Version: v3.0
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/c0f97497fe1b4e5ab5fe74e945be248c/00000-769797013.webp
https://files.tungsten.run/uploads/df1f0d6f17214a1d9c496c0641d847a7/00001-769797014.webp
https://files.tungsten.run/uploads/fd3c965d32ed417286d378cc1276d4f6/00002-769797015.webp
https://files.tungsten.run/uploads/0c7c3798b050494990e1ed2951fcdc94/00003-769797016.webp
This example was created by evevalentine2017
Finished in 49.4 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/clearvae_v2.3_fp16.safetensors Full prompt: Fairy in forest, Claude Monet's impressionist style, soft light dappling through leaves, dreamy watercolor texture, flowing diaphanous gown, serene expression, water lilies nearby, gentle forest stream, palette of pastel colors, blurred background with impressionistic foliage, subtle reflections in water, light breezes stirring leaves, delicate and graceful, serenity of nature, impression of tranquility and peace, (best quality, 4k, 8k, highres, masterpiece: 1.2), ultra-detailed, HDR, UHD, studio lighting, sharp focus, physically-based rendering, extreme detail description, professional, vivid colors, bokeh, <lora:FaceBeauty_qinglong_V3:1.5>, <lora:more_details:0.9>, <lora:add_detail:0.1> Full negative prompt: (worst quality: 2), (low quality: 2), (normal quality: 2), lowres, bad anatomy, nsfw, EasyNegativeV2, ng_deepnegative_v1_75t, (worst quality:2), (low quality:2), (normal quality:2), lowres,bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)), ((watermark)), 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:37, 1.30s/it] 7%|▋ | 2/30 [00:01<00:25, 1.11it/s] 10%|█ | 3/30 [00:02<00:20, 1.30it/s] 13%|█▎ | 4/30 [00:03<00:18, 1.40it/s] 17%|█▋ | 5/30 [00:03<00:16, 1.47it/s] 20%|██ | 6/30 [00:04<00:15, 1.52it/s] 23%|██▎ | 7/30 [00:05<00:14, 1.55it/s] 27%|██▋ | 8/30 [00:05<00:14, 1.56it/s] 30%|███ | 9/30 [00:06<00:13, 1.57it/s] 33%|███▎ | 10/30 [00:06<00:12, 1.59it/s] 37%|███▋ | 11/30 [00:07<00:11, 1.60it/s] 40%|████ | 12/30 [00:08<00:11, 1.60it/s] 43%|████▎ | 13/30 [00:08<00:10, 1.60it/s] 47%|████▋ | 14/30 [00:09<00:10, 1.60it/s] 50%|█████ | 15/30 [00:10<00:09, 1.60it/s] 53%|█████▎ | 16/30 [00:10<00:08, 1.60it/s] 57%|█████▋ | 17/30 [00:11<00:08, 1.60it/s] 60%|██████ | 18/30 [00:11<00:07, 1.60it/s] 63%|██████▎ | 19/30 [00:12<00:06, 1.60it/s] 67%|██████▋ | 20/30 [00:13<00:06, 1.60it/s] 70%|███████ | 21/30 [00:13<00:05, 1.60it/s] 73%|███████▎ | 22/30 [00:14<00:04, 1.60it/s] 77%|███████▋ | 23/30 [00:14<00:04, 1.61it/s] 80%|████████ | 24/30 [00:15<00:03, 1.60it/s] 83%|████████▎ | 25/30 [00:16<00:03, 1.60it/s] 87%|████████▋ | 26/30 [00:16<00:02, 1.60it/s] 90%|█████████ | 27/30 [00:17<00:01, 1.60it/s] 93%|█████████▎| 28/30 [00:18<00:01, 1.60it/s] 97%|█████████▋| 29/30 [00:18<00:00, 1.60it/s] 100%|██████████| 30/30 [00:19<00:00, 1.60it/s] 100%|██████████| 30/30 [00:19<00:00, 1.55it/s] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.1ms Speed: 3.3ms preprocess, 8.1ms inference, 32.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:06, 2.29it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.20it/s] 18%|█▊ | 3/17 [00:00<00:03, 3.67it/s] 24%|██▎ | 4/17 [00:01<00:03, 4.02it/s] 29%|██▉ | 5/17 [00:01<00:02, 4.22it/s] 35%|███▌ | 6/17 [00:01<00:02, 4.32it/s] 41%|████ | 7/17 [00:01<00:02, 4.45it/s] 47%|████▋ | 8/17 [00:01<00:02, 4.44it/s] 53%|█████▎ | 9/17 [00:02<00:01, 4.51it/s] 59%|█████▉ | 10/17 [00:02<00:01, 4.55it/s] 65%|██████▍ | 11/17 [00:02<00:01, 4.62it/s] 71%|███████ | 12/17 [00:02<00:01, 4.63it/s] 76%|███████▋ | 13/17 [00:03<00:00, 4.67it/s] 82%|████████▏ | 14/17 [00:03<00:00, 4.74it/s] 88%|████████▊ | 15/17 [00:03<00:00, 4.77it/s] 94%|█████████▍| 16/17 [00:03<00:00, 4.72it/s] 100%|██████████| 17/17 [00:03<00:00, 4.75it/s] 100%|██████████| 17/17 [00:03<00:00, 4.39it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.01s 0: 640x640 1 face, 7.1ms Speed: 2.7ms preprocess, 7.1ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:03, 4.93it/s] 12%|█▏ | 2/17 [00:00<00:02, 5.00it/s] 18%|█▊ | 3/17 [00:00<00:02, 4.95it/s] 24%|██▎ | 4/17 [00:00<00:02, 4.88it/s] 29%|██▉ | 5/17 [00:01<00:02, 4.76it/s] 35%|███▌ | 6/17 [00:01<00:02, 4.72it/s] 41%|████ | 7/17 [00:01<00:02, 4.78it/s] 47%|████▋ | 8/17 [00:01<00:01, 4.71it/s] 53%|█████▎ | 9/17 [00:01<00:01, 4.77it/s] 59%|█████▉ | 10/17 [00:02<00:01, 4.83it/s] 65%|██████▍ | 11/17 [00:02<00:01, 4.85it/s] 71%|███████ | 12/17 [00:02<00:01, 4.81it/s] 76%|███████▋ | 13/17 [00:02<00:00, 4.73it/s] 82%|████████▏ | 14/17 [00:02<00:00, 4.71it/s] 88%|████████▊ | 15/17 [00:03<00:00, 4.67it/s] 94%|█████████▍| 16/17 [00:03<00:00, 4.76it/s] 100%|██████████| 17/17 [00:03<00:00, 4.81it/s] 100%|██████████| 17/17 [00:03<00:00, 4.79it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 8.1ms Speed: 2.9ms preprocess, 8.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:03, 5.09it/s] 12%|█▏ | 2/17 [00:00<00:02, 5.07it/s] 18%|█▊ | 3/17 [00:00<00:02, 4.96it/s] 24%|██▎ | 4/17 [00:00<00:02, 4.93it/s] 29%|██▉ | 5/17 [00:01<00:02, 4.90it/s] 35%|███▌ | 6/17 [00:01<00:02, 4.87it/s] 41%|████ | 7/17 [00:01<00:02, 4.86it/s] 47%|████▋ | 8/17 [00:01<00:01, 4.79it/s] 53%|█████▎ | 9/17 [00:01<00:01, 4.84it/s] 59%|█████▉ | 10/17 [00:02<00:01, 4.81it/s] 65%|██████▍ | 11/17 [00:02<00:01, 4.76it/s] 71%|███████ | 12/17 [00:02<00:01, 4.66it/s] 76%|███████▋ | 13/17 [00:02<00:00, 4.73it/s] 82%|████████▏ | 14/17 [00:02<00:00, 4.78it/s] 88%|████████▊ | 15/17 [00:03<00:00, 4.76it/s] 94%|█████████▍| 16/17 [00:03<00:00, 4.82it/s] 100%|██████████| 17/17 [00:03<00:00, 4.88it/s] 100%|██████████| 17/17 [00:03<00:00, 4.84it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 8.4ms Speed: 2.8ms preprocess, 8.4ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:03, 4.46it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.63it/s] 18%|█▊ | 3/17 [00:00<00:03, 3.91it/s] 24%|██▎ | 4/17 [00:00<00:03, 4.09it/s] 29%|██▉ | 5/17 [00:01<00:02, 4.29it/s] 35%|███▌ | 6/17 [00:01<00:02, 4.53it/s] 41%|████ | 7/17 [00:01<00:02, 4.69it/s] 47%|████▋ | 8/17 [00:01<00:01, 4.81it/s] 53%|█████▎ | 9/17 [00:01<00:01, 4.89it/s] 59%|█████▉ | 10/17 [00:02<00:01, 4.94it/s] 65%|██████▍ | 11/17 [00:02<00:01, 4.96it/s] 71%|███████ | 12/17 [00:02<00:01, 4.97it/s] 76%|███████▋ | 13/17 [00:02<00:00, 4.93it/s] 82%|████████▏ | 14/17 [00:03<00:00, 4.94it/s] 88%|████████▊ | 15/17 [00:03<00:00, 4.94it/s] 94%|█████████▍| 16/17 [00:03<00:00, 4.89it/s] 100%|██████████| 17/17 [00:03<00:00, 4.92it/s] 100%|██████████| 17/17 [00:03<00:00, 4.70it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 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/c0f97497fe1b4e5ab5fe74e945be248c/00000-769797013.webp
https://files.tungsten.run/uploads/df1f0d6f17214a1d9c496c0641d847a7/00001-769797014.webp
https://files.tungsten.run/uploads/fd3c965d32ed417286d378cc1276d4f6/00002-769797015.webp
https://files.tungsten.run/uploads/0c7c3798b050494990e1ed2951fcdc94/00003-769797016.webp
This example was created by evevalentine2017
Finished in 49.4 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/clearvae_v2.3_fp16.safetensors Full prompt: Fairy in forest, Claude Monet's impressionist style, soft light dappling through leaves, dreamy watercolor texture, flowing diaphanous gown, serene expression, water lilies nearby, gentle forest stream, palette of pastel colors, blurred background with impressionistic foliage, subtle reflections in water, light breezes stirring leaves, delicate and graceful, serenity of nature, impression of tranquility and peace, (best quality, 4k, 8k, highres, masterpiece: 1.2), ultra-detailed, HDR, UHD, studio lighting, sharp focus, physically-based rendering, extreme detail description, professional, vivid colors, bokeh, <lora:FaceBeauty_qinglong_V3:1.5>, <lora:more_details:0.9>, <lora:add_detail:0.1> Full negative prompt: (worst quality: 2), (low quality: 2), (normal quality: 2), lowres, bad anatomy, nsfw, EasyNegativeV2, ng_deepnegative_v1_75t, (worst quality:2), (low quality:2), (normal quality:2), lowres,bad anatomy, bad hands, normal quality, ((monochrome)), ((grayscale)), ((watermark)), 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:37, 1.30s/it] 7%|▋ | 2/30 [00:01<00:25, 1.11it/s] 10%|█ | 3/30 [00:02<00:20, 1.30it/s] 13%|█▎ | 4/30 [00:03<00:18, 1.40it/s] 17%|█▋ | 5/30 [00:03<00:16, 1.47it/s] 20%|██ | 6/30 [00:04<00:15, 1.52it/s] 23%|██▎ | 7/30 [00:05<00:14, 1.55it/s] 27%|██▋ | 8/30 [00:05<00:14, 1.56it/s] 30%|███ | 9/30 [00:06<00:13, 1.57it/s] 33%|███▎ | 10/30 [00:06<00:12, 1.59it/s] 37%|███▋ | 11/30 [00:07<00:11, 1.60it/s] 40%|████ | 12/30 [00:08<00:11, 1.60it/s] 43%|████▎ | 13/30 [00:08<00:10, 1.60it/s] 47%|████▋ | 14/30 [00:09<00:10, 1.60it/s] 50%|█████ | 15/30 [00:10<00:09, 1.60it/s] 53%|█████▎ | 16/30 [00:10<00:08, 1.60it/s] 57%|█████▋ | 17/30 [00:11<00:08, 1.60it/s] 60%|██████ | 18/30 [00:11<00:07, 1.60it/s] 63%|██████▎ | 19/30 [00:12<00:06, 1.60it/s] 67%|██████▋ | 20/30 [00:13<00:06, 1.60it/s] 70%|███████ | 21/30 [00:13<00:05, 1.60it/s] 73%|███████▎ | 22/30 [00:14<00:04, 1.60it/s] 77%|███████▋ | 23/30 [00:14<00:04, 1.61it/s] 80%|████████ | 24/30 [00:15<00:03, 1.60it/s] 83%|████████▎ | 25/30 [00:16<00:03, 1.60it/s] 87%|████████▋ | 26/30 [00:16<00:02, 1.60it/s] 90%|█████████ | 27/30 [00:17<00:01, 1.60it/s] 93%|█████████▎| 28/30 [00:18<00:01, 1.60it/s] 97%|█████████▋| 29/30 [00:18<00:00, 1.60it/s] 100%|██████████| 30/30 [00:19<00:00, 1.60it/s] 100%|██████████| 30/30 [00:19<00:00, 1.55it/s] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.1ms Speed: 3.3ms preprocess, 8.1ms inference, 32.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:06, 2.29it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.20it/s] 18%|█▊ | 3/17 [00:00<00:03, 3.67it/s] 24%|██▎ | 4/17 [00:01<00:03, 4.02it/s] 29%|██▉ | 5/17 [00:01<00:02, 4.22it/s] 35%|███▌ | 6/17 [00:01<00:02, 4.32it/s] 41%|████ | 7/17 [00:01<00:02, 4.45it/s] 47%|████▋ | 8/17 [00:01<00:02, 4.44it/s] 53%|█████▎ | 9/17 [00:02<00:01, 4.51it/s] 59%|█████▉ | 10/17 [00:02<00:01, 4.55it/s] 65%|██████▍ | 11/17 [00:02<00:01, 4.62it/s] 71%|███████ | 12/17 [00:02<00:01, 4.63it/s] 76%|███████▋ | 13/17 [00:03<00:00, 4.67it/s] 82%|████████▏ | 14/17 [00:03<00:00, 4.74it/s] 88%|████████▊ | 15/17 [00:03<00:00, 4.77it/s] 94%|█████████▍| 16/17 [00:03<00:00, 4.72it/s] 100%|██████████| 17/17 [00:03<00:00, 4.75it/s] 100%|██████████| 17/17 [00:03<00:00, 4.39it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.01s 0: 640x640 1 face, 7.1ms Speed: 2.7ms preprocess, 7.1ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:03, 4.93it/s] 12%|█▏ | 2/17 [00:00<00:02, 5.00it/s] 18%|█▊ | 3/17 [00:00<00:02, 4.95it/s] 24%|██▎ | 4/17 [00:00<00:02, 4.88it/s] 29%|██▉ | 5/17 [00:01<00:02, 4.76it/s] 35%|███▌ | 6/17 [00:01<00:02, 4.72it/s] 41%|████ | 7/17 [00:01<00:02, 4.78it/s] 47%|████▋ | 8/17 [00:01<00:01, 4.71it/s] 53%|█████▎ | 9/17 [00:01<00:01, 4.77it/s] 59%|█████▉ | 10/17 [00:02<00:01, 4.83it/s] 65%|██████▍ | 11/17 [00:02<00:01, 4.85it/s] 71%|███████ | 12/17 [00:02<00:01, 4.81it/s] 76%|███████▋ | 13/17 [00:02<00:00, 4.73it/s] 82%|████████▏ | 14/17 [00:02<00:00, 4.71it/s] 88%|████████▊ | 15/17 [00:03<00:00, 4.67it/s] 94%|█████████▍| 16/17 [00:03<00:00, 4.76it/s] 100%|██████████| 17/17 [00:03<00:00, 4.81it/s] 100%|██████████| 17/17 [00:03<00:00, 4.79it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 8.1ms Speed: 2.9ms preprocess, 8.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:03, 5.09it/s] 12%|█▏ | 2/17 [00:00<00:02, 5.07it/s] 18%|█▊ | 3/17 [00:00<00:02, 4.96it/s] 24%|██▎ | 4/17 [00:00<00:02, 4.93it/s] 29%|██▉ | 5/17 [00:01<00:02, 4.90it/s] 35%|███▌ | 6/17 [00:01<00:02, 4.87it/s] 41%|████ | 7/17 [00:01<00:02, 4.86it/s] 47%|████▋ | 8/17 [00:01<00:01, 4.79it/s] 53%|█████▎ | 9/17 [00:01<00:01, 4.84it/s] 59%|█████▉ | 10/17 [00:02<00:01, 4.81it/s] 65%|██████▍ | 11/17 [00:02<00:01, 4.76it/s] 71%|███████ | 12/17 [00:02<00:01, 4.66it/s] 76%|███████▋ | 13/17 [00:02<00:00, 4.73it/s] 82%|████████▏ | 14/17 [00:02<00:00, 4.78it/s] 88%|████████▊ | 15/17 [00:03<00:00, 4.76it/s] 94%|█████████▍| 16/17 [00:03<00:00, 4.82it/s] 100%|██████████| 17/17 [00:03<00:00, 4.88it/s] 100%|██████████| 17/17 [00:03<00:00, 4.84it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 8.4ms Speed: 2.8ms preprocess, 8.4ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:03, 4.46it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.63it/s] 18%|█▊ | 3/17 [00:00<00:03, 3.91it/s] 24%|██▎ | 4/17 [00:00<00:03, 4.09it/s] 29%|██▉ | 5/17 [00:01<00:02, 4.29it/s] 35%|███▌ | 6/17 [00:01<00:02, 4.53it/s] 41%|████ | 7/17 [00:01<00:02, 4.69it/s] 47%|████▋ | 8/17 [00:01<00:01, 4.81it/s] 53%|█████▎ | 9/17 [00:01<00:01, 4.89it/s] 59%|█████▉ | 10/17 [00:02<00:01, 4.94it/s] 65%|██████▍ | 11/17 [00:02<00:01, 4.96it/s] 71%|███████ | 12/17 [00:02<00:01, 4.97it/s] 76%|███████▋ | 13/17 [00:02<00:00, 4.93it/s] 82%|████████▏ | 14/17 [00:03<00:00, 4.94it/s] 88%|████████▊ | 15/17 [00:03<00:00, 4.94it/s] 94%|█████████▍| 16/17 [00:03<00:00, 4.89it/s] 100%|██████████| 17/17 [00:03<00:00, 4.92it/s] 100%|██████████| 17/17 [00:03<00:00, 4.70it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s Finished.