1.27s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.27s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.27s/it] 100%|██████████| 14/14 [00:17<00:00, 1.08s/it] 100%|██████████| 14/14 [00:17<00:00, 1.22s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:17, 1.31s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.28s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.28s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.28s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.27s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.27s/it] 50%|█████ | 7/14 [00:08<00:08, 1.27s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.26s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.26s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.25s/it] 79%|███████▊ | 11/14 [00:13<00:03, 1.25s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.25s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.25s/it] 100%|██████████| 14/14 [00:17<00:00, 1.06s/it] 100%|██████████| 14/14 [00:17<00:00, 1.22s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 2.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.30s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.31s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.28s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.27s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.26s/it] 43%|████▎ | 6/14 [00:07<00:09, 1.25s/it] 50%|█████ | 7/14 [00:08<00:08, 1.25s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.25s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.26s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.26s/it] 79%|███████▊ | 11/14 [00:13<00:03, 1.27s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.27s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.27s/it] 100%|██████████| 14/14 [00:17<00:00, 1.08s/it] 100%|██████████| 14/14 [00:17<00:00, 1.22s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.30s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.29s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.28s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.28s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.28s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.29s/it] 50%|█████ | 7/14 [00:09<00:09, 1.29s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.28s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.28s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.28s/it] 79%|███████▊ | 11/14 [00:14<00:03, 1.27s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.27s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.26s/it] 100%|██████████| 14/14 [00:17<00:00, 1.08s/it] 100%|██████████| 14/14 [00:17<00:00, 1.23s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.4ms preprocess, 7.4ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.27s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.25s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.28s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.28s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.27s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.26s/it] 50%|█████ | 7/14 [00:08<00:08, 1.27s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.25s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.27s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.28s/it] 79%|███████▊ | 11/14 [00:14<00:03, 1.29s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.29s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.28s/it] 100%|██████████| 14/14 [00:17<00:00, 1.09s/it] 100%|██████████| 14/14 [00:17<00:00, 1.23s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.2ms Speed: 3.0ms preprocess, 7.2ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.27s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.28s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.30s/it] 29%|██▊ | 4/14 [00:05<00:13, 1.30s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.30s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.28s/it] 50%|█████ | 7/14 [00:08<00:08, 1.26s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.26s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.27s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.28s/it] 79%|███████▊ | 11/14 [00:14<00:03, 1.28s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.28s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.28s/it] 100%|██████████| 14/14 [00:17<00:00, 1.09s/it] 100%|██████████| 14/14 [00:17<00:00, 1.23s/it] 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
full shot, point of view, ultra wide angle, fisheye lens, from below, 1 girl, sitting, long thin legs, wide hips, short blue skirt, white cropped tight shirt, white sneakers, flat chest, scarlet short wavy hairs, wicked, confused, sad, heavily blushing, bright red eyes, two legs, masterpiece, ultrasharp, dramatic lighting, analog film, raw photo, polaroid scan, fashion photoshoot, analog sharp grain, ultra sharp, faded, detailed skin, <lora:SDXL Detail:1>
negative_prompt
Specify things to not see in the output
(worst quality, low resolution, bad hands, open mouth), distorted, twisted, watermark, looking at the viewer
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
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
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
3000021533
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
Restart
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
4
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>
SDXL Detail.safetensors
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/dc0a7ded274c4e3a8f6054fbbde2d0c7/00000-3000021533.webp
https://files.tungsten.run/uploads/9f9de7e1096d444fa27ab817437f5f3c/00001-3000021534.webp
https://files.tungsten.run/uploads/c5afffc4b62c40f9a106a7b2990a17cf/00002-3000021535.webp
Finished in 227.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: full shot, point of view, ultra wide angle, fisheye lens, from below, 1 girl, sitting, long thin legs, wide hips, short blue skirt, white cropped tight shirt, white sneakers, flat chest, scarlet short wavy hairs, wicked, confused, sad, heavily blushing, bright red eyes, two legs, masterpiece, ultrasharp, dramatic lighting, analog film, raw photo, polaroid scan, fashion photoshoot, analog sharp grain, ultra sharp, faded, detailed skin, <lora:SDXL Detail:1> Full negative prompt: (worst quality, low resolution, bad hands, open mouth), distorted, twisted, watermark, looking at the viewer 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:54, 3.96s/it] 7%|▋ | 2/30 [00:06<01:27, 3.12s/it] 10%|█ | 3/30 [00:09<01:17, 2.86s/it] 13%|█▎ | 4/30 [00:11<01:11, 2.75s/it] 17%|█▋ | 5/30 [00:14<01:07, 2.68s/it] 20%|██ | 6/30 [00:16<01:03, 2.64s/it] 23%|██▎ | 7/30 [00:19<01:00, 2.62s/it] 27%|██▋ | 8/30 [00:21<00:57, 2.60s/it] 30%|███ | 9/30 [00:24<00:54, 2.59s/it] 33%|███▎ | 10/30 [00:27<00:51, 2.58s/it] 37%|███▋ | 11/30 [00:29<00:48, 2.57s/it] 40%|████ | 12/30 [00:32<00:46, 2.57s/it] 43%|████▎ | 13/30 [00:34<00:43, 2.56s/it] 47%|████▋ | 14/30 [00:37<00:40, 2.55s/it] 50%|█████ | 15/30 [00:39<00:38, 2.55s/it] 53%|█████▎ | 16/30 [00:42<00:35, 2.54s/it] 57%|█████▋ | 17/30 [00:44<00:32, 2.54s/it] 60%|██████ | 18/30 [00:47<00:30, 2.54s/it] 63%|██████▎ | 19/30 [00:49<00:27, 2.54s/it] 67%|██████▋ | 20/30 [00:52<00:25, 2.54s/it] 70%|███████ | 21/30 [00:54<00:22, 2.53s/it] 73%|███████▎ | 22/30 [00:57<00:20, 2.53s/it] 77%|███████▋ | 23/30 [00:59<00:17, 2.53s/it] 80%|████████ | 24/30 [01:02<00:15, 2.52s/it] 83%|████████▎ | 25/30 [01:05<00:12, 2.52s/it] 87%|████████▋ | 26/30 [01:07<00:10, 2.52s/it] 90%|█████████ | 27/30 [01:10<00:07, 2.52s/it] 93%|█████████▎| 28/30 [01:12<00:05, 2.52s/it] 97%|█████████▋| 29/30 [01:15<00:02, 2.52s/it] 100%|██████████| 30/30 [01:16<00:00, 2.14s/it] 100%|██████████| 30/30 [01:16<00:00, 2.54s/it] Decoding latents in cuda:0... done in 2.41s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 8.1ms Speed: 3.3ms preprocess, 8.1ms inference, 30.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:02<00:27, 2.10s/it] 14%|█▍ | 2/14 [00:04<00:29, 2.48s/it] 21%|██▏ | 3/14 [00:06<00:24, 2.20s/it] 29%|██▊ | 4/14 [00:07<00:18, 1.82s/it] 36%|███▌ | 5/14 [00:09<00:14, 1.62s/it] 43%|████▎ | 6/14 [00:10<00:11, 1.48s/it] 50%|█████ | 7/14 [00:11<00:09, 1.40s/it] 57%|█████▋ | 8/14 [00:12<00:08, 1.36s/it] 64%|██████▍ | 9/14 [00:14<00:06, 1.32s/it] 71%|███████▏ | 10/14 [00:15<00:05, 1.30s/it] 79%|███████▊ | 11/14 [00:16<00:03, 1.29s/it] 86%|████████▌ | 12/14 [00:17<00:02, 1.28s/it] 93%|█████████▎| 13/14 [00:19<00:01, 1.26s/it] 100%|██████████| 14/14 [00:19<00:00, 1.06s/it] 100%|██████████| 14/14 [00:19<00:00, 1.41s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.7ms Speed: 3.2ms preprocess, 7.7ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.28s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.28s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.27s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.28s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.27s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.26s/it] 50%|█████ | 7/14 [00:08<00:08, 1.26s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.27s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.26s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.27s/it] 79%|███████▊ | 11/14 [00:13<00:03, 1.27s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.27s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.27s/it] 100%|██████████| 14/14 [00:17<00:00, 1.08s/it] 100%|██████████| 14/14 [00:17<00:00, 1.22s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:17, 1.31s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.28s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.28s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.28s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.27s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.27s/it] 50%|█████ | 7/14 [00:08<00:08, 1.27s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.26s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.26s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.25s/it] 79%|███████▊ | 11/14 [00:13<00:03, 1.25s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.25s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.25s/it] 100%|██████████| 14/14 [00:17<00:00, 1.06s/it] 100%|██████████| 14/14 [00:17<00:00, 1.22s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 2.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.30s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.31s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.28s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.27s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.26s/it] 43%|████▎ | 6/14 [00:07<00:09, 1.25s/it] 50%|█████ | 7/14 [00:08<00:08, 1.25s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.25s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.26s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.26s/it] 79%|███████▊ | 11/14 [00:13<00:03, 1.27s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.27s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.27s/it] 100%|██████████| 14/14 [00:17<00:00, 1.08s/it] 100%|██████████| 14/14 [00:17<00:00, 1.22s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.30s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.29s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.28s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.28s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.28s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.29s/it] 50%|█████ | 7/14 [00:09<00:09, 1.29s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.28s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.28s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.28s/it] 79%|███████▊ | 11/14 [00:14<00:03, 1.27s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.27s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.26s/it] 100%|██████████| 14/14 [00:17<00:00, 1.08s/it] 100%|██████████| 14/14 [00:17<00:00, 1.23s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.4ms preprocess, 7.4ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.27s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.25s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.28s/it] 29%|██▊ | 4/14 [00:05<00:12, 1.28s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.27s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.26s/it] 50%|█████ | 7/14 [00:08<00:08, 1.27s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.25s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.27s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.28s/it] 79%|███████▊ | 11/14 [00:14<00:03, 1.29s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.29s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.28s/it] 100%|██████████| 14/14 [00:17<00:00, 1.09s/it] 100%|██████████| 14/14 [00:17<00:00, 1.23s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.2ms Speed: 3.0ms preprocess, 7.2ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:16, 1.27s/it] 14%|█▍ | 2/14 [00:02<00:15, 1.28s/it] 21%|██▏ | 3/14 [00:03<00:14, 1.30s/it] 29%|██▊ | 4/14 [00:05<00:13, 1.30s/it] 36%|███▌ | 5/14 [00:06<00:11, 1.30s/it] 43%|████▎ | 6/14 [00:07<00:10, 1.28s/it] 50%|█████ | 7/14 [00:08<00:08, 1.26s/it] 57%|█████▋ | 8/14 [00:10<00:07, 1.26s/it] 64%|██████▍ | 9/14 [00:11<00:06, 1.27s/it] 71%|███████▏ | 10/14 [00:12<00:05, 1.28s/it] 79%|███████▊ | 11/14 [00:14<00:03, 1.28s/it] 86%|████████▌ | 12/14 [00:15<00:02, 1.28s/it] 93%|█████████▎| 13/14 [00:16<00:01, 1.28s/it] 100%|██████████| 14/14 [00:17<00:00, 1.09s/it] 100%|██████████| 14/14 [00:17<00:00, 1.23s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s Uploading outputs... Finished.