tungsten-logo
Sign In
Handsome Warrior with Funny City
funny-city:v1.5
evevalentine2017
evevalentine2017
·
12/14/2023
360
Input
prompt
Specify things to see in the output
(masterpiece, best quality:1.2), (1man, masculine adult male:1.2), turquoise eyes, dark brown hair, shaved head, focus on character, solo, (style-rustmagic:0.8), solo, from front, front view, half shot, detailed face, wild engineer, tentative trust, standing tall, dark red ornate robe, cape, brandishing forbidden mace of thunder, manifesting ethereal strands of power, color-changing surfaces responding to the environment, long-healed scars, <lora:more_details:0.8>
negative_prompt
Specify things to not see in the output
(human face), FastNegativeV2, (By bad artist -neg: 1), (worst quality, low quality: 1.4), (bad_prompt_version2: 0.8), lowres, bad anatomy, bad hands, ((text)), (watermark), error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, ((username)), blurry, (extra limbs), ng_deepnegative_v1_75t, (three hands: 1.3), (three legs: 1.2), (more than two hands: 1.3), (more than two legs: 1.2), label, watermark.
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
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
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.
2659002561
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
28
cfg_scale
Scale for classifier-free guidance
9.5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
blessed2_fp16.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
more_details.safetensors
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
ExoticDance.safetensors
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)
FastNegativeV2.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
By bad artist -neg.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
ng_deepnegative_v1_75t.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
Output
https://files.tungsten.run/uploads/5f1da5a27de742ff99b38b7f1031d04c/00000-2659002561.webp
https://files.tungsten.run/uploads/234f372081c7405b83f2edc238b642c4/00001-2659002562.webp
https://files.tungsten.run/uploads/4c60cc148516499faa393b76333e95f7/00002-2659002563.webp
https://files.tungsten.run/uploads/b0e329ce44174e368bbfcabb8aa7da73/00003-2659002564.webp
Finished in 47.1 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (masterpiece, best quality:1.2), (1man, masculine adult male:1.2), turquoise eyes, dark brown hair, shaved head, focus on character, solo, (style-rustmagic:0.8), solo, from front, front view, half shot, detailed face, wild engineer, tentative trust, standing tall, dark red ornate robe, cape, brandishing forbidden mace of thunder, manifesting ethereal strands of power, color-changing surfaces responding to the environment, long-healed scars, <lora:more_details:0.8> Full negative prompt: (human face), FastNegativeV2, (By bad artist -neg: 1), (worst quality, low quality: 1.4), (bad_prompt_version2: 0.8), lowres, bad anatomy, bad hands, ((text)), (watermark), error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, ((username)), blurry, (extra limbs), ng_deepnegative_v1_75t, (three hands: 1.3), (three legs: 1.2), (more than two hands: 1.3), (more than two legs: 1.2), label, watermark. 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:32, 1.20s/it] 7%|▋ | 2/28 [00:01<00:23, 1.13it/s] 11%|█ | 3/28 [00:02<00:19, 1.28it/s] 14%|█▍ | 4/28 [00:03<00:17, 1.35it/s] 18%|█▊ | 5/28 [00:03<00:16, 1.41it/s] 21%|██▏ | 6/28 [00:04<00:15, 1.44it/s] 25%|██▌ | 7/28 [00:05<00:14, 1.45it/s] 29%|██▊ | 8/28 [00:05<00:13, 1.47it/s] 32%|███▏ | 9/28 [00:06<00:12, 1.48it/s] 36%|███▌ | 10/28 [00:07<00:12, 1.48it/s] 39%|███▉ | 11/28 [00:07<00:11, 1.49it/s] 43%|████▎ | 12/28 [00:08<00:10, 1.49it/s] 46%|████▋ | 13/28 [00:09<00:10, 1.49it/s] 50%|█████ | 14/28 [00:09<00:09, 1.50it/s] 54%|█████▎ | 15/28 [00:10<00:08, 1.50it/s] 57%|█████▋ | 16/28 [00:11<00:08, 1.50it/s] 61%|██████ | 17/28 [00:11<00:07, 1.50it/s] 64%|██████▍ | 18/28 [00:12<00:06, 1.50it/s] 68%|██████▊ | 19/28 [00:13<00:06, 1.50it/s] 71%|███████▏ | 20/28 [00:13<00:05, 1.50it/s] 75%|███████▌ | 21/28 [00:14<00:04, 1.50it/s] 79%|███████▊ | 22/28 [00:15<00:04, 1.49it/s] 82%|████████▏ | 23/28 [00:15<00:03, 1.49it/s] 86%|████████▌ | 24/28 [00:16<00:02, 1.49it/s] 89%|████████▉ | 25/28 [00:17<00:02, 1.50it/s] 93%|█████████▎| 26/28 [00:17<00:01, 1.49it/s] 96%|█████████▋| 27/28 [00:18<00:00, 1.49it/s] 100%|██████████| 28/28 [00:19<00:00, 1.49it/s] 100%|██████████| 28/28 [00:19<00:00, 1.46it/s] Decoding latents in cuda:0... done in 0.98s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.0ms Speed: 4.8ms preprocess, 8.0ms inference, 33.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:04, 3.39it/s] 12%|█▎ | 2/16 [00:00<00:02, 4.74it/s] 19%|█▉ | 3/16 [00:00<00:02, 5.34it/s] 25%|██▌ | 4/16 [00:00<00:02, 5.74it/s] 31%|███▏ | 5/16 [00:00<00:01, 5.99it/s] 38%|███▊ | 6/16 [00:01<00:01, 6.06it/s] 44%|████▍ | 7/16 [00:01<00:01, 6.09it/s] 50%|█████ | 8/16 [00:01<00:01, 6.17it/s] 56%|█████▋ | 9/16 [00:01<00:01, 6.26it/s] 62%|██████▎ | 10/16 [00:01<00:00, 6.32it/s] 69%|██████▉ | 11/16 [00:01<00:00, 6.35it/s] 75%|███████▌ | 12/16 [00:02<00:00, 6.36it/s] 81%|████████▏ | 13/16 [00:02<00:00, 6.31it/s] 88%|████████▊ | 14/16 [00:02<00:00, 6.31it/s] 94%|█████████▍| 15/16 [00:02<00:00, 6.35it/s] 100%|██████████| 16/16 [00:02<00:00, 6.27it/s] 100%|██████████| 16/16 [00:02<00:00, 6.02it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:02, 6.79it/s] 12%|█▎ | 2/16 [00:00<00:02, 6.59it/s] 19%|█▉ | 3/16 [00:00<00:01, 6.52it/s] 25%|██▌ | 4/16 [00:00<00:01, 6.32it/s] 31%|███▏ | 5/16 [00:00<00:01, 6.36it/s] 38%|███▊ | 6/16 [00:00<00:01, 6.29it/s] 44%|████▍ | 7/16 [00:01<00:01, 6.24it/s] 50%|█████ | 8/16 [00:01<00:01, 6.29it/s] 56%|█████▋ | 9/16 [00:01<00:01, 6.31it/s] 62%|██████▎ | 10/16 [00:01<00:00, 6.32it/s] 69%|██████▉ | 11/16 [00:01<00:00, 6.36it/s] 75%|███████▌ | 12/16 [00:01<00:00, 6.34it/s] 81%|████████▏ | 13/16 [00:02<00:00, 6.31it/s] 88%|████████▊ | 14/16 [00:02<00:00, 6.31it/s] 94%|█████████▍| 15/16 [00:02<00:00, 6.30it/s] 100%|██████████| 16/16 [00:02<00:00, 6.32it/s] 100%|██████████| 16/16 [00:02<00:00, 6.34it/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 0.46s Move latents to cpu... done in 0.22s 0: 640x640 1 face, 7.3ms Speed: 2.8ms preprocess, 7.3ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:02, 6.82it/s] 12%|█▎ | 2/16 [00:00<00:02, 6.61it/s] 19%|█▉ | 3/16 [00:00<00:01, 6.53it/s] 25%|██▌ | 4/16 [00:00<00:01, 6.49it/s] 31%|███▏ | 5/16 [00:00<00:01, 6.48it/s] 38%|███▊ | 6/16 [00:00<00:01, 6.38it/s] 44%|████▍ | 7/16 [00:01<00:01, 6.31it/s] 50%|█████ | 8/16 [00:01<00:01, 6.31it/s] 56%|█████▋ | 9/16 [00:01<00:01, 6.34it/s] 62%|██████▎ | 10/16 [00:01<00:00, 6.30it/s] 69%|██████▉ | 11/16 [00:01<00:00, 6.37it/s] 75%|███████▌ | 12/16 [00:01<00:00, 6.29it/s] 81%|████████▏ | 13/16 [00:02<00:00, 6.23it/s] 88%|████████▊ | 14/16 [00:02<00:00, 6.25it/s] 94%|█████████▍| 15/16 [00:02<00:00, 6.27it/s] 100%|██████████| 16/16 [00:02<00:00, 6.30it/s] 100%|██████████| 16/16 [00:02<00:00, 6.35it/s] Decoding latents in cuda:0... done in 0.41s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:02, 6.73it/s] 12%|█▎ | 2/16 [00:00<00:02, 6.52it/s] 19%|█▉ | 3/16 [00:00<00:02, 6.47it/s] 25%|██▌ | 4/16 [00:00<00:01, 6.45it/s] 31%|███▏ | 5/16 [00:00<00:01, 6.45it/s] 38%|███▊ | 6/16 [00:00<00:01, 6.20it/s] 44%|████▍ | 7/16 [00:01<00:01, 6.16it/s] 50%|█████ | 8/16 [00:01<00:01, 6.21it/s] 56%|█████▋ | 9/16 [00:01<00:01, 6.27it/s] 62%|██████▎ | 10/16 [00:01<00:00, 6.31it/s] 69%|██████▉ | 11/16 [00:01<00:00, 6.32it/s] 75%|███████▌ | 12/16 [00:01<00:00, 6.28it/s] 81%|████████▏ | 13/16 [00:02<00:00, 6.24it/s] 88%|████████▊ | 14/16 [00:02<00:00, 6.26it/s] 94%|█████████▍| 15/16 [00:02<00:00, 6.29it/s] 100%|██████████| 16/16 [00:02<00:00, 6.33it/s] 100%|██████████| 16/16 [00:02<00:00, 6.32it/s] Decoding latents in cuda:0... done in 0.41s Move latents to cpu... done in 0.0s Finished.
prompt
Specify things to see in the output
(masterpiece, best quality:1.2), (1man, masculine adult male:1.2), turquoise eyes, dark brown hair, shaved head, focus on character, solo, (style-rustmagic:0.8), solo, from front, front view, half shot, detailed face, wild engineer, tentative trust, standing tall, dark red ornate robe, cape, brandishing forbidden mace of thunder, manifesting ethereal strands of power, color-changing surfaces responding to the environment, long-healed scars, <lora:more_details:0.8>
negative_prompt
Specify things to not see in the output
(human face), FastNegativeV2, (By bad artist -neg: 1), (worst quality, low quality: 1.4), (bad_prompt_version2: 0.8), lowres, bad anatomy, bad hands, ((text)), (watermark), error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, ((username)), blurry, (extra limbs), ng_deepnegative_v1_75t, (three hands: 1.3), (three legs: 1.2), (more than two hands: 1.3), (more than two legs: 1.2), label, watermark.
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
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
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.
2659002561
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
28
cfg_scale
Scale for classifier-free guidance
9.5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
blessed2_fp16.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
more_details.safetensors
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
ExoticDance.safetensors
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)
FastNegativeV2.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
By bad artist -neg.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
ng_deepnegative_v1_75t.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/5f1da5a27de742ff99b38b7f1031d04c/00000-2659002561.webp
https://files.tungsten.run/uploads/234f372081c7405b83f2edc238b642c4/00001-2659002562.webp
https://files.tungsten.run/uploads/4c60cc148516499faa393b76333e95f7/00002-2659002563.webp
https://files.tungsten.run/uploads/b0e329ce44174e368bbfcabb8aa7da73/00003-2659002564.webp
Finished in 47.1 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (masterpiece, best quality:1.2), (1man, masculine adult male:1.2), turquoise eyes, dark brown hair, shaved head, focus on character, solo, (style-rustmagic:0.8), solo, from front, front view, half shot, detailed face, wild engineer, tentative trust, standing tall, dark red ornate robe, cape, brandishing forbidden mace of thunder, manifesting ethereal strands of power, color-changing surfaces responding to the environment, long-healed scars, <lora:more_details:0.8> Full negative prompt: (human face), FastNegativeV2, (By bad artist -neg: 1), (worst quality, low quality: 1.4), (bad_prompt_version2: 0.8), lowres, bad anatomy, bad hands, ((text)), (watermark), error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, ((username)), blurry, (extra limbs), ng_deepnegative_v1_75t, (three hands: 1.3), (three legs: 1.2), (more than two hands: 1.3), (more than two legs: 1.2), label, watermark. 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:32, 1.20s/it] 7%|▋ | 2/28 [00:01<00:23, 1.13it/s] 11%|█ | 3/28 [00:02<00:19, 1.28it/s] 14%|█▍ | 4/28 [00:03<00:17, 1.35it/s] 18%|█▊ | 5/28 [00:03<00:16, 1.41it/s] 21%|██▏ | 6/28 [00:04<00:15, 1.44it/s] 25%|██▌ | 7/28 [00:05<00:14, 1.45it/s] 29%|██▊ | 8/28 [00:05<00:13, 1.47it/s] 32%|███▏ | 9/28 [00:06<00:12, 1.48it/s] 36%|███▌ | 10/28 [00:07<00:12, 1.48it/s] 39%|███▉ | 11/28 [00:07<00:11, 1.49it/s] 43%|████▎ | 12/28 [00:08<00:10, 1.49it/s] 46%|████▋ | 13/28 [00:09<00:10, 1.49it/s] 50%|█████ | 14/28 [00:09<00:09, 1.50it/s] 54%|█████▎ | 15/28 [00:10<00:08, 1.50it/s] 57%|█████▋ | 16/28 [00:11<00:08, 1.50it/s] 61%|██████ | 17/28 [00:11<00:07, 1.50it/s] 64%|██████▍ | 18/28 [00:12<00:06, 1.50it/s] 68%|██████▊ | 19/28 [00:13<00:06, 1.50it/s] 71%|███████▏ | 20/28 [00:13<00:05, 1.50it/s] 75%|███████▌ | 21/28 [00:14<00:04, 1.50it/s] 79%|███████▊ | 22/28 [00:15<00:04, 1.49it/s] 82%|████████▏ | 23/28 [00:15<00:03, 1.49it/s] 86%|████████▌ | 24/28 [00:16<00:02, 1.49it/s] 89%|████████▉ | 25/28 [00:17<00:02, 1.50it/s] 93%|█████████▎| 26/28 [00:17<00:01, 1.49it/s] 96%|█████████▋| 27/28 [00:18<00:00, 1.49it/s] 100%|██████████| 28/28 [00:19<00:00, 1.49it/s] 100%|██████████| 28/28 [00:19<00:00, 1.46it/s] Decoding latents in cuda:0... done in 0.98s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.0ms Speed: 4.8ms preprocess, 8.0ms inference, 33.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:04, 3.39it/s] 12%|█▎ | 2/16 [00:00<00:02, 4.74it/s] 19%|█▉ | 3/16 [00:00<00:02, 5.34it/s] 25%|██▌ | 4/16 [00:00<00:02, 5.74it/s] 31%|███▏ | 5/16 [00:00<00:01, 5.99it/s] 38%|███▊ | 6/16 [00:01<00:01, 6.06it/s] 44%|████▍ | 7/16 [00:01<00:01, 6.09it/s] 50%|█████ | 8/16 [00:01<00:01, 6.17it/s] 56%|█████▋ | 9/16 [00:01<00:01, 6.26it/s] 62%|██████▎ | 10/16 [00:01<00:00, 6.32it/s] 69%|██████▉ | 11/16 [00:01<00:00, 6.35it/s] 75%|███████▌ | 12/16 [00:02<00:00, 6.36it/s] 81%|████████▏ | 13/16 [00:02<00:00, 6.31it/s] 88%|████████▊ | 14/16 [00:02<00:00, 6.31it/s] 94%|█████████▍| 15/16 [00:02<00:00, 6.35it/s] 100%|██████████| 16/16 [00:02<00:00, 6.27it/s] 100%|██████████| 16/16 [00:02<00:00, 6.02it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:02, 6.79it/s] 12%|█▎ | 2/16 [00:00<00:02, 6.59it/s] 19%|█▉ | 3/16 [00:00<00:01, 6.52it/s] 25%|██▌ | 4/16 [00:00<00:01, 6.32it/s] 31%|███▏ | 5/16 [00:00<00:01, 6.36it/s] 38%|███▊ | 6/16 [00:00<00:01, 6.29it/s] 44%|████▍ | 7/16 [00:01<00:01, 6.24it/s] 50%|█████ | 8/16 [00:01<00:01, 6.29it/s] 56%|█████▋ | 9/16 [00:01<00:01, 6.31it/s] 62%|██████▎ | 10/16 [00:01<00:00, 6.32it/s] 69%|██████▉ | 11/16 [00:01<00:00, 6.36it/s] 75%|███████▌ | 12/16 [00:01<00:00, 6.34it/s] 81%|████████▏ | 13/16 [00:02<00:00, 6.31it/s] 88%|████████▊ | 14/16 [00:02<00:00, 6.31it/s] 94%|█████████▍| 15/16 [00:02<00:00, 6.30it/s] 100%|██████████| 16/16 [00:02<00:00, 6.32it/s] 100%|██████████| 16/16 [00:02<00:00, 6.34it/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 0.46s Move latents to cpu... done in 0.22s 0: 640x640 1 face, 7.3ms Speed: 2.8ms preprocess, 7.3ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:02, 6.82it/s] 12%|█▎ | 2/16 [00:00<00:02, 6.61it/s] 19%|█▉ | 3/16 [00:00<00:01, 6.53it/s] 25%|██▌ | 4/16 [00:00<00:01, 6.49it/s] 31%|███▏ | 5/16 [00:00<00:01, 6.48it/s] 38%|███▊ | 6/16 [00:00<00:01, 6.38it/s] 44%|████▍ | 7/16 [00:01<00:01, 6.31it/s] 50%|█████ | 8/16 [00:01<00:01, 6.31it/s] 56%|█████▋ | 9/16 [00:01<00:01, 6.34it/s] 62%|██████▎ | 10/16 [00:01<00:00, 6.30it/s] 69%|██████▉ | 11/16 [00:01<00:00, 6.37it/s] 75%|███████▌ | 12/16 [00:01<00:00, 6.29it/s] 81%|████████▏ | 13/16 [00:02<00:00, 6.23it/s] 88%|████████▊ | 14/16 [00:02<00:00, 6.25it/s] 94%|█████████▍| 15/16 [00:02<00:00, 6.27it/s] 100%|██████████| 16/16 [00:02<00:00, 6.30it/s] 100%|██████████| 16/16 [00:02<00:00, 6.35it/s] Decoding latents in cuda:0... done in 0.41s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:02, 6.73it/s] 12%|█▎ | 2/16 [00:00<00:02, 6.52it/s] 19%|█▉ | 3/16 [00:00<00:02, 6.47it/s] 25%|██▌ | 4/16 [00:00<00:01, 6.45it/s] 31%|███▏ | 5/16 [00:00<00:01, 6.45it/s] 38%|███▊ | 6/16 [00:00<00:01, 6.20it/s] 44%|████▍ | 7/16 [00:01<00:01, 6.16it/s] 50%|█████ | 8/16 [00:01<00:01, 6.21it/s] 56%|█████▋ | 9/16 [00:01<00:01, 6.27it/s] 62%|██████▎ | 10/16 [00:01<00:00, 6.31it/s] 69%|██████▉ | 11/16 [00:01<00:00, 6.32it/s] 75%|███████▌ | 12/16 [00:01<00:00, 6.28it/s] 81%|████████▏ | 13/16 [00:02<00:00, 6.24it/s] 88%|████████▊ | 14/16 [00:02<00:00, 6.26it/s] 94%|█████████▍| 15/16 [00:02<00:00, 6.29it/s] 100%|██████████| 16/16 [00:02<00:00, 6.33it/s] 100%|██████████| 16/16 [00:02<00:00, 6.32it/s] Decoding latents in cuda:0... done in 0.41s Move latents to cpu... done in 0.0s Finished.