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
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/9542a0d6224d43adbd7dd14cca9e17a2/00000-1727086093.webp
https://files.tungsten.run/uploads/45e23ffda1024cb5ad91d4ee6a8419a0/00001-1727086094.webp
https://files.tungsten.run/uploads/9a711f98eb13444ab0da32fe0d273e2d/00002-1727086095.webp
This example was created by evevalentine2017
Finished in 164.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Female bugbear, (best quality), (highly detailed), masterpiece, detailed face, beautiful face, (detailed eyes, deep eyes), (1girl:1.33, solo), full body, very long hair, earrings, (grin:0.9), walking, city, outside, cobblestone, <lora:RPGBugbearXL:1> Full negative prompt: featureless, colorless, text, watermark 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:38, 3.38s/it] 7%|▋ | 2/30 [00:06<01:24, 3.03s/it] 10%|█ | 3/30 [00:08<01:18, 2.90s/it] 13%|█▎ | 4/30 [00:11<01:15, 2.92s/it] 17%|█▋ | 5/30 [00:14<01:10, 2.84s/it] 20%|██ | 6/30 [00:17<01:07, 2.83s/it] 23%|██▎ | 7/30 [00:20<01:06, 2.89s/it] 27%|██▋ | 8/30 [00:22<01:01, 2.78s/it] 30%|███ | 9/30 [00:25<00:57, 2.72s/it] 33%|███▎ | 10/30 [00:28<00:54, 2.74s/it] 37%|███▋ | 11/30 [00:31<00:52, 2.77s/it] 40%|████ | 12/30 [00:33<00:49, 2.75s/it] 43%|████▎ | 13/30 [00:36<00:47, 2.77s/it] 47%|████▋ | 14/30 [00:39<00:44, 2.79s/it] 50%|█████ | 15/30 [00:42<00:41, 2.78s/it] 53%|█████▎ | 16/30 [00:44<00:37, 2.71s/it] 57%|█████▋ | 17/30 [00:47<00:35, 2.70s/it] 60%|██████ | 18/30 [00:50<00:31, 2.66s/it] 63%|██████▎ | 19/30 [00:52<00:28, 2.64s/it] 67%|██████▋ | 20/30 [00:55<00:26, 2.65s/it] 70%|███████ | 21/30 [00:57<00:23, 2.63s/it] 73%|███████▎ | 22/30 [01:00<00:20, 2.53s/it] 77%|███████▋ | 23/30 [01:02<00:17, 2.52s/it] 80%|████████ | 24/30 [01:05<00:14, 2.50s/it] 83%|████████▎ | 25/30 [01:07<00:12, 2.54s/it] 87%|████████▋ | 26/30 [01:10<00:09, 2.49s/it] 90%|█████████ | 27/30 [01:12<00:07, 2.46s/it] 93%|█████████▎| 28/30 [01:14<00:04, 2.40s/it] 97%|█████████▋| 29/30 [01:16<00:02, 2.10s/it] 100%|██████████| 30/30 [01:17<00:00, 1.86s/it] 100%|██████████| 30/30 [01:17<00:00, 2.58s/it] Decoding latents in cuda:0... done in 2.38s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.9ms Speed: 3.3ms preprocess, 7.9ms inference, 22.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:13, 1.00s/it] 14%|█▍ | 2/14 [00:01<00:10, 1.13it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.15it/s] 29%|██▊ | 4/14 [00:03<00:08, 1.12it/s] 36%|███▌ | 5/14 [00:04<00:07, 1.16it/s] 43%|████▎ | 6/14 [00:05<00:06, 1.24it/s] 50%|█████ | 7/14 [00:05<00:05, 1.24it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.26it/s] 64%|██████▍ | 9/14 [00:07<00:04, 1.24it/s] 71%|███████▏ | 10/14 [00:08<00:03, 1.27it/s] 79%|███████▊ | 11/14 [00:08<00:02, 1.29it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.33it/s] 93%|█████████▎| 13/14 [00:10<00:00, 1.53it/s] 100%|██████████| 14/14 [00:10<00:00, 1.75it/s] 100%|██████████| 14/14 [00:10<00:00, 1.33it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.1ms preprocess, 7.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 (no detections), 7.5ms Speed: 3.0ms preprocess, 7.5ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 1 hand, 7.1ms Speed: 3.0ms preprocess, 7.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:11, 1.11it/s] 14%|█▍ | 2/14 [00:01<00:10, 1.13it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.11it/s] 29%|██▊ | 4/14 [00:03<00:09, 1.11it/s] 36%|███▌ | 5/14 [00:04<00:08, 1.12it/s] 43%|████▎ | 6/14 [00:05<00:06, 1.19it/s] 50%|█████ | 7/14 [00:06<00:05, 1.19it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.21it/s] 64%|██████▍ | 9/14 [00:07<00:04, 1.19it/s] 71%|███████▏ | 10/14 [00:08<00:03, 1.24it/s] 79%|███████▊ | 11/14 [00:09<00:02, 1.27it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.30it/s] 93%|█████████▎| 13/14 [00:10<00:00, 1.49it/s] 100%|██████████| 14/14 [00:10<00:00, 1.71it/s] 100%|██████████| 14/14 [00:10<00:00, 1.30it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.8ms Speed: 3.2ms preprocess, 7.8ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:11, 1.13it/s] 14%|█▍ | 2/14 [00:01<00:10, 1.19it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.20it/s] 29%|██▊ | 4/14 [00:03<00:08, 1.19it/s] 36%|███▌ | 5/14 [00:04<00:07, 1.21it/s] 43%|████▎ | 6/14 [00:04<00:06, 1.27it/s] 50%|█████ | 7/14 [00:05<00:05, 1.27it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.30it/s] 64%|██████▍ | 9/14 [00:07<00:03, 1.28it/s] 71%|███████▏ | 10/14 [00:07<00:03, 1.30it/s] 79%|███████▊ | 11/14 [00:08<00:02, 1.29it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.32it/s] 93%|█████████▎| 13/14 [00:09<00:00, 1.52it/s] 100%|██████████| 14/14 [00:10<00:00, 1.73it/s] 100%|██████████| 14/14 [00:10<00:00, 1.36it/s] Decoding latents in cuda:0... done in 0.81s Move latents to cpu... done in 0.0s 0: 640x640 3 hands, 7.0ms Speed: 2.9ms preprocess, 7.0ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:12, 1.03it/s] 14%|█▍ | 2/14 [00:01<00:10, 1.15it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.19it/s] 29%|██▊ | 4/14 [00:03<00:08, 1.19it/s] 36%|███▌ | 5/14 [00:04<00:07, 1.20it/s] 43%|████▎ | 6/14 [00:04<00:06, 1.27it/s] 50%|█████ | 7/14 [00:05<00:05, 1.28it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.30it/s] 64%|██████▍ | 9/14 [00:07<00:03, 1.28it/s] 71%|███████▏ | 10/14 [00:07<00:03, 1.30it/s] 79%|███████▊ | 11/14 [00:08<00:02, 1.31it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.35it/s] 93%|█████████▎| 13/14 [00:09<00:00, 1.53it/s] 100%|██████████| 14/14 [00:10<00:00, 1.74it/s] 100%|██████████| 14/14 [00:10<00:00, 1.36it/s] Decoding latents in cuda:0... done in 0.82s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:11, 1.12it/s] 14%|█▍ | 2/14 [00:01<00:10, 1.14it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.12it/s] 29%|██▊ | 4/14 [00:03<00:09, 1.07it/s] 36%|███▌ | 5/14 [00:04<00:08, 1.09it/s] 43%|████▎ | 6/14 [00:05<00:06, 1.17it/s] 50%|█████ | 7/14 [00:06<00:06, 1.14it/s] 57%|█████▋ | 8/14 [00:07<00:05, 1.16it/s] 64%|██████▍ | 9/14 [00:07<00:04, 1.15it/s] 71%|███████▏ | 10/14 [00:08<00:03, 1.18it/s] 79%|███████▊ | 11/14 [00:09<00:02, 1.17it/s] 86%|████████▌ | 12/14 [00:10<00:01, 1.20it/s] 93%|█████████▎| 13/14 [00:10<00:00, 1.40it/s] 100%|██████████| 14/14 [00:11<00:00, 1.63it/s] 100%|██████████| 14/14 [00:11<00:00, 1.25it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:10, 1.19it/s] 14%|█▍ | 2/14 [00:01<00:09, 1.23it/s] 21%|██▏ | 3/14 [00:02<00:08, 1.23it/s] 29%|██▊ | 4/14 [00:03<00:08, 1.21it/s] 36%|███▌ | 5/14 [00:04<00:07, 1.22it/s] 43%|████▎ | 6/14 [00:04<00:06, 1.29it/s] 50%|█████ | 7/14 [00:05<00:05, 1.29it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.31it/s] 64%|██████▍ | 9/14 [00:07<00:03, 1.29it/s] 71%|███████▏ | 10/14 [00:07<00:03, 1.31it/s] 79%|███████▊ | 11/14 [00:08<00:02, 1.32it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.35it/s] 93%|█████████▎| 13/14 [00:09<00:00, 1.55it/s] 100%|██████████| 14/14 [00:10<00:00, 1.77it/s] 100%|██████████| 14/14 [00:10<00:00, 1.39it/s] Decoding latents in cuda:0... done in 0.79s 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
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/9542a0d6224d43adbd7dd14cca9e17a2/00000-1727086093.webp
https://files.tungsten.run/uploads/45e23ffda1024cb5ad91d4ee6a8419a0/00001-1727086094.webp
https://files.tungsten.run/uploads/9a711f98eb13444ab0da32fe0d273e2d/00002-1727086095.webp
This example was created by evevalentine2017
Finished in 164.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Female bugbear, (best quality), (highly detailed), masterpiece, detailed face, beautiful face, (detailed eyes, deep eyes), (1girl:1.33, solo), full body, very long hair, earrings, (grin:0.9), walking, city, outside, cobblestone, <lora:RPGBugbearXL:1> Full negative prompt: featureless, colorless, text, watermark 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:38, 3.38s/it] 7%|▋ | 2/30 [00:06<01:24, 3.03s/it] 10%|█ | 3/30 [00:08<01:18, 2.90s/it] 13%|█▎ | 4/30 [00:11<01:15, 2.92s/it] 17%|█▋ | 5/30 [00:14<01:10, 2.84s/it] 20%|██ | 6/30 [00:17<01:07, 2.83s/it] 23%|██▎ | 7/30 [00:20<01:06, 2.89s/it] 27%|██▋ | 8/30 [00:22<01:01, 2.78s/it] 30%|███ | 9/30 [00:25<00:57, 2.72s/it] 33%|███▎ | 10/30 [00:28<00:54, 2.74s/it] 37%|███▋ | 11/30 [00:31<00:52, 2.77s/it] 40%|████ | 12/30 [00:33<00:49, 2.75s/it] 43%|████▎ | 13/30 [00:36<00:47, 2.77s/it] 47%|████▋ | 14/30 [00:39<00:44, 2.79s/it] 50%|█████ | 15/30 [00:42<00:41, 2.78s/it] 53%|█████▎ | 16/30 [00:44<00:37, 2.71s/it] 57%|█████▋ | 17/30 [00:47<00:35, 2.70s/it] 60%|██████ | 18/30 [00:50<00:31, 2.66s/it] 63%|██████▎ | 19/30 [00:52<00:28, 2.64s/it] 67%|██████▋ | 20/30 [00:55<00:26, 2.65s/it] 70%|███████ | 21/30 [00:57<00:23, 2.63s/it] 73%|███████▎ | 22/30 [01:00<00:20, 2.53s/it] 77%|███████▋ | 23/30 [01:02<00:17, 2.52s/it] 80%|████████ | 24/30 [01:05<00:14, 2.50s/it] 83%|████████▎ | 25/30 [01:07<00:12, 2.54s/it] 87%|████████▋ | 26/30 [01:10<00:09, 2.49s/it] 90%|█████████ | 27/30 [01:12<00:07, 2.46s/it] 93%|█████████▎| 28/30 [01:14<00:04, 2.40s/it] 97%|█████████▋| 29/30 [01:16<00:02, 2.10s/it] 100%|██████████| 30/30 [01:17<00:00, 1.86s/it] 100%|██████████| 30/30 [01:17<00:00, 2.58s/it] Decoding latents in cuda:0... done in 2.38s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.9ms Speed: 3.3ms preprocess, 7.9ms inference, 22.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:13, 1.00s/it] 14%|█▍ | 2/14 [00:01<00:10, 1.13it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.15it/s] 29%|██▊ | 4/14 [00:03<00:08, 1.12it/s] 36%|███▌ | 5/14 [00:04<00:07, 1.16it/s] 43%|████▎ | 6/14 [00:05<00:06, 1.24it/s] 50%|█████ | 7/14 [00:05<00:05, 1.24it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.26it/s] 64%|██████▍ | 9/14 [00:07<00:04, 1.24it/s] 71%|███████▏ | 10/14 [00:08<00:03, 1.27it/s] 79%|███████▊ | 11/14 [00:08<00:02, 1.29it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.33it/s] 93%|█████████▎| 13/14 [00:10<00:00, 1.53it/s] 100%|██████████| 14/14 [00:10<00:00, 1.75it/s] 100%|██████████| 14/14 [00:10<00:00, 1.33it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.1ms preprocess, 7.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 (no detections), 7.5ms Speed: 3.0ms preprocess, 7.5ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 1 hand, 7.1ms Speed: 3.0ms preprocess, 7.1ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:11, 1.11it/s] 14%|█▍ | 2/14 [00:01<00:10, 1.13it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.11it/s] 29%|██▊ | 4/14 [00:03<00:09, 1.11it/s] 36%|███▌ | 5/14 [00:04<00:08, 1.12it/s] 43%|████▎ | 6/14 [00:05<00:06, 1.19it/s] 50%|█████ | 7/14 [00:06<00:05, 1.19it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.21it/s] 64%|██████▍ | 9/14 [00:07<00:04, 1.19it/s] 71%|███████▏ | 10/14 [00:08<00:03, 1.24it/s] 79%|███████▊ | 11/14 [00:09<00:02, 1.27it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.30it/s] 93%|█████████▎| 13/14 [00:10<00:00, 1.49it/s] 100%|██████████| 14/14 [00:10<00:00, 1.71it/s] 100%|██████████| 14/14 [00:10<00:00, 1.30it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.8ms Speed: 3.2ms preprocess, 7.8ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:11, 1.13it/s] 14%|█▍ | 2/14 [00:01<00:10, 1.19it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.20it/s] 29%|██▊ | 4/14 [00:03<00:08, 1.19it/s] 36%|███▌ | 5/14 [00:04<00:07, 1.21it/s] 43%|████▎ | 6/14 [00:04<00:06, 1.27it/s] 50%|█████ | 7/14 [00:05<00:05, 1.27it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.30it/s] 64%|██████▍ | 9/14 [00:07<00:03, 1.28it/s] 71%|███████▏ | 10/14 [00:07<00:03, 1.30it/s] 79%|███████▊ | 11/14 [00:08<00:02, 1.29it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.32it/s] 93%|█████████▎| 13/14 [00:09<00:00, 1.52it/s] 100%|██████████| 14/14 [00:10<00:00, 1.73it/s] 100%|██████████| 14/14 [00:10<00:00, 1.36it/s] Decoding latents in cuda:0... done in 0.81s Move latents to cpu... done in 0.0s 0: 640x640 3 hands, 7.0ms Speed: 2.9ms preprocess, 7.0ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:12, 1.03it/s] 14%|█▍ | 2/14 [00:01<00:10, 1.15it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.19it/s] 29%|██▊ | 4/14 [00:03<00:08, 1.19it/s] 36%|███▌ | 5/14 [00:04<00:07, 1.20it/s] 43%|████▎ | 6/14 [00:04<00:06, 1.27it/s] 50%|█████ | 7/14 [00:05<00:05, 1.28it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.30it/s] 64%|██████▍ | 9/14 [00:07<00:03, 1.28it/s] 71%|███████▏ | 10/14 [00:07<00:03, 1.30it/s] 79%|███████▊ | 11/14 [00:08<00:02, 1.31it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.35it/s] 93%|█████████▎| 13/14 [00:09<00:00, 1.53it/s] 100%|██████████| 14/14 [00:10<00:00, 1.74it/s] 100%|██████████| 14/14 [00:10<00:00, 1.36it/s] Decoding latents in cuda:0... done in 0.82s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:11, 1.12it/s] 14%|█▍ | 2/14 [00:01<00:10, 1.14it/s] 21%|██▏ | 3/14 [00:02<00:09, 1.12it/s] 29%|██▊ | 4/14 [00:03<00:09, 1.07it/s] 36%|███▌ | 5/14 [00:04<00:08, 1.09it/s] 43%|████▎ | 6/14 [00:05<00:06, 1.17it/s] 50%|█████ | 7/14 [00:06<00:06, 1.14it/s] 57%|█████▋ | 8/14 [00:07<00:05, 1.16it/s] 64%|██████▍ | 9/14 [00:07<00:04, 1.15it/s] 71%|███████▏ | 10/14 [00:08<00:03, 1.18it/s] 79%|███████▊ | 11/14 [00:09<00:02, 1.17it/s] 86%|████████▌ | 12/14 [00:10<00:01, 1.20it/s] 93%|█████████▎| 13/14 [00:10<00:00, 1.40it/s] 100%|██████████| 14/14 [00:11<00:00, 1.63it/s] 100%|██████████| 14/14 [00:11<00:00, 1.25it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:10, 1.19it/s] 14%|█▍ | 2/14 [00:01<00:09, 1.23it/s] 21%|██▏ | 3/14 [00:02<00:08, 1.23it/s] 29%|██▊ | 4/14 [00:03<00:08, 1.21it/s] 36%|███▌ | 5/14 [00:04<00:07, 1.22it/s] 43%|████▎ | 6/14 [00:04<00:06, 1.29it/s] 50%|█████ | 7/14 [00:05<00:05, 1.29it/s] 57%|█████▋ | 8/14 [00:06<00:04, 1.31it/s] 64%|██████▍ | 9/14 [00:07<00:03, 1.29it/s] 71%|███████▏ | 10/14 [00:07<00:03, 1.31it/s] 79%|███████▊ | 11/14 [00:08<00:02, 1.32it/s] 86%|████████▌ | 12/14 [00:09<00:01, 1.35it/s] 93%|█████████▎| 13/14 [00:09<00:00, 1.55it/s] 100%|██████████| 14/14 [00:10<00:00, 1.77it/s] 100%|██████████| 14/14 [00:10<00:00, 1.39it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s Uploading outputs... Finished.