Version: v1
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
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
num_outputs
Number of output images
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
width
Output image width
height
Output image height
reference_image
Image that the output should be similar to
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/a4dd117619444d16b453352fcd34af57/00000-1957357307.png
https://files.tungsten.run/uploads/74e882eef55a4c4b9a25071cbdbe413b/00001-1957357308.png
https://files.tungsten.run/uploads/57534b7497064cbf81d0ff390ccb5567/00002-1957357309.png
https://files.tungsten.run/uploads/e8275ca12bbf4c6d8d323b90d87c535c/00003-1957357310.png
This example was created by evevalentine2017
Finished in 65.1 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: absurdres, weird atmosphere, (best quality:1.1), (masterpiece:1.2), ((full body view)), detailed, (high detailed skin), depth of field, highres, best illumination, 1girl, cute face, behind view, looking back, beautiful face, perfect skin, long hair, white hair, white skin, ass, ((1mechanical girl)), solo, (machine made joints:1.2), ((mechanical limbs)), (vessels connected to tubes), robot horns, (mechanical vertebra attaching to back), ((mechanical cervial attaching to neck)), (wires and cables attaching to neck:1.2), (wires and cables on head:1.2), science fiction, wired-hair, cable hair, (masterpiece:1.5), (best quality:1.5), (ultra detailed:1.5) Full negative prompt: BadDream, negative_hand-neg, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, (monochrome), (grayscale), text, signature, watermark, logo 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:00<00:15, 1.52it/s] 8%|▊ | 2/24 [00:01<00:13, 1.57it/s] 12%|█▎ | 3/24 [00:01<00:13, 1.61it/s] 17%|█▋ | 4/24 [00:02<00:12, 1.61it/s] 21%|██ | 5/24 [00:03<00:11, 1.62it/s] 25%|██▌ | 6/24 [00:03<00:11, 1.62it/s] 29%|██▉ | 7/24 [00:04<00:10, 1.63it/s] 33%|███▎ | 8/24 [00:04<00:09, 1.63it/s] 38%|███▊ | 9/24 [00:05<00:09, 1.63it/s] 42%|████▏ | 10/24 [00:06<00:08, 1.63it/s] 46%|████▌ | 11/24 [00:06<00:07, 1.63it/s] 50%|█████ | 12/24 [00:07<00:07, 1.63it/s] 54%|█████▍ | 13/24 [00:08<00:06, 1.63it/s] 58%|█████▊ | 14/24 [00:08<00:06, 1.63it/s] 62%|██████▎ | 15/24 [00:09<00:05, 1.63it/s] 67%|██████▋ | 16/24 [00:09<00:04, 1.63it/s] 71%|███████ | 17/24 [00:10<00:04, 1.63it/s] 75%|███████▌ | 18/24 [00:11<00:03, 1.63it/s] 79%|███████▉ | 19/24 [00:11<00:03, 1.63it/s] 83%|████████▎ | 20/24 [00:12<00:02, 1.63it/s] 88%|████████▊ | 21/24 [00:12<00:01, 1.63it/s] 92%|█████████▏| 22/24 [00:13<00:01, 1.62it/s] 96%|█████████▌| 23/24 [00:14<00:00, 1.62it/s] 100%|██████████| 24/24 [00:14<00:00, 1.62it/s] 100%|██████████| 24/24 [00:14<00:00, 1.62it/s] Decoding latents in cuda:0... done in 0.95s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 4.6ms preprocess, 7.8ms inference, 33.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:04, 2.60it/s] 14%|█▍ | 2/14 [00:00<00:03, 3.68it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.19it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.33it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.59it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.74it/s] 50%|█████ | 7/14 [00:01<00:01, 4.84it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.91it/s] 64%|██████▍ | 9/14 [00:02<00:01, 4.80it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.91it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.97it/s] 86%|████████▌ | 12/14 [00:02<00:00, 5.02it/s] 93%|█████████▎| 13/14 [00:02<00:00, 5.02it/s] 100%|██████████| 14/14 [00:02<00:00, 4.91it/s] 100%|██████████| 14/14 [00:02<00:00, 4.67it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.01s 0: 640x640 2 hands, 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 2.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.03it/s] 14%|█▍ | 2/14 [00:00<00:02, 5.03it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.97it/s] 29%|██▊ | 4/14 [00:00<00:02, 5.00it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.98it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.96it/s] 50%|█████ | 7/14 [00:01<00:01, 5.00it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.85it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.91it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.94it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.96it/s] 86%|████████▌ | 12/14 [00:02<00:00, 5.00it/s] 93%|█████████▎| 13/14 [00:02<00:00, 5.00it/s] 100%|██████████| 14/14 [00:02<00:00, 4.92it/s] 100%|██████████| 14/14 [00:02<00:00, 4.95it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.09it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.74it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.88it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.99it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.95it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.96it/s] 50%|█████ | 7/14 [00:01<00:01, 4.86it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.93it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.98it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.97it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.96it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.80it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.86it/s] 100%|██████████| 14/14 [00:02<00:00, 4.90it/s] 100%|██████████| 14/14 [00:02<00:00, 4.91it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.8ms Speed: 3.1ms preprocess, 7.8ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.08it/s] 14%|█▍ | 2/14 [00:00<00:02, 5.05it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.96it/s] 29%|██▊ | 4/14 [00:00<00:01, 5.01it/s] 36%|███▌ | 5/14 [00:00<00:01, 5.03it/s] 43%|████▎ | 6/14 [00:01<00:01, 5.05it/s] 50%|█████ | 7/14 [00:01<00:01, 5.04it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.91it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.95it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.96it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.97it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.94it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.88it/s] 100%|██████████| 14/14 [00:02<00:00, 4.94it/s] 100%|██████████| 14/14 [00:02<00:00, 4.97it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.3ms Speed: 2.9ms preprocess, 7.3ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.07it/s] 14%|█▍ | 2/14 [00:00<00:02, 5.02it/s] 21%|██▏ | 3/14 [00:00<00:02, 5.00it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.96it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.93it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.95it/s] 50%|█████ | 7/14 [00:01<00:01, 4.97it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.99it/s] 64%|██████▍ | 9/14 [00:01<00:00, 5.01it/s] 71%|███████▏ | 10/14 [00:02<00:00, 5.00it/s] 79%|███████▊ | 11/14 [00:02<00:00, 5.01it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.99it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.99it/s] 100%|██████████| 14/14 [00:02<00:00, 4.99it/s] 100%|██████████| 14/14 [00:02<00:00, 4.99it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.00it/s] 14%|█▍ | 2/14 [00:00<00:02, 5.00it/s] 21%|██▏ | 3/14 [00:00<00:02, 5.00it/s] 29%|██▊ | 4/14 [00:00<00:01, 5.01it/s] 36%|███▌ | 5/14 [00:00<00:01, 5.02it/s] 43%|████▎ | 6/14 [00:01<00:01, 5.04it/s] 50%|█████ | 7/14 [00:01<00:01, 5.05it/s] 57%|█████▋ | 8/14 [00:01<00:01, 5.06it/s] 64%|██████▍ | 9/14 [00:01<00:00, 5.05it/s] 71%|███████▏ | 10/14 [00:01<00:00, 5.07it/s] 79%|███████▊ | 11/14 [00:02<00:00, 5.06it/s] 86%|████████▌ | 12/14 [00:02<00:00, 5.08it/s] 93%|█████████▎| 13/14 [00:02<00:00, 5.07it/s] 100%|██████████| 14/14 [00:02<00:00, 5.08it/s] 100%|██████████| 14/14 [00:02<00:00, 5.05it/s] Decoding latents in cuda:0... =========================================== A tensor with all NaNs was produced in VAE. Converted VAE into 32-bit float and retry. =========================================== done in 0.44s Move latents to cpu... done in 0.22s 0: 640x640 1 face, 7.5ms Speed: 2.7ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.02it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.71it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.84it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.91it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.91it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.94it/s] 50%|█████ | 7/14 [00:01<00:01, 4.78it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.83it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.89it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.92it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.93it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.87it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.91it/s] 100%|██████████| 14/14 [00:02<00:00, 4.94it/s] 100%|██████████| 14/14 [00:02<00:00, 4.89it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.3ms Speed: 3.0ms preprocess, 7.3ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 4.57it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.76it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.79it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.85it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.88it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.69it/s] 50%|█████ | 7/14 [00:01<00:01, 4.77it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.86it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.90it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.93it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.88it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.91it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.96it/s] 100%|██████████| 14/14 [00:02<00:00, 4.99it/s] 100%|██████████| 14/14 [00:02<00:00, 4.88it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 8.0ms Speed: 2.9ms preprocess, 8.0ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 4.78it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.93it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.97it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.98it/s] 36%|███▌ | 5/14 [00:01<00:01, 5.00it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.81it/s] 50%|█████ | 7/14 [00:01<00:01, 4.86it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.84it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.90it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.91it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.83it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.78it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.83it/s] 100%|██████████| 14/14 [00:02<00:00, 4.87it/s] 100%|██████████| 14/14 [00:02<00:00, 4.87it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.3ms Speed: 2.9ms preprocess, 7.3ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 4.61it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.77it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.86it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.88it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.94it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.83it/s] 50%|█████ | 7/14 [00:01<00:01, 4.89it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.95it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.98it/s] 71%|███████▏ | 10/14 [00:02<00:00, 5.00it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.98it/s] 86%|████████▌ | 12/14 [00:02<00:00, 5.00it/s] 93%|█████████▎| 13/14 [00:02<00:00, 5.01it/s] 100%|██████████| 14/14 [00:02<00:00, 4.96it/s] 100%|██████████| 14/14 [00:02<00:00, 4.93it/s] Decoding latents in cuda:0... done in 0.4s 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
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
num_outputs
Number of output images
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
width
Output image width
height
Output image height
reference_image
Image that the output should be similar to
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/a4dd117619444d16b453352fcd34af57/00000-1957357307.png
https://files.tungsten.run/uploads/74e882eef55a4c4b9a25071cbdbe413b/00001-1957357308.png
https://files.tungsten.run/uploads/57534b7497064cbf81d0ff390ccb5567/00002-1957357309.png
https://files.tungsten.run/uploads/e8275ca12bbf4c6d8d323b90d87c535c/00003-1957357310.png
This example was created by evevalentine2017
Finished in 65.1 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: absurdres, weird atmosphere, (best quality:1.1), (masterpiece:1.2), ((full body view)), detailed, (high detailed skin), depth of field, highres, best illumination, 1girl, cute face, behind view, looking back, beautiful face, perfect skin, long hair, white hair, white skin, ass, ((1mechanical girl)), solo, (machine made joints:1.2), ((mechanical limbs)), (vessels connected to tubes), robot horns, (mechanical vertebra attaching to back), ((mechanical cervial attaching to neck)), (wires and cables attaching to neck:1.2), (wires and cables on head:1.2), science fiction, wired-hair, cable hair, (masterpiece:1.5), (best quality:1.5), (ultra detailed:1.5) Full negative prompt: BadDream, negative_hand-neg, (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, (monochrome), (grayscale), text, signature, watermark, logo 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:00<00:15, 1.52it/s] 8%|▊ | 2/24 [00:01<00:13, 1.57it/s] 12%|█▎ | 3/24 [00:01<00:13, 1.61it/s] 17%|█▋ | 4/24 [00:02<00:12, 1.61it/s] 21%|██ | 5/24 [00:03<00:11, 1.62it/s] 25%|██▌ | 6/24 [00:03<00:11, 1.62it/s] 29%|██▉ | 7/24 [00:04<00:10, 1.63it/s] 33%|███▎ | 8/24 [00:04<00:09, 1.63it/s] 38%|███▊ | 9/24 [00:05<00:09, 1.63it/s] 42%|████▏ | 10/24 [00:06<00:08, 1.63it/s] 46%|████▌ | 11/24 [00:06<00:07, 1.63it/s] 50%|█████ | 12/24 [00:07<00:07, 1.63it/s] 54%|█████▍ | 13/24 [00:08<00:06, 1.63it/s] 58%|█████▊ | 14/24 [00:08<00:06, 1.63it/s] 62%|██████▎ | 15/24 [00:09<00:05, 1.63it/s] 67%|██████▋ | 16/24 [00:09<00:04, 1.63it/s] 71%|███████ | 17/24 [00:10<00:04, 1.63it/s] 75%|███████▌ | 18/24 [00:11<00:03, 1.63it/s] 79%|███████▉ | 19/24 [00:11<00:03, 1.63it/s] 83%|████████▎ | 20/24 [00:12<00:02, 1.63it/s] 88%|████████▊ | 21/24 [00:12<00:01, 1.63it/s] 92%|█████████▏| 22/24 [00:13<00:01, 1.62it/s] 96%|█████████▌| 23/24 [00:14<00:00, 1.62it/s] 100%|██████████| 24/24 [00:14<00:00, 1.62it/s] 100%|██████████| 24/24 [00:14<00:00, 1.62it/s] Decoding latents in cuda:0... done in 0.95s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 4.6ms preprocess, 7.8ms inference, 33.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:04, 2.60it/s] 14%|█▍ | 2/14 [00:00<00:03, 3.68it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.19it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.33it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.59it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.74it/s] 50%|█████ | 7/14 [00:01<00:01, 4.84it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.91it/s] 64%|██████▍ | 9/14 [00:02<00:01, 4.80it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.91it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.97it/s] 86%|████████▌ | 12/14 [00:02<00:00, 5.02it/s] 93%|█████████▎| 13/14 [00:02<00:00, 5.02it/s] 100%|██████████| 14/14 [00:02<00:00, 4.91it/s] 100%|██████████| 14/14 [00:02<00:00, 4.67it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.01s 0: 640x640 2 hands, 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 2.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.03it/s] 14%|█▍ | 2/14 [00:00<00:02, 5.03it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.97it/s] 29%|██▊ | 4/14 [00:00<00:02, 5.00it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.98it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.96it/s] 50%|█████ | 7/14 [00:01<00:01, 5.00it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.85it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.91it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.94it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.96it/s] 86%|████████▌ | 12/14 [00:02<00:00, 5.00it/s] 93%|█████████▎| 13/14 [00:02<00:00, 5.00it/s] 100%|██████████| 14/14 [00:02<00:00, 4.92it/s] 100%|██████████| 14/14 [00:02<00:00, 4.95it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.09it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.74it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.88it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.99it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.95it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.96it/s] 50%|█████ | 7/14 [00:01<00:01, 4.86it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.93it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.98it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.97it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.96it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.80it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.86it/s] 100%|██████████| 14/14 [00:02<00:00, 4.90it/s] 100%|██████████| 14/14 [00:02<00:00, 4.91it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.8ms Speed: 3.1ms preprocess, 7.8ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.08it/s] 14%|█▍ | 2/14 [00:00<00:02, 5.05it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.96it/s] 29%|██▊ | 4/14 [00:00<00:01, 5.01it/s] 36%|███▌ | 5/14 [00:00<00:01, 5.03it/s] 43%|████▎ | 6/14 [00:01<00:01, 5.05it/s] 50%|█████ | 7/14 [00:01<00:01, 5.04it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.91it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.95it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.96it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.97it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.94it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.88it/s] 100%|██████████| 14/14 [00:02<00:00, 4.94it/s] 100%|██████████| 14/14 [00:02<00:00, 4.97it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.3ms Speed: 2.9ms preprocess, 7.3ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.07it/s] 14%|█▍ | 2/14 [00:00<00:02, 5.02it/s] 21%|██▏ | 3/14 [00:00<00:02, 5.00it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.96it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.93it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.95it/s] 50%|█████ | 7/14 [00:01<00:01, 4.97it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.99it/s] 64%|██████▍ | 9/14 [00:01<00:00, 5.01it/s] 71%|███████▏ | 10/14 [00:02<00:00, 5.00it/s] 79%|███████▊ | 11/14 [00:02<00:00, 5.01it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.99it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.99it/s] 100%|██████████| 14/14 [00:02<00:00, 4.99it/s] 100%|██████████| 14/14 [00:02<00:00, 4.99it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.00it/s] 14%|█▍ | 2/14 [00:00<00:02, 5.00it/s] 21%|██▏ | 3/14 [00:00<00:02, 5.00it/s] 29%|██▊ | 4/14 [00:00<00:01, 5.01it/s] 36%|███▌ | 5/14 [00:00<00:01, 5.02it/s] 43%|████▎ | 6/14 [00:01<00:01, 5.04it/s] 50%|█████ | 7/14 [00:01<00:01, 5.05it/s] 57%|█████▋ | 8/14 [00:01<00:01, 5.06it/s] 64%|██████▍ | 9/14 [00:01<00:00, 5.05it/s] 71%|███████▏ | 10/14 [00:01<00:00, 5.07it/s] 79%|███████▊ | 11/14 [00:02<00:00, 5.06it/s] 86%|████████▌ | 12/14 [00:02<00:00, 5.08it/s] 93%|█████████▎| 13/14 [00:02<00:00, 5.07it/s] 100%|██████████| 14/14 [00:02<00:00, 5.08it/s] 100%|██████████| 14/14 [00:02<00:00, 5.05it/s] Decoding latents in cuda:0... =========================================== A tensor with all NaNs was produced in VAE. Converted VAE into 32-bit float and retry. =========================================== done in 0.44s Move latents to cpu... done in 0.22s 0: 640x640 1 face, 7.5ms Speed: 2.7ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 5.02it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.71it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.84it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.91it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.91it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.94it/s] 50%|█████ | 7/14 [00:01<00:01, 4.78it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.83it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.89it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.92it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.93it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.87it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.91it/s] 100%|██████████| 14/14 [00:02<00:00, 4.94it/s] 100%|██████████| 14/14 [00:02<00:00, 4.89it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.3ms Speed: 3.0ms preprocess, 7.3ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 4.57it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.76it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.79it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.85it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.88it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.69it/s] 50%|█████ | 7/14 [00:01<00:01, 4.77it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.86it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.90it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.93it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.88it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.91it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.96it/s] 100%|██████████| 14/14 [00:02<00:00, 4.99it/s] 100%|██████████| 14/14 [00:02<00:00, 4.88it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 8.0ms Speed: 2.9ms preprocess, 8.0ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 4.78it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.93it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.97it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.98it/s] 36%|███▌ | 5/14 [00:01<00:01, 5.00it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.81it/s] 50%|█████ | 7/14 [00:01<00:01, 4.86it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.84it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.90it/s] 71%|███████▏ | 10/14 [00:02<00:00, 4.91it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.83it/s] 86%|████████▌ | 12/14 [00:02<00:00, 4.78it/s] 93%|█████████▎| 13/14 [00:02<00:00, 4.83it/s] 100%|██████████| 14/14 [00:02<00:00, 4.87it/s] 100%|██████████| 14/14 [00:02<00:00, 4.87it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.3ms Speed: 2.9ms preprocess, 7.3ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:02, 4.61it/s] 14%|█▍ | 2/14 [00:00<00:02, 4.77it/s] 21%|██▏ | 3/14 [00:00<00:02, 4.86it/s] 29%|██▊ | 4/14 [00:00<00:02, 4.88it/s] 36%|███▌ | 5/14 [00:01<00:01, 4.94it/s] 43%|████▎ | 6/14 [00:01<00:01, 4.83it/s] 50%|█████ | 7/14 [00:01<00:01, 4.89it/s] 57%|█████▋ | 8/14 [00:01<00:01, 4.95it/s] 64%|██████▍ | 9/14 [00:01<00:01, 4.98it/s] 71%|███████▏ | 10/14 [00:02<00:00, 5.00it/s] 79%|███████▊ | 11/14 [00:02<00:00, 4.98it/s] 86%|████████▌ | 12/14 [00:02<00:00, 5.00it/s] 93%|█████████▎| 13/14 [00:02<00:00, 5.01it/s] 100%|██████████| 14/14 [00:02<00:00, 4.96it/s] 100%|██████████| 14/14 [00:02<00:00, 4.93it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s Finished.