tungsten-logo
Sign In
astreapixie-mix
astreapixie-mix

astreapixie-mix

4 stars
Version: v1.6
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/7e610e6dcaac4487a825df6b5c4c27f8/00000-13562001.webp
https://files.tungsten.run/uploads/b8d13dd8e4304ac9b7f39e76e24c1dbf/00001-13562002.webp
https://files.tungsten.run/uploads/27e92b2e10a54af2854a775f2e8f5864/00002-13562003.webp
https://files.tungsten.run/uploads/420b11db54ed465fb3dbaeadf01c1d8e/00003-13562004.webp
This example was created by evevalentine2017
Finished in 165.0 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: 1girl, ((cinematic light)), colorful, hyper detail, dramatic light, intricate details, best quality, (wallpaper, masterpiece, best quality, ultra-detailed, best shadow), (detailed background:1.4), (beautiful detailed face, beautiful detailed eyes), high contrast, (best illumination, an extremely delicate and beautiful),(girl:1.5), spink hair, small breasts, (wide hips:1.2), standing, smile, school uniform, blue miniskirt, hands at sides, looking at viewer, outside, near tree, arms behind back, (road:0.6), pov, looking at viewer, facing viewer, perfect eyes, blue eyes, ((caustic)), dynamic angle, beautiful detailed glow, full body, cowboy shot, volumetric light, <lora:epiCRealismHelper:1> Full negative prompt: fcNeg-neg, (worst quality:1.6, low quality:1.6), (zombie, sketch, interlocked fingers, comic) 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:35, 3.28s/it] 7%|▋ | 2/30 [00:06<01:35, 3.42s/it] 10%|█ | 3/30 [00:10<01:33, 3.46s/it] 13%|█▎ | 4/30 [00:13<01:30, 3.49s/it] 17%|█▋ | 5/30 [00:17<01:29, 3.57s/it] 20%|██ | 6/30 [00:21<01:25, 3.55s/it] 23%|██▎ | 7/30 [00:23<01:15, 3.30s/it] 27%|██▋ | 8/30 [00:27<01:15, 3.42s/it] 30%|███ | 9/30 [00:31<01:12, 3.45s/it] 33%|███▎ | 10/30 [00:33<01:03, 3.18s/it] 37%|███▋ | 11/30 [00:37<01:02, 3.29s/it] 40%|████ | 12/30 [00:40<00:58, 3.28s/it] 43%|████▎ | 13/30 [00:43<00:56, 3.32s/it] 47%|████▋ | 14/30 [00:47<00:55, 3.44s/it] 50%|█████ | 15/30 [00:50<00:49, 3.30s/it] 53%|█████▎ | 16/30 [00:53<00:46, 3.31s/it] 57%|█████▋ | 17/30 [00:57<00:43, 3.33s/it] 60%|██████ | 18/30 [01:00<00:40, 3.38s/it] 63%|██████▎ | 19/30 [01:03<00:34, 3.17s/it] 67%|██████▋ | 20/30 [01:05<00:28, 2.88s/it] 70%|███████ | 21/30 [01:08<00:27, 3.00s/it] 73%|███████▎ | 22/30 [01:12<00:24, 3.11s/it] 77%|███████▋ | 23/30 [01:14<00:20, 2.92s/it] 80%|████████ | 24/30 [01:17<00:17, 2.99s/it] 83%|████████▎ | 25/30 [01:20<00:14, 2.95s/it] 87%|████████▋ | 26/30 [01:23<00:11, 2.99s/it] 90%|█████████ | 27/30 [01:27<00:09, 3.07s/it] 93%|█████████▎| 28/30 [01:30<00:06, 3.14s/it] 97%|█████████▋| 29/30 [01:32<00:02, 2.89s/it] 100%|██████████| 30/30 [01:33<00:00, 2.21s/it] 100%|██████████| 30/30 [01:33<00:00, 3.11s/it] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.1ms Speed: 3.7ms preprocess, 8.1ms inference, 25.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:01<00:20, 1.26s/it] 12%|█▏ | 2/17 [00:02<00:15, 1.03s/it] 18%|█▊ | 3/17 [00:03<00:13, 1.01it/s] 24%|██▎ | 4/17 [00:04<00:12, 1.01it/s] 29%|██▉ | 5/17 [00:05<00:11, 1.01it/s] 35%|███▌ | 6/17 [00:05<00:10, 1.08it/s] 41%|████ | 7/17 [00:06<00:08, 1.20it/s] 47%|████▋ | 8/17 [00:07<00:07, 1.16it/s] 53%|█████▎ | 9/17 [00:08<00:07, 1.11it/s] 59%|█████▉ | 10/17 [00:09<00:05, 1.18it/s] 65%|██████▍ | 11/17 [00:10<00:05, 1.16it/s] 71%|███████ | 12/17 [00:10<00:04, 1.18it/s] 76%|███████▋ | 13/17 [00:11<00:03, 1.16it/s] 82%|████████▏ | 14/17 [00:12<00:02, 1.12it/s] 88%|████████▊ | 15/17 [00:13<00:01, 1.10it/s] 94%|█████████▍| 16/17 [00:14<00:00, 1.19it/s] 100%|██████████| 17/17 [00:14<00:00, 1.54it/s] 100%|██████████| 17/17 [00:14<00:00, 1.17it/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: 3.4ms preprocess, 8.1ms inference, 2.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:01<00:16, 1.01s/it] 12%|█▏ | 2/17 [00:01<00:13, 1.10it/s] 18%|█▊ | 3/17 [00:02<00:12, 1.11it/s] 24%|██▎ | 4/17 [00:03<00:11, 1.11it/s] 29%|██▉ | 5/17 [00:04<00:10, 1.09it/s] 35%|███▌ | 6/17 [00:05<00:09, 1.16it/s] 41%|████ | 7/17 [00:05<00:07, 1.27it/s] 47%|████▋ | 8/17 [00:06<00:07, 1.21it/s] 53%|█████▎ | 9/17 [00:07<00:06, 1.16it/s] 59%|█████▉ | 10/17 [00:08<00:05, 1.23it/s] 65%|██████▍ | 11/17 [00:09<00:04, 1.21it/s] 71%|███████ | 12/17 [00:10<00:04, 1.22it/s] 76%|███████▋ | 13/17 [00:11<00:03, 1.21it/s] 82%|████████▏ | 14/17 [00:11<00:02, 1.20it/s] 88%|████████▊ | 15/17 [00:12<00:01, 1.17it/s] 94%|█████████▍| 16/17 [00:13<00:00, 1.25it/s] 100%|██████████| 17/17 [00:13<00:00, 1.62it/s] 100%|██████████| 17/17 [00:13<00:00, 1.25it/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: 3.1ms preprocess, 7.5ms inference, 2.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:01<00:16, 1.02s/it] 12%|█▏ | 2/17 [00:01<00:13, 1.09it/s] 18%|█▊ | 3/17 [00:02<00:12, 1.10it/s] 24%|██▎ | 4/17 [00:03<00:12, 1.08it/s] 29%|██▉ | 5/17 [00:04<00:11, 1.05it/s] 35%|███▌ | 6/17 [00:05<00:09, 1.12it/s] 41%|████ | 7/17 [00:06<00:08, 1.23it/s] 47%|████▋ | 8/17 [00:07<00:07, 1.18it/s] 53%|█████▎ | 9/17 [00:07<00:06, 1.15it/s] 59%|█████▉ | 10/17 [00:08<00:05, 1.21it/s] 65%|██████▍ | 11/17 [00:09<00:05, 1.18it/s] 71%|███████ | 12/17 [00:10<00:04, 1.19it/s] 76%|███████▋ | 13/17 [00:11<00:03, 1.18it/s] 82%|████████▏ | 14/17 [00:12<00:02, 1.16it/s] 88%|████████▊ | 15/17 [00:13<00:01, 1.14it/s] 94%|█████████▍| 16/17 [00:13<00:00, 1.23it/s] 100%|██████████| 17/17 [00:13<00:00, 1.59it/s] 100%|██████████| 17/17 [00:13<00:00, 1.22it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.6ms Speed: 3.2ms preprocess, 7.6ms inference, 2.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:01<00:16, 1.00s/it] 12%|█▏ | 2/17 [00:01<00:13, 1.09it/s] 18%|█▊ | 3/17 [00:02<00:12, 1.09it/s] 24%|██▎ | 4/17 [00:03<00:12, 1.08it/s] 29%|██▉ | 5/17 [00:04<00:11, 1.05it/s] 35%|███▌ | 6/17 [00:05<00:09, 1.13it/s] 41%|████ | 7/17 [00:06<00:08, 1.24it/s] 47%|████▋ | 8/17 [00:07<00:07, 1.20it/s] 53%|█████▎ | 9/17 [00:07<00:06, 1.14it/s] 59%|█████▉ | 10/17 [00:08<00:05, 1.21it/s] 65%|██████▍ | 11/17 [00:09<00:05, 1.19it/s] 71%|███████ | 12/17 [00:10<00:04, 1.20it/s] 76%|███████▋ | 13/17 [00:11<00:03, 1.18it/s] 82%|████████▏ | 14/17 [00:12<00:02, 1.16it/s] 88%|████████▊ | 15/17 [00:13<00:01, 1.13it/s] 94%|█████████▍| 16/17 [00:13<00:00, 1.22it/s] 100%|██████████| 17/17 [00:13<00:00, 1.57it/s] 100%|██████████| 17/17 [00:13<00:00, 1.22it/s] Decoding latents in cuda:0... done in 0.23s 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/7e610e6dcaac4487a825df6b5c4c27f8/00000-13562001.webp
https://files.tungsten.run/uploads/b8d13dd8e4304ac9b7f39e76e24c1dbf/00001-13562002.webp
https://files.tungsten.run/uploads/27e92b2e10a54af2854a775f2e8f5864/00002-13562003.webp
https://files.tungsten.run/uploads/420b11db54ed465fb3dbaeadf01c1d8e/00003-13562004.webp
This example was created by evevalentine2017
Finished in 165.0 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: 1girl, ((cinematic light)), colorful, hyper detail, dramatic light, intricate details, best quality, (wallpaper, masterpiece, best quality, ultra-detailed, best shadow), (detailed background:1.4), (beautiful detailed face, beautiful detailed eyes), high contrast, (best illumination, an extremely delicate and beautiful),(girl:1.5), spink hair, small breasts, (wide hips:1.2), standing, smile, school uniform, blue miniskirt, hands at sides, looking at viewer, outside, near tree, arms behind back, (road:0.6), pov, looking at viewer, facing viewer, perfect eyes, blue eyes, ((caustic)), dynamic angle, beautiful detailed glow, full body, cowboy shot, volumetric light, <lora:epiCRealismHelper:1> Full negative prompt: fcNeg-neg, (worst quality:1.6, low quality:1.6), (zombie, sketch, interlocked fingers, comic) 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:35, 3.28s/it] 7%|▋ | 2/30 [00:06<01:35, 3.42s/it] 10%|█ | 3/30 [00:10<01:33, 3.46s/it] 13%|█▎ | 4/30 [00:13<01:30, 3.49s/it] 17%|█▋ | 5/30 [00:17<01:29, 3.57s/it] 20%|██ | 6/30 [00:21<01:25, 3.55s/it] 23%|██▎ | 7/30 [00:23<01:15, 3.30s/it] 27%|██▋ | 8/30 [00:27<01:15, 3.42s/it] 30%|███ | 9/30 [00:31<01:12, 3.45s/it] 33%|███▎ | 10/30 [00:33<01:03, 3.18s/it] 37%|███▋ | 11/30 [00:37<01:02, 3.29s/it] 40%|████ | 12/30 [00:40<00:58, 3.28s/it] 43%|████▎ | 13/30 [00:43<00:56, 3.32s/it] 47%|████▋ | 14/30 [00:47<00:55, 3.44s/it] 50%|█████ | 15/30 [00:50<00:49, 3.30s/it] 53%|█████▎ | 16/30 [00:53<00:46, 3.31s/it] 57%|█████▋ | 17/30 [00:57<00:43, 3.33s/it] 60%|██████ | 18/30 [01:00<00:40, 3.38s/it] 63%|██████▎ | 19/30 [01:03<00:34, 3.17s/it] 67%|██████▋ | 20/30 [01:05<00:28, 2.88s/it] 70%|███████ | 21/30 [01:08<00:27, 3.00s/it] 73%|███████▎ | 22/30 [01:12<00:24, 3.11s/it] 77%|███████▋ | 23/30 [01:14<00:20, 2.92s/it] 80%|████████ | 24/30 [01:17<00:17, 2.99s/it] 83%|████████▎ | 25/30 [01:20<00:14, 2.95s/it] 87%|████████▋ | 26/30 [01:23<00:11, 2.99s/it] 90%|█████████ | 27/30 [01:27<00:09, 3.07s/it] 93%|█████████▎| 28/30 [01:30<00:06, 3.14s/it] 97%|█████████▋| 29/30 [01:32<00:02, 2.89s/it] 100%|██████████| 30/30 [01:33<00:00, 2.21s/it] 100%|██████████| 30/30 [01:33<00:00, 3.11s/it] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.1ms Speed: 3.7ms preprocess, 8.1ms inference, 25.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:01<00:20, 1.26s/it] 12%|█▏ | 2/17 [00:02<00:15, 1.03s/it] 18%|█▊ | 3/17 [00:03<00:13, 1.01it/s] 24%|██▎ | 4/17 [00:04<00:12, 1.01it/s] 29%|██▉ | 5/17 [00:05<00:11, 1.01it/s] 35%|███▌ | 6/17 [00:05<00:10, 1.08it/s] 41%|████ | 7/17 [00:06<00:08, 1.20it/s] 47%|████▋ | 8/17 [00:07<00:07, 1.16it/s] 53%|█████▎ | 9/17 [00:08<00:07, 1.11it/s] 59%|█████▉ | 10/17 [00:09<00:05, 1.18it/s] 65%|██████▍ | 11/17 [00:10<00:05, 1.16it/s] 71%|███████ | 12/17 [00:10<00:04, 1.18it/s] 76%|███████▋ | 13/17 [00:11<00:03, 1.16it/s] 82%|████████▏ | 14/17 [00:12<00:02, 1.12it/s] 88%|████████▊ | 15/17 [00:13<00:01, 1.10it/s] 94%|█████████▍| 16/17 [00:14<00:00, 1.19it/s] 100%|██████████| 17/17 [00:14<00:00, 1.54it/s] 100%|██████████| 17/17 [00:14<00:00, 1.17it/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: 3.4ms preprocess, 8.1ms inference, 2.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:01<00:16, 1.01s/it] 12%|█▏ | 2/17 [00:01<00:13, 1.10it/s] 18%|█▊ | 3/17 [00:02<00:12, 1.11it/s] 24%|██▎ | 4/17 [00:03<00:11, 1.11it/s] 29%|██▉ | 5/17 [00:04<00:10, 1.09it/s] 35%|███▌ | 6/17 [00:05<00:09, 1.16it/s] 41%|████ | 7/17 [00:05<00:07, 1.27it/s] 47%|████▋ | 8/17 [00:06<00:07, 1.21it/s] 53%|█████▎ | 9/17 [00:07<00:06, 1.16it/s] 59%|█████▉ | 10/17 [00:08<00:05, 1.23it/s] 65%|██████▍ | 11/17 [00:09<00:04, 1.21it/s] 71%|███████ | 12/17 [00:10<00:04, 1.22it/s] 76%|███████▋ | 13/17 [00:11<00:03, 1.21it/s] 82%|████████▏ | 14/17 [00:11<00:02, 1.20it/s] 88%|████████▊ | 15/17 [00:12<00:01, 1.17it/s] 94%|█████████▍| 16/17 [00:13<00:00, 1.25it/s] 100%|██████████| 17/17 [00:13<00:00, 1.62it/s] 100%|██████████| 17/17 [00:13<00:00, 1.25it/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: 3.1ms preprocess, 7.5ms inference, 2.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:01<00:16, 1.02s/it] 12%|█▏ | 2/17 [00:01<00:13, 1.09it/s] 18%|█▊ | 3/17 [00:02<00:12, 1.10it/s] 24%|██▎ | 4/17 [00:03<00:12, 1.08it/s] 29%|██▉ | 5/17 [00:04<00:11, 1.05it/s] 35%|███▌ | 6/17 [00:05<00:09, 1.12it/s] 41%|████ | 7/17 [00:06<00:08, 1.23it/s] 47%|████▋ | 8/17 [00:07<00:07, 1.18it/s] 53%|█████▎ | 9/17 [00:07<00:06, 1.15it/s] 59%|█████▉ | 10/17 [00:08<00:05, 1.21it/s] 65%|██████▍ | 11/17 [00:09<00:05, 1.18it/s] 71%|███████ | 12/17 [00:10<00:04, 1.19it/s] 76%|███████▋ | 13/17 [00:11<00:03, 1.18it/s] 82%|████████▏ | 14/17 [00:12<00:02, 1.16it/s] 88%|████████▊ | 15/17 [00:13<00:01, 1.14it/s] 94%|█████████▍| 16/17 [00:13<00:00, 1.23it/s] 100%|██████████| 17/17 [00:13<00:00, 1.59it/s] 100%|██████████| 17/17 [00:13<00:00, 1.22it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.6ms Speed: 3.2ms preprocess, 7.6ms inference, 2.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:01<00:16, 1.00s/it] 12%|█▏ | 2/17 [00:01<00:13, 1.09it/s] 18%|█▊ | 3/17 [00:02<00:12, 1.09it/s] 24%|██▎ | 4/17 [00:03<00:12, 1.08it/s] 29%|██▉ | 5/17 [00:04<00:11, 1.05it/s] 35%|███▌ | 6/17 [00:05<00:09, 1.13it/s] 41%|████ | 7/17 [00:06<00:08, 1.24it/s] 47%|████▋ | 8/17 [00:07<00:07, 1.20it/s] 53%|█████▎ | 9/17 [00:07<00:06, 1.14it/s] 59%|█████▉ | 10/17 [00:08<00:05, 1.21it/s] 65%|██████▍ | 11/17 [00:09<00:05, 1.19it/s] 71%|███████ | 12/17 [00:10<00:04, 1.20it/s] 76%|███████▋ | 13/17 [00:11<00:03, 1.18it/s] 82%|████████▏ | 14/17 [00:12<00:02, 1.16it/s] 88%|████████▊ | 15/17 [00:13<00:01, 1.13it/s] 94%|█████████▍| 16/17 [00:13<00:00, 1.22it/s] 100%|██████████| 17/17 [00:13<00:00, 1.57it/s] 100%|██████████| 17/17 [00:13<00:00, 1.22it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s Finished.