picx-real
picx-real
50 stars
Version: v1.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
saturation
Adjust saturation
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
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.
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.
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.
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.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
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.
Sign in to run this model for free!
Output
https://files.tungsten.run/uploads/a6d47df92864436aa63152803f211cf6/00000-3550611454.webp
https://files.tungsten.run/uploads/6d7f31d7e06b4e64846e66ea4d11cdf6/00001-3550611455.webp
https://files.tungsten.run/uploads/d0afd81f860f409884c1bcda6c696700/00002-3550611456.webp
https://files.tungsten.run/uploads/74becd28f9b940808140ee55681eede7/00003-3550611457.webp
This example was created by evevalentine2017
Finished in 91.6 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/vae-ft-mse-840000-ema-pruned_fp16.safetensors Full prompt: illustration, cartoon, soothing tones, calm colors, (masterpiece drawning, high quality, horror:1.3), (solo:1.1), a digital art of an undead girl, (pink, heart, love:1.2), wounds, gothic gown, (deathcore:1.2), mistery pink forest, Extreme detail, morbid, paper texture, 2d, high angle, <lora:more_details:0.7>, <lora:color_slider_v10:1.5>, <lora:add_brightness:0.5>, <lora:contrast_slider_v10:-1.36> Full negative prompt: ((portrait:2)), ((mouth:2)), ((lips:2)), ((lipstick:2)), ((focus on face:2)), (focus on ass), nsfw, nipples, breasts, (CyberRealistic_Negative-neg:0.8), (headgear:1.2), mature, curvy, big tits, panties, shorts, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured, ugly, large breasts, out of focus, blur, blurry, low details, normal quality, bad quality, low quality, Wart , Rash , Boil , Cyst , worms, ugly, disgusting, unrealistic, watermark, logo, cartoon, anime, manga, illustration, painting, 3d, bad anatomy, worst quality, low quality, low resolution, extra fingers, wrong proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image, ng_deepnegative_v1_75t, realisticvision-negative-embedding 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:01<00:45, 1.97s/it] 8%|▊ | 2/24 [00:03<00:42, 1.92s/it] 12%|█▎ | 3/24 [00:05<00:39, 1.89s/it] 17%|█▋ | 4/24 [00:07<00:38, 1.92s/it] 21%|██ | 5/24 [00:09<00:34, 1.80s/it] 25%|██▌ | 6/24 [00:11<00:32, 1.79s/it] 29%|██▉ | 7/24 [00:12<00:29, 1.74s/it] 33%|███▎ | 8/24 [00:14<00:27, 1.70s/it] 38%|███▊ | 9/24 [00:15<00:25, 1.70s/it] 42%|████▏ | 10/24 [00:17<00:24, 1.72s/it] 46%|████▌ | 11/24 [00:19<00:22, 1.72s/it] 50%|█████ | 12/24 [00:21<00:20, 1.70s/it] 54%|█████▍ | 13/24 [00:22<00:18, 1.64s/it] 58%|█████▊ | 14/24 [00:24<00:16, 1.67s/it] 62%|██████▎ | 15/24 [00:26<00:14, 1.66s/it] 67%|██████▋ | 16/24 [00:27<00:13, 1.66s/it] 71%|███████ | 17/24 [00:29<00:11, 1.65s/it] 75%|███████▌ | 18/24 [00:30<00:09, 1.65s/it] 79%|███████▉ | 19/24 [00:32<00:07, 1.58s/it] 83%|████████▎ | 20/24 [00:33<00:06, 1.54s/it] 88%|████████▊ | 21/24 [00:35<00:04, 1.49s/it] 92%|█████████▏| 22/24 [00:36<00:02, 1.48s/it] 96%|█████████▌| 23/24 [00:37<00:01, 1.30s/it] 100%|██████████| 24/24 [00:38<00:00, 1.09s/it] 100%|██████████| 24/24 [00:38<00:00, 1.59s/it] Decoding latents in cuda:0... done in 0.95s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.2ms preprocess, 7.8ms inference, 24.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:06, 1.48it/s] 18%|█▊ | 2/11 [00:01<00:04, 1.81it/s] 27%|██▋ | 3/11 [00:01<00:04, 1.96it/s] 36%|███▋ | 4/11 [00:02<00:03, 2.02it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.08it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.19it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.27it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.37it/s] 82%|████████▏ | 9/11 [00:04<00:00, 2.39it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.68it/s] 100%|██████████| 11/11 [00:04<00:00, 3.11it/s] 100%|██████████| 11/11 [00:04<00:00, 2.38it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.01s 0: 640x640 (no detections), 7.6ms Speed: 2.9ms preprocess, 7.6ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 8.8ms Speed: 3.0ms preprocess, 8.8ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.04it/s] 18%|█▊ | 2/11 [00:01<00:04, 1.98it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.02it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.02it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.05it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.17it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.27it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.36it/s] 82%|████████▏ | 9/11 [00:04<00:00, 2.36it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.66it/s] 100%|██████████| 11/11 [00:04<00:00, 3.10it/s] 100%|██████████| 11/11 [00:04<00:00, 2.42it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.3ms Speed: 3.0ms preprocess, 7.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.01it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.10it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.14it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.17it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.17it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.24it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.29it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.34it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.37it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.67it/s] 100%|██████████| 11/11 [00:04<00:00, 3.12it/s] 100%|██████████| 11/11 [00:04<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.7ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.03it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.11it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.15it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.18it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.14it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.24it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.30it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.37it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.39it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.66it/s] 100%|██████████| 11/11 [00:04<00:00, 3.09it/s] 100%|██████████| 11/11 [00:04<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 8.1ms Speed: 3.1ms preprocess, 8.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.10it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.13it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.15it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.15it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.15it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.26it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.30it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.37it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.38it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.69it/s] 100%|██████████| 11/11 [00:04<00:00, 3.13it/s] 100%|██████████| 11/11 [00:04<00:00, 2.49it/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: 2.7ms preprocess, 7.5ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.03it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.14it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.17it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.22it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.21it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.25it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.32it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.35it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.39it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.70it/s] 100%|██████████| 11/11 [00:04<00:00, 3.15it/s] 100%|██████████| 11/11 [00:04<00:00, 2.50it/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%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.04it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.12it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.14it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.16it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.16it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.27it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.32it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.35it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.37it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.64it/s] 100%|██████████| 11/11 [00:04<00:00, 3.07it/s] 100%|██████████| 11/11 [00:04<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:05, 1.94it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.02it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.08it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.12it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.14it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.26it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.33it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.36it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.40it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.70it/s] 100%|██████████| 11/11 [00:04<00:00, 3.13it/s] 100%|██████████| 11/11 [00:04<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
saturation
Adjust saturation
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
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.
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.
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.
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.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
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.
Sign in to run this model for free!
https://files.tungsten.run/uploads/a6d47df92864436aa63152803f211cf6/00000-3550611454.webp
https://files.tungsten.run/uploads/6d7f31d7e06b4e64846e66ea4d11cdf6/00001-3550611455.webp
https://files.tungsten.run/uploads/d0afd81f860f409884c1bcda6c696700/00002-3550611456.webp
https://files.tungsten.run/uploads/74becd28f9b940808140ee55681eede7/00003-3550611457.webp
This example was created by evevalentine2017
Finished in 91.6 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/vae-ft-mse-840000-ema-pruned_fp16.safetensors Full prompt: illustration, cartoon, soothing tones, calm colors, (masterpiece drawning, high quality, horror:1.3), (solo:1.1), a digital art of an undead girl, (pink, heart, love:1.2), wounds, gothic gown, (deathcore:1.2), mistery pink forest, Extreme detail, morbid, paper texture, 2d, high angle, <lora:more_details:0.7>, <lora:color_slider_v10:1.5>, <lora:add_brightness:0.5>, <lora:contrast_slider_v10:-1.36> Full negative prompt: ((portrait:2)), ((mouth:2)), ((lips:2)), ((lipstick:2)), ((focus on face:2)), (focus on ass), nsfw, nipples, breasts, (CyberRealistic_Negative-neg:0.8), (headgear:1.2), mature, curvy, big tits, panties, shorts, painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured, ugly, large breasts, out of focus, blur, blurry, low details, normal quality, bad quality, low quality, Wart , Rash , Boil , Cyst , worms, ugly, disgusting, unrealistic, watermark, logo, cartoon, anime, manga, illustration, painting, 3d, bad anatomy, worst quality, low quality, low resolution, extra fingers, wrong proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image, ng_deepnegative_v1_75t, realisticvision-negative-embedding 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:01<00:45, 1.97s/it] 8%|▊ | 2/24 [00:03<00:42, 1.92s/it] 12%|█▎ | 3/24 [00:05<00:39, 1.89s/it] 17%|█▋ | 4/24 [00:07<00:38, 1.92s/it] 21%|██ | 5/24 [00:09<00:34, 1.80s/it] 25%|██▌ | 6/24 [00:11<00:32, 1.79s/it] 29%|██▉ | 7/24 [00:12<00:29, 1.74s/it] 33%|███▎ | 8/24 [00:14<00:27, 1.70s/it] 38%|███▊ | 9/24 [00:15<00:25, 1.70s/it] 42%|████▏ | 10/24 [00:17<00:24, 1.72s/it] 46%|████▌ | 11/24 [00:19<00:22, 1.72s/it] 50%|█████ | 12/24 [00:21<00:20, 1.70s/it] 54%|█████▍ | 13/24 [00:22<00:18, 1.64s/it] 58%|█████▊ | 14/24 [00:24<00:16, 1.67s/it] 62%|██████▎ | 15/24 [00:26<00:14, 1.66s/it] 67%|██████▋ | 16/24 [00:27<00:13, 1.66s/it] 71%|███████ | 17/24 [00:29<00:11, 1.65s/it] 75%|███████▌ | 18/24 [00:30<00:09, 1.65s/it] 79%|███████▉ | 19/24 [00:32<00:07, 1.58s/it] 83%|████████▎ | 20/24 [00:33<00:06, 1.54s/it] 88%|████████▊ | 21/24 [00:35<00:04, 1.49s/it] 92%|█████████▏| 22/24 [00:36<00:02, 1.48s/it] 96%|█████████▌| 23/24 [00:37<00:01, 1.30s/it] 100%|██████████| 24/24 [00:38<00:00, 1.09s/it] 100%|██████████| 24/24 [00:38<00:00, 1.59s/it] Decoding latents in cuda:0... done in 0.95s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.2ms preprocess, 7.8ms inference, 24.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:06, 1.48it/s] 18%|█▊ | 2/11 [00:01<00:04, 1.81it/s] 27%|██▋ | 3/11 [00:01<00:04, 1.96it/s] 36%|███▋ | 4/11 [00:02<00:03, 2.02it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.08it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.19it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.27it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.37it/s] 82%|████████▏ | 9/11 [00:04<00:00, 2.39it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.68it/s] 100%|██████████| 11/11 [00:04<00:00, 3.11it/s] 100%|██████████| 11/11 [00:04<00:00, 2.38it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.01s 0: 640x640 (no detections), 7.6ms Speed: 2.9ms preprocess, 7.6ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 8.8ms Speed: 3.0ms preprocess, 8.8ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.04it/s] 18%|█▊ | 2/11 [00:01<00:04, 1.98it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.02it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.02it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.05it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.17it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.27it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.36it/s] 82%|████████▏ | 9/11 [00:04<00:00, 2.36it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.66it/s] 100%|██████████| 11/11 [00:04<00:00, 3.10it/s] 100%|██████████| 11/11 [00:04<00:00, 2.42it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.3ms Speed: 3.0ms preprocess, 7.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.01it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.10it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.14it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.17it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.17it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.24it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.29it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.34it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.37it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.67it/s] 100%|██████████| 11/11 [00:04<00:00, 3.12it/s] 100%|██████████| 11/11 [00:04<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.7ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.03it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.11it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.15it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.18it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.14it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.24it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.30it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.37it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.39it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.66it/s] 100%|██████████| 11/11 [00:04<00:00, 3.09it/s] 100%|██████████| 11/11 [00:04<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 8.1ms Speed: 3.1ms preprocess, 8.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.10it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.13it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.15it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.15it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.15it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.26it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.30it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.37it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.38it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.69it/s] 100%|██████████| 11/11 [00:04<00:00, 3.13it/s] 100%|██████████| 11/11 [00:04<00:00, 2.49it/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: 2.7ms preprocess, 7.5ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.03it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.14it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.17it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.22it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.21it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.25it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.32it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.35it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.39it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.70it/s] 100%|██████████| 11/11 [00:04<00:00, 3.15it/s] 100%|██████████| 11/11 [00:04<00:00, 2.50it/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%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:04, 2.04it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.12it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.14it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.16it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.16it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.27it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.32it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.35it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.37it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.64it/s] 100%|██████████| 11/11 [00:04<00:00, 3.07it/s] 100%|██████████| 11/11 [00:04<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:05, 1.94it/s] 18%|█▊ | 2/11 [00:00<00:04, 2.02it/s] 27%|██▋ | 3/11 [00:01<00:03, 2.08it/s] 36%|███▋ | 4/11 [00:01<00:03, 2.12it/s] 45%|████▌ | 5/11 [00:02<00:02, 2.14it/s] 55%|█████▍ | 6/11 [00:02<00:02, 2.26it/s] 64%|██████▎ | 7/11 [00:03<00:01, 2.33it/s] 73%|███████▎ | 8/11 [00:03<00:01, 2.36it/s] 82%|████████▏ | 9/11 [00:03<00:00, 2.40it/s] 91%|█████████ | 10/11 [00:04<00:00, 2.70it/s] 100%|██████████| 11/11 [00:04<00:00, 3.13it/s] 100%|██████████| 11/11 [00:04<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s Uploading outputs... Finished.