tungsten-logo
Sign In
Art by Adrian Ghenie & Jean Giraud with Artisanal
artisanal-sdxl:alpha-1
evevalentine2017
evevalentine2017
·
Mar 6
376
Input
prompt
Specify things to see in the output
1 warrior, detailed face, detailed gradient shadow (best quality), sci-fi futuristic, art by Adrian Ghenie, Jean Giraud
negative_prompt
Specify things to not see in the output
unaestheticXL2v10, (worst quality, low quality:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation. tattoo, watermark, text,
num_outputs
Number of output images
3
width
Output image width
1024
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
0.45
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.
3631489396
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
47
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
Output
https://files.tungsten.run/uploads/de69a25e933346ddab50b57cdd97ddb2/00000-3631489396.webp
https://files.tungsten.run/uploads/d72cae1d96ac43b698a5507ecff7b131/00001-3631489397.webp
https://files.tungsten.run/uploads/1ff06a41fa4a45e09b55fd2000ca975e/00002-3631489398.webp
Finished in 80.8 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1 warrior, detailed face, detailed gradient shadow (best quality), sci-fi futuristic, art by Adrian Ghenie, Jean Giraud Full negative prompt: unaestheticXL2v10, (worst quality, low quality:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation. tattoo, watermark, text, 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:00<00:42, 1.09it/s] 4%|▍ | 2/47 [00:01<00:40, 1.10it/s] 6%|▋ | 3/47 [00:02<00:39, 1.11it/s] 9%|▊ | 4/47 [00:03<00:38, 1.11it/s] 11%|█ | 5/47 [00:04<00:37, 1.11it/s] 13%|█▎ | 6/47 [00:05<00:37, 1.11it/s] 15%|█▍ | 7/47 [00:06<00:36, 1.11it/s] 17%|█▋ | 8/47 [00:07<00:35, 1.11it/s] 19%|█▉ | 9/47 [00:08<00:34, 1.11it/s] 21%|██▏ | 10/47 [00:09<00:33, 1.11it/s] 23%|██▎ | 11/47 [00:09<00:32, 1.11it/s] 26%|██▌ | 12/47 [00:10<00:31, 1.11it/s] 28%|██▊ | 13/47 [00:11<00:30, 1.10it/s] 30%|██▉ | 14/47 [00:12<00:30, 1.09it/s] 32%|███▏ | 15/47 [00:13<00:29, 1.09it/s] 34%|███▍ | 16/47 [00:14<00:28, 1.08it/s] 36%|███▌ | 17/47 [00:15<00:27, 1.08it/s] 38%|███▊ | 18/47 [00:16<00:26, 1.08it/s] 40%|████ | 19/47 [00:17<00:25, 1.08it/s] 43%|████▎ | 20/47 [00:18<00:25, 1.08it/s] 45%|████▍ | 21/47 [00:19<00:24, 1.07it/s] 47%|████▋ | 22/47 [00:20<00:23, 1.07it/s] 49%|████▉ | 23/47 [00:21<00:22, 1.07it/s] 51%|█████ | 24/47 [00:22<00:21, 1.07it/s] 53%|█████▎ | 25/47 [00:22<00:20, 1.07it/s] 55%|█████▌ | 26/47 [00:23<00:19, 1.07it/s] 57%|█████▋ | 27/47 [00:24<00:18, 1.06it/s] 60%|█████▉ | 28/47 [00:25<00:17, 1.06it/s] 62%|██████▏ | 29/47 [00:26<00:16, 1.06it/s] 64%|██████▍ | 30/47 [00:27<00:16, 1.06it/s] 66%|██████▌ | 31/47 [00:28<00:15, 1.06it/s] 68%|██████▊ | 32/47 [00:29<00:14, 1.06it/s] 70%|███████ | 33/47 [00:30<00:13, 1.06it/s] 72%|███████▏ | 34/47 [00:31<00:12, 1.05it/s] 74%|███████▍ | 35/47 [00:32<00:11, 1.05it/s] 77%|███████▋ | 36/47 [00:33<00:10, 1.05it/s] 79%|███████▊ | 37/47 [00:34<00:09, 1.05it/s] 81%|████████ | 38/47 [00:35<00:08, 1.05it/s] 83%|████████▎ | 39/47 [00:36<00:07, 1.05it/s] 85%|████████▌ | 40/47 [00:37<00:06, 1.05it/s] 87%|████████▋ | 41/47 [00:38<00:05, 1.05it/s] 89%|████████▉ | 42/47 [00:39<00:04, 1.04it/s] 91%|█████████▏| 43/47 [00:40<00:03, 1.04it/s] 94%|█████████▎| 44/47 [00:41<00:02, 1.04it/s] 96%|█████████▌| 45/47 [00:42<00:01, 1.04it/s] 98%|█████████▊| 46/47 [00:42<00:00, 1.04it/s] 100%|██████████| 47/47 [00:43<00:00, 1.04it/s] 100%|██████████| 47/47 [00:43<00:00, 1.07it/s] Decoding latents in cuda:0... done in 1.76s Move latents to cpu... done in 0.02s 0: 480x640 1 face, 173.8ms Speed: 3.0ms preprocess, 173.8ms inference, 30.0ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:00<00:09, 2.11it/s] 9%|▉ | 2/22 [00:00<00:07, 2.56it/s] 14%|█▎ | 3/22 [00:01<00:06, 2.76it/s] 18%|█▊ | 4/22 [00:01<00:06, 2.80it/s] 23%|██▎ | 5/22 [00:01<00:06, 2.82it/s] 27%|██▋ | 6/22 [00:02<00:05, 2.83it/s] 32%|███▏ | 7/22 [00:02<00:05, 2.88it/s] 36%|███▋ | 8/22 [00:02<00:04, 2.93it/s] 41%|████ | 9/22 [00:03<00:04, 2.98it/s] 45%|████▌ | 10/22 [00:03<00:04, 2.98it/s] 50%|█████ | 11/22 [00:03<00:03, 3.00it/s] 55%|█████▍ | 12/22 [00:04<00:03, 2.93it/s] 59%|█████▉ | 13/22 [00:04<00:03, 2.95it/s] 64%|██████▎ | 14/22 [00:04<00:02, 2.97it/s] 68%|██████▊ | 15/22 [00:05<00:02, 3.00it/s] 73%|███████▎ | 16/22 [00:05<00:02, 2.86it/s] 77%|███████▋ | 17/22 [00:05<00:01, 2.92it/s] 82%|████████▏ | 18/22 [00:06<00:01, 2.96it/s] 86%|████████▋ | 19/22 [00:06<00:01, 2.92it/s] 91%|█████████ | 20/22 [00:06<00:00, 2.91it/s] 95%|█████████▌| 21/22 [00:07<00:00, 2.90it/s] 100%|██████████| 22/22 [00:07<00:00, 2.93it/s] 100%|██████████| 22/22 [00:07<00:00, 2.89it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s 0: 480x640 1 face, 8.0ms Speed: 2.5ms preprocess, 8.0ms inference, 1.6ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:00<00:06, 3.03it/s] 9%|▉ | 2/22 [00:00<00:06, 3.06it/s] 14%|█▎ | 3/22 [00:00<00:06, 3.01it/s] 18%|█▊ | 4/22 [00:01<00:06, 2.93it/s] 23%|██▎ | 5/22 [00:01<00:05, 2.97it/s] 27%|██▋ | 6/22 [00:02<00:05, 2.97it/s] 32%|███▏ | 7/22 [00:02<00:05, 2.96it/s] 36%|███▋ | 8/22 [00:02<00:04, 3.01it/s] 41%|████ | 9/22 [00:02<00:04, 3.03it/s] 45%|████▌ | 10/22 [00:03<00:03, 3.04it/s] 50%|█████ | 11/22 [00:03<00:03, 3.06it/s] 55%|█████▍ | 12/22 [00:04<00:03, 2.99it/s] 59%|█████▉ | 13/22 [00:04<00:03, 2.99it/s] 64%|██████▎ | 14/22 [00:04<00:02, 2.99it/s] 68%|██████▊ | 15/22 [00:05<00:02, 2.99it/s] 73%|███████▎ | 16/22 [00:05<00:02, 2.79it/s] 77%|███████▋ | 17/22 [00:05<00:01, 2.86it/s] 82%|████████▏ | 18/22 [00:06<00:01, 2.87it/s] 86%|████████▋ | 19/22 [00:06<00:01, 2.88it/s] 91%|█████████ | 20/22 [00:06<00:00, 2.94it/s] 95%|█████████▌| 21/22 [00:07<00:00, 2.96it/s] 100%|██████████| 22/22 [00:07<00:00, 2.98it/s] 100%|██████████| 22/22 [00:07<00:00, 2.96it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s 0: 480x640 1 face, 8.1ms Speed: 2.3ms preprocess, 8.1ms inference, 1.5ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:00<00:07, 2.93it/s] 9%|▉ | 2/22 [00:00<00:06, 2.99it/s] 14%|█▎ | 3/22 [00:01<00:06, 2.99it/s] 18%|█▊ | 4/22 [00:01<00:05, 3.01it/s] 23%|██▎ | 5/22 [00:01<00:05, 3.02it/s] 27%|██▋ | 6/22 [00:01<00:05, 3.03it/s] 32%|███▏ | 7/22 [00:02<00:04, 3.04it/s] 36%|███▋ | 8/22 [00:02<00:04, 3.02it/s] 41%|████ | 9/22 [00:02<00:04, 3.02it/s] 45%|████▌ | 10/22 [00:03<00:03, 3.03it/s] 50%|█████ | 11/22 [00:03<00:03, 2.99it/s] 55%|█████▍ | 12/22 [00:03<00:03, 3.00it/s] 59%|█████▉ | 13/22 [00:04<00:03, 2.88it/s] 64%|██████▎ | 14/22 [00:04<00:02, 2.91it/s] 68%|██████▊ | 15/22 [00:05<00:02, 2.94it/s] 73%|███████▎ | 16/22 [00:05<00:02, 2.95it/s] 77%|███████▋ | 17/22 [00:05<00:01, 2.94it/s] 82%|████████▏ | 18/22 [00:06<00:01, 2.97it/s] 86%|████████▋ | 19/22 [00:06<00:01, 2.91it/s] 91%|█████████ | 20/22 [00:06<00:00, 2.92it/s] 95%|█████████▌| 21/22 [00:07<00:00, 2.95it/s] 100%|██████████| 22/22 [00:07<00:00, 2.98it/s] 100%|██████████| 22/22 [00:07<00:00, 2.97it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt
Specify things to see in the output
1 warrior, detailed face, detailed gradient shadow (best quality), sci-fi futuristic, art by Adrian Ghenie, Jean Giraud
negative_prompt
Specify things to not see in the output
unaestheticXL2v10, (worst quality, low quality:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation. tattoo, watermark, text,
num_outputs
Number of output images
3
width
Output image width
1024
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
0.45
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.
3631489396
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
47
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/de69a25e933346ddab50b57cdd97ddb2/00000-3631489396.webp
https://files.tungsten.run/uploads/d72cae1d96ac43b698a5507ecff7b131/00001-3631489397.webp
https://files.tungsten.run/uploads/1ff06a41fa4a45e09b55fd2000ca975e/00002-3631489398.webp
Finished in 80.8 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1 warrior, detailed face, detailed gradient shadow (best quality), sci-fi futuristic, art by Adrian Ghenie, Jean Giraud Full negative prompt: unaestheticXL2v10, (worst quality, low quality:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation. tattoo, watermark, text, 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:00<00:42, 1.09it/s] 4%|▍ | 2/47 [00:01<00:40, 1.10it/s] 6%|▋ | 3/47 [00:02<00:39, 1.11it/s] 9%|▊ | 4/47 [00:03<00:38, 1.11it/s] 11%|█ | 5/47 [00:04<00:37, 1.11it/s] 13%|█▎ | 6/47 [00:05<00:37, 1.11it/s] 15%|█▍ | 7/47 [00:06<00:36, 1.11it/s] 17%|█▋ | 8/47 [00:07<00:35, 1.11it/s] 19%|█▉ | 9/47 [00:08<00:34, 1.11it/s] 21%|██▏ | 10/47 [00:09<00:33, 1.11it/s] 23%|██▎ | 11/47 [00:09<00:32, 1.11it/s] 26%|██▌ | 12/47 [00:10<00:31, 1.11it/s] 28%|██▊ | 13/47 [00:11<00:30, 1.10it/s] 30%|██▉ | 14/47 [00:12<00:30, 1.09it/s] 32%|███▏ | 15/47 [00:13<00:29, 1.09it/s] 34%|███▍ | 16/47 [00:14<00:28, 1.08it/s] 36%|███▌ | 17/47 [00:15<00:27, 1.08it/s] 38%|███▊ | 18/47 [00:16<00:26, 1.08it/s] 40%|████ | 19/47 [00:17<00:25, 1.08it/s] 43%|████▎ | 20/47 [00:18<00:25, 1.08it/s] 45%|████▍ | 21/47 [00:19<00:24, 1.07it/s] 47%|████▋ | 22/47 [00:20<00:23, 1.07it/s] 49%|████▉ | 23/47 [00:21<00:22, 1.07it/s] 51%|█████ | 24/47 [00:22<00:21, 1.07it/s] 53%|█████▎ | 25/47 [00:22<00:20, 1.07it/s] 55%|█████▌ | 26/47 [00:23<00:19, 1.07it/s] 57%|█████▋ | 27/47 [00:24<00:18, 1.06it/s] 60%|█████▉ | 28/47 [00:25<00:17, 1.06it/s] 62%|██████▏ | 29/47 [00:26<00:16, 1.06it/s] 64%|██████▍ | 30/47 [00:27<00:16, 1.06it/s] 66%|██████▌ | 31/47 [00:28<00:15, 1.06it/s] 68%|██████▊ | 32/47 [00:29<00:14, 1.06it/s] 70%|███████ | 33/47 [00:30<00:13, 1.06it/s] 72%|███████▏ | 34/47 [00:31<00:12, 1.05it/s] 74%|███████▍ | 35/47 [00:32<00:11, 1.05it/s] 77%|███████▋ | 36/47 [00:33<00:10, 1.05it/s] 79%|███████▊ | 37/47 [00:34<00:09, 1.05it/s] 81%|████████ | 38/47 [00:35<00:08, 1.05it/s] 83%|████████▎ | 39/47 [00:36<00:07, 1.05it/s] 85%|████████▌ | 40/47 [00:37<00:06, 1.05it/s] 87%|████████▋ | 41/47 [00:38<00:05, 1.05it/s] 89%|████████▉ | 42/47 [00:39<00:04, 1.04it/s] 91%|█████████▏| 43/47 [00:40<00:03, 1.04it/s] 94%|█████████▎| 44/47 [00:41<00:02, 1.04it/s] 96%|█████████▌| 45/47 [00:42<00:01, 1.04it/s] 98%|█████████▊| 46/47 [00:42<00:00, 1.04it/s] 100%|██████████| 47/47 [00:43<00:00, 1.04it/s] 100%|██████████| 47/47 [00:43<00:00, 1.07it/s] Decoding latents in cuda:0... done in 1.76s Move latents to cpu... done in 0.02s 0: 480x640 1 face, 173.8ms Speed: 3.0ms preprocess, 173.8ms inference, 30.0ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:00<00:09, 2.11it/s] 9%|▉ | 2/22 [00:00<00:07, 2.56it/s] 14%|█▎ | 3/22 [00:01<00:06, 2.76it/s] 18%|█▊ | 4/22 [00:01<00:06, 2.80it/s] 23%|██▎ | 5/22 [00:01<00:06, 2.82it/s] 27%|██▋ | 6/22 [00:02<00:05, 2.83it/s] 32%|███▏ | 7/22 [00:02<00:05, 2.88it/s] 36%|███▋ | 8/22 [00:02<00:04, 2.93it/s] 41%|████ | 9/22 [00:03<00:04, 2.98it/s] 45%|████▌ | 10/22 [00:03<00:04, 2.98it/s] 50%|█████ | 11/22 [00:03<00:03, 3.00it/s] 55%|█████▍ | 12/22 [00:04<00:03, 2.93it/s] 59%|█████▉ | 13/22 [00:04<00:03, 2.95it/s] 64%|██████▎ | 14/22 [00:04<00:02, 2.97it/s] 68%|██████▊ | 15/22 [00:05<00:02, 3.00it/s] 73%|███████▎ | 16/22 [00:05<00:02, 2.86it/s] 77%|███████▋ | 17/22 [00:05<00:01, 2.92it/s] 82%|████████▏ | 18/22 [00:06<00:01, 2.96it/s] 86%|████████▋ | 19/22 [00:06<00:01, 2.92it/s] 91%|█████████ | 20/22 [00:06<00:00, 2.91it/s] 95%|█████████▌| 21/22 [00:07<00:00, 2.90it/s] 100%|██████████| 22/22 [00:07<00:00, 2.93it/s] 100%|██████████| 22/22 [00:07<00:00, 2.89it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s 0: 480x640 1 face, 8.0ms Speed: 2.5ms preprocess, 8.0ms inference, 1.6ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:00<00:06, 3.03it/s] 9%|▉ | 2/22 [00:00<00:06, 3.06it/s] 14%|█▎ | 3/22 [00:00<00:06, 3.01it/s] 18%|█▊ | 4/22 [00:01<00:06, 2.93it/s] 23%|██▎ | 5/22 [00:01<00:05, 2.97it/s] 27%|██▋ | 6/22 [00:02<00:05, 2.97it/s] 32%|███▏ | 7/22 [00:02<00:05, 2.96it/s] 36%|███▋ | 8/22 [00:02<00:04, 3.01it/s] 41%|████ | 9/22 [00:02<00:04, 3.03it/s] 45%|████▌ | 10/22 [00:03<00:03, 3.04it/s] 50%|█████ | 11/22 [00:03<00:03, 3.06it/s] 55%|█████▍ | 12/22 [00:04<00:03, 2.99it/s] 59%|█████▉ | 13/22 [00:04<00:03, 2.99it/s] 64%|██████▎ | 14/22 [00:04<00:02, 2.99it/s] 68%|██████▊ | 15/22 [00:05<00:02, 2.99it/s] 73%|███████▎ | 16/22 [00:05<00:02, 2.79it/s] 77%|███████▋ | 17/22 [00:05<00:01, 2.86it/s] 82%|████████▏ | 18/22 [00:06<00:01, 2.87it/s] 86%|████████▋ | 19/22 [00:06<00:01, 2.88it/s] 91%|█████████ | 20/22 [00:06<00:00, 2.94it/s] 95%|█████████▌| 21/22 [00:07<00:00, 2.96it/s] 100%|██████████| 22/22 [00:07<00:00, 2.98it/s] 100%|██████████| 22/22 [00:07<00:00, 2.96it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s 0: 480x640 1 face, 8.1ms Speed: 2.3ms preprocess, 8.1ms inference, 1.5ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:00<00:07, 2.93it/s] 9%|▉ | 2/22 [00:00<00:06, 2.99it/s] 14%|█▎ | 3/22 [00:01<00:06, 2.99it/s] 18%|█▊ | 4/22 [00:01<00:05, 3.01it/s] 23%|██▎ | 5/22 [00:01<00:05, 3.02it/s] 27%|██▋ | 6/22 [00:01<00:05, 3.03it/s] 32%|███▏ | 7/22 [00:02<00:04, 3.04it/s] 36%|███▋ | 8/22 [00:02<00:04, 3.02it/s] 41%|████ | 9/22 [00:02<00:04, 3.02it/s] 45%|████▌ | 10/22 [00:03<00:03, 3.03it/s] 50%|█████ | 11/22 [00:03<00:03, 2.99it/s] 55%|█████▍ | 12/22 [00:03<00:03, 3.00it/s] 59%|█████▉ | 13/22 [00:04<00:03, 2.88it/s] 64%|██████▎ | 14/22 [00:04<00:02, 2.91it/s] 68%|██████▊ | 15/22 [00:05<00:02, 2.94it/s] 73%|███████▎ | 16/22 [00:05<00:02, 2.95it/s] 77%|███████▋ | 17/22 [00:05<00:01, 2.94it/s] 82%|████████▏ | 18/22 [00:06<00:01, 2.97it/s] 86%|████████▋ | 19/22 [00:06<00:01, 2.91it/s] 91%|█████████ | 20/22 [00:06<00:00, 2.92it/s] 95%|█████████▌| 21/22 [00:07<00:00, 2.95it/s] 100%|██████████| 22/22 [00:07<00:00, 2.98it/s] 100%|██████████| 22/22 [00:07<00:00, 2.97it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s Uploading outputs... Finished.