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/339e055e1a514c5eb97f0d9eaff0d766/00000-2701830442.webp
https://files.tungsten.run/uploads/1b65718f2a9f45eea772573339f6af69/00001-2701830443.webp
https://files.tungsten.run/uploads/f62b7994dbaa421ca08523987e1e3dc3/00002-2701830444.webp
https://files.tungsten.run/uploads/f2162f0a93954259a3c27a97a5906069/00003-2701830445.webp
This example was created by evevalentine2017
Finished in 82.2 seconds
Setting up the model... Processing... Full prompt: upper body, 1boy, man, fantasy setting, medieval, tunic, standing, dynamic angle, latino, stubble, realistic, HD, market, customers, (best quality, perfect face, beautiful and aesthetic:1.2, dynamic wide angle, detailed face, detailed eyes), <lora:epiCRealismHelper:1> Full negative prompt: mirrored, cloned, duplicate, ugly, deformed, signature, watermark, realisticvision-negative-embedding, text 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:01<00:36, 1.90s/it] 10%|█ | 2/20 [00:03<00:34, 1.92s/it] 15%|█▌ | 3/20 [00:05<00:32, 1.89s/it] 20%|██ | 4/20 [00:07<00:30, 1.91s/it] 25%|██▌ | 5/20 [00:09<00:27, 1.86s/it] 30%|███ | 6/20 [00:11<00:26, 1.87s/it] 35%|███▌ | 7/20 [00:13<00:24, 1.85s/it] 40%|████ | 8/20 [00:14<00:21, 1.78s/it] 45%|████▌ | 9/20 [00:16<00:19, 1.77s/it] 50%|█████ | 10/20 [00:18<00:18, 1.81s/it] 55%|█████▌ | 11/20 [00:20<00:16, 1.78s/it] 60%|██████ | 12/20 [00:21<00:13, 1.74s/it] 65%|██████▌ | 13/20 [00:23<00:12, 1.76s/it] 70%|███████ | 14/20 [00:25<00:10, 1.73s/it] 75%|███████▌ | 15/20 [00:26<00:08, 1.73s/it] 80%|████████ | 16/20 [00:29<00:07, 1.85s/it] 85%|████████▌ | 17/20 [00:30<00:05, 1.77s/it] 90%|█████████ | 18/20 [00:32<00:03, 1.72s/it] 95%|█████████▌| 19/20 [00:33<00:01, 1.50s/it] 100%|██████████| 20/20 [00:33<00:00, 1.25s/it] 100%|██████████| 20/20 [00:33<00:00, 1.70s/it] Decoding latents in cuda:0... done in 1.02s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.6ms Speed: 3.4ms preprocess, 7.6ms inference, 24.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:06, 1.79it/s] 17%|█▋ | 2/12 [00:01<00:05, 1.99it/s] 25%|██▌ | 3/12 [00:01<00:04, 2.12it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.26it/s] 42%|████▏ | 5/12 [00:02<00:03, 2.29it/s] 50%|█████ | 6/12 [00:02<00:02, 2.34it/s] 58%|█████▊ | 7/12 [00:03<00:02, 2.39it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.49it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.52it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.56it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.92it/s] 100%|██████████| 12/12 [00:04<00:00, 3.52it/s] 100%|██████████| 12/12 [00:04<00:00, 2.61it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 4 faces, 7.4ms Speed: 2.8ms preprocess, 7.4ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.41it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.31it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.39it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.46it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.40it/s] 50%|█████ | 6/12 [00:02<00:02, 2.46it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.48it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.55it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.60it/s] 83%|████████▎ | 10/12 [00:03<00:00, 2.64it/s] 92%|█████████▏| 11/12 [00:04<00:00, 3.00it/s] 100%|██████████| 12/12 [00:04<00:00, 3.61it/s] 100%|██████████| 12/12 [00:04<00:00, 2.76it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.30it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.27it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.30it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.38it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.37it/s] 50%|█████ | 6/12 [00:02<00:02, 2.43it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.45it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.47it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.53it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.56it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.90it/s] 100%|██████████| 12/12 [00:04<00:00, 3.51it/s] 100%|██████████| 12/12 [00:04<00:00, 2.69it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.41it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.29it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.38it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.44it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.41it/s] 50%|█████ | 6/12 [00:02<00:02, 2.46it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.48it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.57it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.59it/s] 83%|████████▎ | 10/12 [00:03<00:00, 2.61it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.98it/s] 100%|██████████| 12/12 [00:04<00:00, 3.60it/s] 100%|██████████| 12/12 [00:04<00:00, 2.75it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:05, 1.96it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.10it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.25it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.36it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.37it/s] 50%|█████ | 6/12 [00:02<00:02, 2.44it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.46it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.55it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.61it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.64it/s] 92%|█████████▏| 11/12 [00:04<00:00, 3.00it/s] 100%|██████████| 12/12 [00:04<00:00, 3.62it/s] 100%|██████████| 12/12 [00:04<00:00, 2.71it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 2.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.38it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.29it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.36it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.43it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.41it/s] 50%|█████ | 6/12 [00:02<00:02, 2.43it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.43it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.53it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.59it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.62it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.99it/s] 100%|██████████| 12/12 [00:04<00:00, 3.60it/s] 100%|██████████| 12/12 [00:04<00:00, 2.74it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.41it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.29it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.34it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.41it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.38it/s] 50%|█████ | 6/12 [00:02<00:02, 2.42it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.44it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.50it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.53it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.57it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.89it/s] 100%|██████████| 12/12 [00:04<00:00, 3.50it/s] 100%|██████████| 12/12 [00:04<00:00, 2.70it/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
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/339e055e1a514c5eb97f0d9eaff0d766/00000-2701830442.webp
https://files.tungsten.run/uploads/1b65718f2a9f45eea772573339f6af69/00001-2701830443.webp
https://files.tungsten.run/uploads/f62b7994dbaa421ca08523987e1e3dc3/00002-2701830444.webp
https://files.tungsten.run/uploads/f2162f0a93954259a3c27a97a5906069/00003-2701830445.webp
This example was created by evevalentine2017
Finished in 82.2 seconds
Setting up the model... Processing... Full prompt: upper body, 1boy, man, fantasy setting, medieval, tunic, standing, dynamic angle, latino, stubble, realistic, HD, market, customers, (best quality, perfect face, beautiful and aesthetic:1.2, dynamic wide angle, detailed face, detailed eyes), <lora:epiCRealismHelper:1> Full negative prompt: mirrored, cloned, duplicate, ugly, deformed, signature, watermark, realisticvision-negative-embedding, text 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:01<00:36, 1.90s/it] 10%|█ | 2/20 [00:03<00:34, 1.92s/it] 15%|█▌ | 3/20 [00:05<00:32, 1.89s/it] 20%|██ | 4/20 [00:07<00:30, 1.91s/it] 25%|██▌ | 5/20 [00:09<00:27, 1.86s/it] 30%|███ | 6/20 [00:11<00:26, 1.87s/it] 35%|███▌ | 7/20 [00:13<00:24, 1.85s/it] 40%|████ | 8/20 [00:14<00:21, 1.78s/it] 45%|████▌ | 9/20 [00:16<00:19, 1.77s/it] 50%|█████ | 10/20 [00:18<00:18, 1.81s/it] 55%|█████▌ | 11/20 [00:20<00:16, 1.78s/it] 60%|██████ | 12/20 [00:21<00:13, 1.74s/it] 65%|██████▌ | 13/20 [00:23<00:12, 1.76s/it] 70%|███████ | 14/20 [00:25<00:10, 1.73s/it] 75%|███████▌ | 15/20 [00:26<00:08, 1.73s/it] 80%|████████ | 16/20 [00:29<00:07, 1.85s/it] 85%|████████▌ | 17/20 [00:30<00:05, 1.77s/it] 90%|█████████ | 18/20 [00:32<00:03, 1.72s/it] 95%|█████████▌| 19/20 [00:33<00:01, 1.50s/it] 100%|██████████| 20/20 [00:33<00:00, 1.25s/it] 100%|██████████| 20/20 [00:33<00:00, 1.70s/it] Decoding latents in cuda:0... done in 1.02s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.6ms Speed: 3.4ms preprocess, 7.6ms inference, 24.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:06, 1.79it/s] 17%|█▋ | 2/12 [00:01<00:05, 1.99it/s] 25%|██▌ | 3/12 [00:01<00:04, 2.12it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.26it/s] 42%|████▏ | 5/12 [00:02<00:03, 2.29it/s] 50%|█████ | 6/12 [00:02<00:02, 2.34it/s] 58%|█████▊ | 7/12 [00:03<00:02, 2.39it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.49it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.52it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.56it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.92it/s] 100%|██████████| 12/12 [00:04<00:00, 3.52it/s] 100%|██████████| 12/12 [00:04<00:00, 2.61it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 4 faces, 7.4ms Speed: 2.8ms preprocess, 7.4ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.41it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.31it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.39it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.46it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.40it/s] 50%|█████ | 6/12 [00:02<00:02, 2.46it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.48it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.55it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.60it/s] 83%|████████▎ | 10/12 [00:03<00:00, 2.64it/s] 92%|█████████▏| 11/12 [00:04<00:00, 3.00it/s] 100%|██████████| 12/12 [00:04<00:00, 3.61it/s] 100%|██████████| 12/12 [00:04<00:00, 2.76it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.30it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.27it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.30it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.38it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.37it/s] 50%|█████ | 6/12 [00:02<00:02, 2.43it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.45it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.47it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.53it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.56it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.90it/s] 100%|██████████| 12/12 [00:04<00:00, 3.51it/s] 100%|██████████| 12/12 [00:04<00:00, 2.69it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.41it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.29it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.38it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.44it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.41it/s] 50%|█████ | 6/12 [00:02<00:02, 2.46it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.48it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.57it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.59it/s] 83%|████████▎ | 10/12 [00:03<00:00, 2.61it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.98it/s] 100%|██████████| 12/12 [00:04<00:00, 3.60it/s] 100%|██████████| 12/12 [00:04<00:00, 2.75it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:05, 1.96it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.10it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.25it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.36it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.37it/s] 50%|█████ | 6/12 [00:02<00:02, 2.44it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.46it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.55it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.61it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.64it/s] 92%|█████████▏| 11/12 [00:04<00:00, 3.00it/s] 100%|██████████| 12/12 [00:04<00:00, 3.62it/s] 100%|██████████| 12/12 [00:04<00:00, 2.71it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 2.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.38it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.29it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.36it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.43it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.41it/s] 50%|█████ | 6/12 [00:02<00:02, 2.43it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.43it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.53it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.59it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.62it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.99it/s] 100%|██████████| 12/12 [00:04<00:00, 3.60it/s] 100%|██████████| 12/12 [00:04<00:00, 2.74it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/12 [00:00<?, ?it/s] 8%|▊ | 1/12 [00:00<00:04, 2.41it/s] 17%|█▋ | 2/12 [00:00<00:04, 2.29it/s] 25%|██▌ | 3/12 [00:01<00:03, 2.34it/s] 33%|███▎ | 4/12 [00:01<00:03, 2.41it/s] 42%|████▏ | 5/12 [00:02<00:02, 2.38it/s] 50%|█████ | 6/12 [00:02<00:02, 2.42it/s] 58%|█████▊ | 7/12 [00:02<00:02, 2.44it/s] 67%|██████▋ | 8/12 [00:03<00:01, 2.50it/s] 75%|███████▌ | 9/12 [00:03<00:01, 2.53it/s] 83%|████████▎ | 10/12 [00:04<00:00, 2.57it/s] 92%|█████████▏| 11/12 [00:04<00:00, 2.89it/s] 100%|██████████| 12/12 [00:04<00:00, 3.50it/s] 100%|██████████| 12/12 [00:04<00:00, 2.70it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s Uploading outputs... Finished.