tungsten-logo
Sign In
By the Aquarium with Kawaii Niji Mix
kawaii-niji-mix:v1.0
evevalentine2017
evevalentine2017
·
Mar 18
356
Input
prompt
Specify things to see in the output
1girl, kawaii, cute, aquarium, casual, fish, looking at viewer, smile, hair ornament, multicolored hair, hairclip, dolphin, dutch angle, pov,
negative_prompt
Specify things to not see in the output
watermark, sepia, black & white, EasyNegative, NG_DeepNegative_V1_75T, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)),(ugly:1.33)
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
3928673858
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M Karras
samping_steps
Number of denoising steps
24
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
anything_fp16.safetensors
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)
EasyNegative.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
ng_deepnegative_v1_75t.pt
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.
false
Output
https://files.tungsten.run/uploads/b3b607fed28141aaa38261c209f27e65/00000-3928673858.webp
https://files.tungsten.run/uploads/b623cb27f1ff428c82bb2f4f33f2523c/00001-3928673859.webp
https://files.tungsten.run/uploads/1f49121eb1ba43afa643a50a28b64f29/00002-3928673860.webp
https://files.tungsten.run/uploads/97669bbebcca4197b14c852f42bbc813/00003-3928673861.webp
Finished in 52.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/anything_fp16.safetensors Full prompt: 1girl, kawaii, cute, aquarium, casual, fish, looking at viewer, smile, hair ornament, multicolored hair, hairclip, dolphin, dutch angle, pov, Full negative prompt: watermark, sepia, black & white, EasyNegative, NG_DeepNegative_V1_75T, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)),(ugly:1.33) 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:00<00:14, 1.54it/s] 8%|▊ | 2/24 [00:01<00:14, 1.49it/s] 12%|█▎ | 3/24 [00:01<00:14, 1.50it/s] 17%|█▋ | 4/24 [00:02<00:13, 1.49it/s] 21%|██ | 5/24 [00:03<00:12, 1.48it/s] 25%|██▌ | 6/24 [00:04<00:12, 1.47it/s] 29%|██▉ | 7/24 [00:04<00:11, 1.48it/s] 33%|███▎ | 8/24 [00:05<00:10, 1.46it/s] 38%|███▊ | 9/24 [00:06<00:10, 1.46it/s] 42%|████▏ | 10/24 [00:06<00:09, 1.47it/s] 46%|████▌ | 11/24 [00:07<00:08, 1.47it/s] 50%|█████ | 12/24 [00:08<00:08, 1.47it/s] 54%|█████▍ | 13/24 [00:08<00:07, 1.47it/s] 58%|█████▊ | 14/24 [00:09<00:06, 1.47it/s] 62%|██████▎ | 15/24 [00:10<00:06, 1.46it/s] 67%|██████▋ | 16/24 [00:10<00:05, 1.46it/s] 71%|███████ | 17/24 [00:11<00:04, 1.46it/s] 75%|███████▌ | 18/24 [00:12<00:04, 1.47it/s] 79%|███████▉ | 19/24 [00:12<00:03, 1.47it/s] 83%|████████▎ | 20/24 [00:13<00:02, 1.47it/s] 88%|████████▊ | 21/24 [00:14<00:02, 1.46it/s] 92%|█████████▏| 22/24 [00:14<00:01, 1.47it/s] 96%|█████████▌| 23/24 [00:15<00:00, 1.46it/s] 100%|██████████| 24/24 [00:16<00:00, 1.46it/s] 100%|██████████| 24/24 [00:16<00:00, 1.47it/s] Decoding latents in cuda:0... done in 0.99s Move latents to cpu... done in 0.05s 0: 640x640 1 face, 8.7ms Speed: 3.2ms preprocess, 8.7ms inference, 31.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:03, 3.28it/s] 18%|█▊ | 2/11 [00:00<00:01, 4.66it/s] 27%|██▋ | 3/11 [00:00<00:01, 5.35it/s] 36%|███▋ | 4/11 [00:00<00:01, 5.76it/s] 45%|████▌ | 5/11 [00:00<00:01, 5.95it/s] 55%|█████▍ | 6/11 [00:01<00:00, 6.01it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.02it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.08it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.19it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.24it/s] 100%|██████████| 11/11 [00:01<00:00, 6.31it/s] 100%|██████████| 11/11 [00:01<00:00, 5.86it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.5ms Speed: 2.8ms preprocess, 7.5ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.92it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.65it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.56it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.54it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.53it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.38it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.29it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.05it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.17it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.27it/s] 100%|██████████| 11/11 [00:01<00:00, 6.34it/s] 100%|██████████| 11/11 [00:01<00:00, 6.36it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.7ms Speed: 2.7ms preprocess, 7.7ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.89it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.52it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.51it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.51it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.49it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.38it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.26it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.25it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.29it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.22it/s] 100%|██████████| 11/11 [00:01<00:00, 6.30it/s] 100%|██████████| 11/11 [00:01<00:00, 6.35it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.2ms Speed: 2.8ms preprocess, 7.2ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.94it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.70it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.61it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.57it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.54it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.41it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.31it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.29it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.34it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.40it/s] 100%|██████████| 11/11 [00:01<00:00, 6.43it/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 0.45s Move latents to cpu... done in 0.23s 0: 640x640 1 face, 7.5ms Speed: 2.8ms preprocess, 7.5ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.80it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.61it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.58it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.54it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.50it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.36it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.26it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.26it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.32it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.40it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.9ms Speed: 2.6ms preprocess, 7.9ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 5.92it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.19it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.32it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.36it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.37it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.28it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.20it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.23it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.29it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.32it/s] 100%|██████████| 11/11 [00:01<00:00, 6.36it/s] 100%|██████████| 11/11 [00:01<00:00, 6.29it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.62it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.52it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.51it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.50it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.26it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.19it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.22it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.30it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.35it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.32it/s] 100%|██████████| 11/11 [00:01<00:00, 6.34it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.7ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.88it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.63it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.55it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.52it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.51it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.36it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.22it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.22it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.28it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.35it/s] 100%|██████████| 11/11 [00:01<00:00, 6.39it/s] 100%|██████████| 11/11 [00:01<00:00, 6.39it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.2ms Speed: 2.8ms preprocess, 7.2ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.71it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.60it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.52it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.50it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.49it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.38it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.27it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.22it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.29it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.34it/s] 100%|██████████| 11/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.38it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.67it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.58it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.55it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.53it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.41it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.20it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.21it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.22it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.26it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.32it/s] 100%|██████████| 11/11 [00:01<00:00, 6.28it/s] 100%|██████████| 11/11 [00:01<00:00, 6.33it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt
Specify things to see in the output
1girl, kawaii, cute, aquarium, casual, fish, looking at viewer, smile, hair ornament, multicolored hair, hairclip, dolphin, dutch angle, pov,
negative_prompt
Specify things to not see in the output
watermark, sepia, black & white, EasyNegative, NG_DeepNegative_V1_75T, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)),(ugly:1.33)
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
3928673858
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M Karras
samping_steps
Number of denoising steps
24
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
anything_fp16.safetensors
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)
EasyNegative.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
ng_deepnegative_v1_75t.pt
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.
false
https://files.tungsten.run/uploads/b3b607fed28141aaa38261c209f27e65/00000-3928673858.webp
https://files.tungsten.run/uploads/b623cb27f1ff428c82bb2f4f33f2523c/00001-3928673859.webp
https://files.tungsten.run/uploads/1f49121eb1ba43afa643a50a28b64f29/00002-3928673860.webp
https://files.tungsten.run/uploads/97669bbebcca4197b14c852f42bbc813/00003-3928673861.webp
Finished in 52.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/anything_fp16.safetensors Full prompt: 1girl, kawaii, cute, aquarium, casual, fish, looking at viewer, smile, hair ornament, multicolored hair, hairclip, dolphin, dutch angle, pov, Full negative prompt: watermark, sepia, black & white, EasyNegative, NG_DeepNegative_V1_75T, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)),(ugly:1.33) 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:00<00:14, 1.54it/s] 8%|▊ | 2/24 [00:01<00:14, 1.49it/s] 12%|█▎ | 3/24 [00:01<00:14, 1.50it/s] 17%|█▋ | 4/24 [00:02<00:13, 1.49it/s] 21%|██ | 5/24 [00:03<00:12, 1.48it/s] 25%|██▌ | 6/24 [00:04<00:12, 1.47it/s] 29%|██▉ | 7/24 [00:04<00:11, 1.48it/s] 33%|███▎ | 8/24 [00:05<00:10, 1.46it/s] 38%|███▊ | 9/24 [00:06<00:10, 1.46it/s] 42%|████▏ | 10/24 [00:06<00:09, 1.47it/s] 46%|████▌ | 11/24 [00:07<00:08, 1.47it/s] 50%|█████ | 12/24 [00:08<00:08, 1.47it/s] 54%|█████▍ | 13/24 [00:08<00:07, 1.47it/s] 58%|█████▊ | 14/24 [00:09<00:06, 1.47it/s] 62%|██████▎ | 15/24 [00:10<00:06, 1.46it/s] 67%|██████▋ | 16/24 [00:10<00:05, 1.46it/s] 71%|███████ | 17/24 [00:11<00:04, 1.46it/s] 75%|███████▌ | 18/24 [00:12<00:04, 1.47it/s] 79%|███████▉ | 19/24 [00:12<00:03, 1.47it/s] 83%|████████▎ | 20/24 [00:13<00:02, 1.47it/s] 88%|████████▊ | 21/24 [00:14<00:02, 1.46it/s] 92%|█████████▏| 22/24 [00:14<00:01, 1.47it/s] 96%|█████████▌| 23/24 [00:15<00:00, 1.46it/s] 100%|██████████| 24/24 [00:16<00:00, 1.46it/s] 100%|██████████| 24/24 [00:16<00:00, 1.47it/s] Decoding latents in cuda:0... done in 0.99s Move latents to cpu... done in 0.05s 0: 640x640 1 face, 8.7ms Speed: 3.2ms preprocess, 8.7ms inference, 31.1ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:03, 3.28it/s] 18%|█▊ | 2/11 [00:00<00:01, 4.66it/s] 27%|██▋ | 3/11 [00:00<00:01, 5.35it/s] 36%|███▋ | 4/11 [00:00<00:01, 5.76it/s] 45%|████▌ | 5/11 [00:00<00:01, 5.95it/s] 55%|█████▍ | 6/11 [00:01<00:00, 6.01it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.02it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.08it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.19it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.24it/s] 100%|██████████| 11/11 [00:01<00:00, 6.31it/s] 100%|██████████| 11/11 [00:01<00:00, 5.86it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.5ms Speed: 2.8ms preprocess, 7.5ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.92it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.65it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.56it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.54it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.53it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.38it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.29it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.05it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.17it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.27it/s] 100%|██████████| 11/11 [00:01<00:00, 6.34it/s] 100%|██████████| 11/11 [00:01<00:00, 6.36it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.7ms Speed: 2.7ms preprocess, 7.7ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.89it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.52it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.51it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.51it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.49it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.38it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.26it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.25it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.29it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.22it/s] 100%|██████████| 11/11 [00:01<00:00, 6.30it/s] 100%|██████████| 11/11 [00:01<00:00, 6.35it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 7.2ms Speed: 2.8ms preprocess, 7.2ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.94it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.70it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.61it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.57it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.54it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.41it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.31it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.29it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.34it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.40it/s] 100%|██████████| 11/11 [00:01<00:00, 6.43it/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 0.45s Move latents to cpu... done in 0.23s 0: 640x640 1 face, 7.5ms Speed: 2.8ms preprocess, 7.5ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.80it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.61it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.58it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.54it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.50it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.36it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.26it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.26it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.32it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.40it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.9ms Speed: 2.6ms preprocess, 7.9ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 5.92it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.19it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.32it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.36it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.37it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.28it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.20it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.23it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.29it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.32it/s] 100%|██████████| 11/11 [00:01<00:00, 6.36it/s] 100%|██████████| 11/11 [00:01<00:00, 6.29it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.62it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.52it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.51it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.50it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.26it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.19it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.22it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.30it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.35it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.32it/s] 100%|██████████| 11/11 [00:01<00:00, 6.34it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.7ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.88it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.63it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.55it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.52it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.51it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.36it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.22it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.22it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.28it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.35it/s] 100%|██████████| 11/11 [00:01<00:00, 6.39it/s] 100%|██████████| 11/11 [00:01<00:00, 6.39it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.2ms Speed: 2.8ms preprocess, 7.2ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.71it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.60it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.52it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.50it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.49it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.38it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.27it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.22it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.29it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.34it/s] 100%|██████████| 11/11 [00:01<00:00, 6.37it/s] 100%|██████████| 11/11 [00:01<00:00, 6.38it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:01, 6.67it/s] 18%|█▊ | 2/11 [00:00<00:01, 6.58it/s] 27%|██▋ | 3/11 [00:00<00:01, 6.55it/s] 36%|███▋ | 4/11 [00:00<00:01, 6.53it/s] 45%|████▌ | 5/11 [00:00<00:00, 6.41it/s] 55%|█████▍ | 6/11 [00:00<00:00, 6.20it/s] 64%|██████▎ | 7/11 [00:01<00:00, 6.21it/s] 73%|███████▎ | 8/11 [00:01<00:00, 6.22it/s] 82%|████████▏ | 9/11 [00:01<00:00, 6.26it/s] 91%|█████████ | 10/11 [00:01<00:00, 6.32it/s] 100%|██████████| 11/11 [00:01<00:00, 6.28it/s] 100%|██████████| 11/11 [00:01<00:00, 6.33it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s Uploading outputs... Finished.