tungsten-logo
Sign In
Afroamerican Men with Kamikun Mix
kamikun-mix:v1.1
evevalentine2017
evevalentine2017
·
12/27/2023
381
Input
prompt
Specify things to see in the output
(masterpiece, best quality), RAW photo, semi-realistic illustration of a soldier,(black man:1.3),(topless:1.3), 1boy, muscular male, wearing backpack, medium shot, f1.8 bokeh, masterpiece, best quality, (dark skinned-male:1.3), sweat, (sweatpants), countryside, highres <lora:128dimTurbomaleV7_128:.25>, bulgerk-soft,realistic, volumetric light, glossy skin, shiny metal, <lora:add_detail:0.8>, <lora:FaceBeauty_qinglong_V3:1>
negative_prompt
Specify things to not see in the output
nsfw, nipples, topless, low quality, lowres, worst quality, normal quality, earth, land, oversized hairstyle, bad-image-v2-39000, By bad artist -neg, verybadimagenegative_v1.3
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
-0.1
brightness
Adjust brightness
0.4
contrast
Adjust contrast
-1.15
saturation
Adjust saturation
-0.47
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2039550196
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
Euler a
samping_steps
Number of denoising steps
35
cfg_scale
Scale for classifier-free guidance
8
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>
add_detail.safetensors
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
FaceBeauty_qinglong_V3.safetensors
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
128dimTurbomaleV7_128.safetensors
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-image-v2-39000.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)
verybadimagenegative_v1.3.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/6e0965272a7e4f8d8de974c6f02cb9f4/00000-2039550196.webp
https://files.tungsten.run/uploads/ff6a9b6d51ba4e4b915a1f606f90da01/00001-2039550197.webp
https://files.tungsten.run/uploads/a77421288b87451aad0f6e71bdfe6ab1/00002-2039550198.webp
https://files.tungsten.run/uploads/9fee1e924e3646d99b17415756e2ad27/00003-2039550199.webp
Finished in 57.4 seconds
v1.1: Pulling from evevalentine2017/kamikun-mix 578acb154839: Already exists ac65017cfc56: Already exists 146269b80f9c: Already exists b51bc62cc3ca: Already exists 4ba34dd48a55: Already exists 2c0d7edf2b4f: Already exists bd3aa092d934: Already exists a2a0b079260c: Already exists 48e8a1cea0b1: Already exists 607175607db9: Already exists 44762e60be28: Already exists d1e8a6995bc7: Already exists 8915fc22d7d8: Already exists e186b03af121: Already exists 4f4fb700ef54: Already exists 030de23c0760: Already exists 10651bd4d550: Pull complete c52da7519bc8: Pull complete 52343e265588: Pull complete Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (masterpiece, best quality), RAW photo, semi-realistic illustration of a soldier,(black man:1.3),(topless:1.3), 1boy, muscular male, wearing backpack, medium shot, f1.8 bokeh, masterpiece, best quality, (dark skinned-male:1.3), sweat, (sweatpants), countryside, highres <lora:128dimTurbomaleV7_128:.25>, bulgerk-soft,realistic, volumetric light, glossy skin, shiny metal, <lora:FaceBeauty_qinglong_V3:1>, <lora:add_detail:-0.1>, <lora:add_brightness:0.4>, <lora:contrast_slider_v10:-1.15>, <lora:add_saturation:-0.47> Full negative prompt: nsfw, nipples, topless, low quality, lowres, worst quality, normal quality, earth, land, oversized hairstyle, bad-image-v2-39000, By bad artist -neg, verybadimagenegative_v1.3 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:01<00:50, 1.48s/it] 6%|▌ | 2/35 [00:02<00:32, 1.03it/s] 9%|▊ | 3/35 [00:02<00:25, 1.24it/s] 11%|█▏ | 4/35 [00:03<00:22, 1.36it/s] 14%|█▍ | 5/35 [00:03<00:20, 1.45it/s] 17%|█▋ | 6/35 [00:04<00:19, 1.50it/s] 20%|██ | 7/35 [00:05<00:18, 1.54it/s] 23%|██▎ | 8/35 [00:05<00:17, 1.56it/s] 26%|██▌ | 9/35 [00:06<00:16, 1.58it/s] 29%|██▊ | 10/35 [00:07<00:15, 1.59it/s] 31%|███▏ | 11/35 [00:07<00:15, 1.58it/s] 34%|███▍ | 12/35 [00:08<00:14, 1.59it/s] 37%|███▋ | 13/35 [00:08<00:13, 1.60it/s] 40%|████ | 14/35 [00:09<00:13, 1.60it/s] 43%|████▎ | 15/35 [00:10<00:12, 1.61it/s] 46%|████▌ | 16/35 [00:10<00:11, 1.61it/s] 49%|████▊ | 17/35 [00:11<00:11, 1.61it/s] 51%|█████▏ | 18/35 [00:12<00:10, 1.61it/s] 54%|█████▍ | 19/35 [00:12<00:09, 1.61it/s] 57%|█████▋ | 20/35 [00:13<00:09, 1.62it/s] 60%|██████ | 21/35 [00:13<00:08, 1.61it/s] 63%|██████▎ | 22/35 [00:14<00:08, 1.61it/s] 66%|██████▌ | 23/35 [00:15<00:07, 1.61it/s] 69%|██████▊ | 24/35 [00:15<00:06, 1.61it/s] 71%|███████▏ | 25/35 [00:16<00:06, 1.61it/s] 74%|███████▍ | 26/35 [00:16<00:05, 1.61it/s] 77%|███████▋ | 27/35 [00:17<00:05, 1.60it/s] 80%|████████ | 28/35 [00:18<00:04, 1.60it/s] 83%|████████▎ | 29/35 [00:18<00:03, 1.60it/s] 86%|████████▌ | 30/35 [00:19<00:03, 1.60it/s] 89%|████████▊ | 31/35 [00:20<00:02, 1.60it/s] 91%|█████████▏| 32/35 [00:20<00:01, 1.60it/s] 94%|█████████▍| 33/35 [00:21<00:01, 1.60it/s] 97%|█████████▋| 34/35 [00:21<00:00, 1.60it/s] 100%|██████████| 35/35 [00:22<00:00, 1.62it/s] 100%|██████████| 35/35 [00:22<00:00, 1.55it/s] Decoding latents in cuda:0... done in 0.93s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.7ms preprocess, 7.8ms inference, 33.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:07, 2.61it/s] 10%|█ | 2/20 [00:00<00:04, 3.62it/s] 15%|█▌ | 3/20 [00:00<00:04, 4.12it/s] 20%|██ | 4/20 [00:01<00:03, 4.32it/s] 25%|██▌ | 5/20 [00:01<00:03, 4.49it/s] 30%|███ | 6/20 [00:01<00:03, 4.61it/s] 35%|███▌ | 7/20 [00:01<00:02, 4.71it/s] 40%|████ | 8/20 [00:01<00:02, 4.74it/s] 45%|████▌ | 9/20 [00:02<00:02, 4.66it/s] 50%|█████ | 10/20 [00:02<00:02, 4.73it/s] 55%|█████▌ | 11/20 [00:02<00:01, 4.80it/s] 60%|██████ | 12/20 [00:02<00:01, 4.84it/s] 65%|██████▌ | 13/20 [00:02<00:01, 4.87it/s] 70%|███████ | 14/20 [00:03<00:01, 4.73it/s] 75%|███████▌ | 15/20 [00:03<00:01, 4.79it/s] 80%|████████ | 16/20 [00:03<00:00, 4.81it/s] 85%|████████▌ | 17/20 [00:03<00:00, 4.86it/s] 90%|█████████ | 18/20 [00:03<00:00, 4.90it/s] 95%|█████████▌| 19/20 [00:04<00:00, 4.83it/s] 100%|██████████| 20/20 [00:04<00:00, 4.89it/s] 100%|██████████| 20/20 [00:04<00:00, 4.65it/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 0.43s Move latents to cpu... done in 0.22s 0: 640x640 1 face, 7.5ms Speed: 2.9ms preprocess, 7.5ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:04, 4.74it/s] 10%|█ | 2/20 [00:00<00:03, 4.78it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.72it/s] 20%|██ | 4/20 [00:00<00:03, 4.81it/s] 25%|██▌ | 5/20 [00:01<00:03, 4.88it/s] 30%|███ | 6/20 [00:01<00:02, 4.89it/s] 35%|███▌ | 7/20 [00:01<00:02, 4.76it/s] 40%|████ | 8/20 [00:01<00:02, 4.77it/s] 45%|████▌ | 9/20 [00:01<00:02, 4.83it/s] 50%|█████ | 10/20 [00:02<00:02, 4.87it/s] 55%|█████▌ | 11/20 [00:02<00:01, 4.90it/s] 60%|██████ | 12/20 [00:02<00:01, 4.77it/s] 65%|██████▌ | 13/20 [00:02<00:01, 4.82it/s] 70%|███████ | 14/20 [00:02<00:01, 4.87it/s] 75%|███████▌ | 15/20 [00:03<00:01, 4.89it/s] 80%|████████ | 16/20 [00:03<00:00, 4.90it/s] 85%|████████▌ | 17/20 [00:03<00:00, 4.79it/s] 90%|█████████ | 18/20 [00:03<00:00, 4.83it/s] 95%|█████████▌| 19/20 [00:03<00:00, 4.87it/s] 100%|██████████| 20/20 [00:04<00:00, 4.94it/s] 100%|██████████| 20/20 [00:04<00:00, 4.85it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 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%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:03, 4.87it/s] 10%|█ | 2/20 [00:00<00:03, 4.91it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.92it/s] 20%|██ | 4/20 [00:00<00:03, 4.94it/s] 25%|██▌ | 5/20 [00:01<00:03, 4.96it/s] 30%|███ | 6/20 [00:01<00:02, 4.76it/s] 35%|███▌ | 7/20 [00:01<00:02, 4.80it/s] 40%|████ | 8/20 [00:01<00:02, 4.84it/s] 45%|████▌ | 9/20 [00:01<00:02, 4.86it/s] 50%|█████ | 10/20 [00:02<00:02, 4.90it/s] 55%|█████▌ | 11/20 [00:02<00:01, 4.70it/s] 60%|██████ | 12/20 [00:02<00:01, 4.72it/s] 65%|██████▌ | 13/20 [00:02<00:01, 4.78it/s] 70%|███████ | 14/20 [00:02<00:01, 4.78it/s] 75%|███████▌ | 15/20 [00:03<00:01, 4.84it/s] 80%|████████ | 16/20 [00:03<00:00, 4.72it/s] 85%|████████▌ | 17/20 [00:03<00:00, 4.76it/s] 90%|█████████ | 18/20 [00:03<00:00, 4.81it/s] 95%|█████████▌| 19/20 [00:03<00:00, 4.85it/s] 100%|██████████| 20/20 [00:04<00:00, 4.92it/s] 100%|██████████| 20/20 [00:04<00:00, 4.83it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.2ms Speed: 2.8ms preprocess, 7.2ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:04, 4.44it/s] 10%|█ | 2/20 [00:00<00:03, 4.71it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.81it/s] 20%|██ | 4/20 [00:00<00:03, 4.85it/s] 25%|██▌ | 5/20 [00:01<00:03, 4.88it/s] 30%|███ | 6/20 [00:01<00:02, 4.80it/s] 35%|███▌ | 7/20 [00:01<00:02, 4.84it/s] 40%|████ | 8/20 [00:01<00:02, 4.88it/s] 45%|████▌ | 9/20 [00:01<00:02, 4.90it/s] 50%|█████ | 10/20 [00:02<00:02, 4.92it/s] 55%|█████▌ | 11/20 [00:02<00:01, 4.81it/s] 60%|██████ | 12/20 [00:02<00:01, 4.85it/s] 65%|██████▌ | 13/20 [00:02<00:01, 4.87it/s] 70%|███████ | 14/20 [00:02<00:01, 4.88it/s] 75%|███████▌ | 15/20 [00:03<00:01, 4.89it/s] 80%|████████ | 16/20 [00:03<00:00, 4.73it/s] 85%|████████▌ | 17/20 [00:03<00:00, 4.78it/s] 90%|█████████ | 18/20 [00:03<00:00, 4.82it/s] 95%|█████████▌| 19/20 [00:03<00:00, 4.85it/s] 100%|██████████| 20/20 [00:04<00:00, 4.91it/s] 100%|██████████| 20/20 [00:04<00:00, 4.85it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt
Specify things to see in the output
(masterpiece, best quality), RAW photo, semi-realistic illustration of a soldier,(black man:1.3),(topless:1.3), 1boy, muscular male, wearing backpack, medium shot, f1.8 bokeh, masterpiece, best quality, (dark skinned-male:1.3), sweat, (sweatpants), countryside, highres <lora:128dimTurbomaleV7_128:.25>, bulgerk-soft,realistic, volumetric light, glossy skin, shiny metal, <lora:add_detail:0.8>, <lora:FaceBeauty_qinglong_V3:1>
negative_prompt
Specify things to not see in the output
nsfw, nipples, topless, low quality, lowres, worst quality, normal quality, earth, land, oversized hairstyle, bad-image-v2-39000, By bad artist -neg, verybadimagenegative_v1.3
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
-0.1
brightness
Adjust brightness
0.4
contrast
Adjust contrast
-1.15
saturation
Adjust saturation
-0.47
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2039550196
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
Euler a
samping_steps
Number of denoising steps
35
cfg_scale
Scale for classifier-free guidance
8
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>
add_detail.safetensors
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
FaceBeauty_qinglong_V3.safetensors
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
128dimTurbomaleV7_128.safetensors
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-image-v2-39000.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)
verybadimagenegative_v1.3.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/6e0965272a7e4f8d8de974c6f02cb9f4/00000-2039550196.webp
https://files.tungsten.run/uploads/ff6a9b6d51ba4e4b915a1f606f90da01/00001-2039550197.webp
https://files.tungsten.run/uploads/a77421288b87451aad0f6e71bdfe6ab1/00002-2039550198.webp
https://files.tungsten.run/uploads/9fee1e924e3646d99b17415756e2ad27/00003-2039550199.webp
Finished in 57.4 seconds
v1.1: Pulling from evevalentine2017/kamikun-mix 578acb154839: Already exists ac65017cfc56: Already exists 146269b80f9c: Already exists b51bc62cc3ca: Already exists 4ba34dd48a55: Already exists 2c0d7edf2b4f: Already exists bd3aa092d934: Already exists a2a0b079260c: Already exists 48e8a1cea0b1: Already exists 607175607db9: Already exists 44762e60be28: Already exists d1e8a6995bc7: Already exists 8915fc22d7d8: Already exists e186b03af121: Already exists 4f4fb700ef54: Already exists 030de23c0760: Already exists 10651bd4d550: Pull complete c52da7519bc8: Pull complete 52343e265588: Pull complete Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (masterpiece, best quality), RAW photo, semi-realistic illustration of a soldier,(black man:1.3),(topless:1.3), 1boy, muscular male, wearing backpack, medium shot, f1.8 bokeh, masterpiece, best quality, (dark skinned-male:1.3), sweat, (sweatpants), countryside, highres <lora:128dimTurbomaleV7_128:.25>, bulgerk-soft,realistic, volumetric light, glossy skin, shiny metal, <lora:FaceBeauty_qinglong_V3:1>, <lora:add_detail:-0.1>, <lora:add_brightness:0.4>, <lora:contrast_slider_v10:-1.15>, <lora:add_saturation:-0.47> Full negative prompt: nsfw, nipples, topless, low quality, lowres, worst quality, normal quality, earth, land, oversized hairstyle, bad-image-v2-39000, By bad artist -neg, verybadimagenegative_v1.3 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:01<00:50, 1.48s/it] 6%|▌ | 2/35 [00:02<00:32, 1.03it/s] 9%|▊ | 3/35 [00:02<00:25, 1.24it/s] 11%|█▏ | 4/35 [00:03<00:22, 1.36it/s] 14%|█▍ | 5/35 [00:03<00:20, 1.45it/s] 17%|█▋ | 6/35 [00:04<00:19, 1.50it/s] 20%|██ | 7/35 [00:05<00:18, 1.54it/s] 23%|██▎ | 8/35 [00:05<00:17, 1.56it/s] 26%|██▌ | 9/35 [00:06<00:16, 1.58it/s] 29%|██▊ | 10/35 [00:07<00:15, 1.59it/s] 31%|███▏ | 11/35 [00:07<00:15, 1.58it/s] 34%|███▍ | 12/35 [00:08<00:14, 1.59it/s] 37%|███▋ | 13/35 [00:08<00:13, 1.60it/s] 40%|████ | 14/35 [00:09<00:13, 1.60it/s] 43%|████▎ | 15/35 [00:10<00:12, 1.61it/s] 46%|████▌ | 16/35 [00:10<00:11, 1.61it/s] 49%|████▊ | 17/35 [00:11<00:11, 1.61it/s] 51%|█████▏ | 18/35 [00:12<00:10, 1.61it/s] 54%|█████▍ | 19/35 [00:12<00:09, 1.61it/s] 57%|█████▋ | 20/35 [00:13<00:09, 1.62it/s] 60%|██████ | 21/35 [00:13<00:08, 1.61it/s] 63%|██████▎ | 22/35 [00:14<00:08, 1.61it/s] 66%|██████▌ | 23/35 [00:15<00:07, 1.61it/s] 69%|██████▊ | 24/35 [00:15<00:06, 1.61it/s] 71%|███████▏ | 25/35 [00:16<00:06, 1.61it/s] 74%|███████▍ | 26/35 [00:16<00:05, 1.61it/s] 77%|███████▋ | 27/35 [00:17<00:05, 1.60it/s] 80%|████████ | 28/35 [00:18<00:04, 1.60it/s] 83%|████████▎ | 29/35 [00:18<00:03, 1.60it/s] 86%|████████▌ | 30/35 [00:19<00:03, 1.60it/s] 89%|████████▊ | 31/35 [00:20<00:02, 1.60it/s] 91%|█████████▏| 32/35 [00:20<00:01, 1.60it/s] 94%|█████████▍| 33/35 [00:21<00:01, 1.60it/s] 97%|█████████▋| 34/35 [00:21<00:00, 1.60it/s] 100%|██████████| 35/35 [00:22<00:00, 1.62it/s] 100%|██████████| 35/35 [00:22<00:00, 1.55it/s] Decoding latents in cuda:0... done in 0.93s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.7ms preprocess, 7.8ms inference, 33.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:07, 2.61it/s] 10%|█ | 2/20 [00:00<00:04, 3.62it/s] 15%|█▌ | 3/20 [00:00<00:04, 4.12it/s] 20%|██ | 4/20 [00:01<00:03, 4.32it/s] 25%|██▌ | 5/20 [00:01<00:03, 4.49it/s] 30%|███ | 6/20 [00:01<00:03, 4.61it/s] 35%|███▌ | 7/20 [00:01<00:02, 4.71it/s] 40%|████ | 8/20 [00:01<00:02, 4.74it/s] 45%|████▌ | 9/20 [00:02<00:02, 4.66it/s] 50%|█████ | 10/20 [00:02<00:02, 4.73it/s] 55%|█████▌ | 11/20 [00:02<00:01, 4.80it/s] 60%|██████ | 12/20 [00:02<00:01, 4.84it/s] 65%|██████▌ | 13/20 [00:02<00:01, 4.87it/s] 70%|███████ | 14/20 [00:03<00:01, 4.73it/s] 75%|███████▌ | 15/20 [00:03<00:01, 4.79it/s] 80%|████████ | 16/20 [00:03<00:00, 4.81it/s] 85%|████████▌ | 17/20 [00:03<00:00, 4.86it/s] 90%|█████████ | 18/20 [00:03<00:00, 4.90it/s] 95%|█████████▌| 19/20 [00:04<00:00, 4.83it/s] 100%|██████████| 20/20 [00:04<00:00, 4.89it/s] 100%|██████████| 20/20 [00:04<00:00, 4.65it/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 0.43s Move latents to cpu... done in 0.22s 0: 640x640 1 face, 7.5ms Speed: 2.9ms preprocess, 7.5ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:04, 4.74it/s] 10%|█ | 2/20 [00:00<00:03, 4.78it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.72it/s] 20%|██ | 4/20 [00:00<00:03, 4.81it/s] 25%|██▌ | 5/20 [00:01<00:03, 4.88it/s] 30%|███ | 6/20 [00:01<00:02, 4.89it/s] 35%|███▌ | 7/20 [00:01<00:02, 4.76it/s] 40%|████ | 8/20 [00:01<00:02, 4.77it/s] 45%|████▌ | 9/20 [00:01<00:02, 4.83it/s] 50%|█████ | 10/20 [00:02<00:02, 4.87it/s] 55%|█████▌ | 11/20 [00:02<00:01, 4.90it/s] 60%|██████ | 12/20 [00:02<00:01, 4.77it/s] 65%|██████▌ | 13/20 [00:02<00:01, 4.82it/s] 70%|███████ | 14/20 [00:02<00:01, 4.87it/s] 75%|███████▌ | 15/20 [00:03<00:01, 4.89it/s] 80%|████████ | 16/20 [00:03<00:00, 4.90it/s] 85%|████████▌ | 17/20 [00:03<00:00, 4.79it/s] 90%|█████████ | 18/20 [00:03<00:00, 4.83it/s] 95%|█████████▌| 19/20 [00:03<00:00, 4.87it/s] 100%|██████████| 20/20 [00:04<00:00, 4.94it/s] 100%|██████████| 20/20 [00:04<00:00, 4.85it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 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%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:03, 4.87it/s] 10%|█ | 2/20 [00:00<00:03, 4.91it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.92it/s] 20%|██ | 4/20 [00:00<00:03, 4.94it/s] 25%|██▌ | 5/20 [00:01<00:03, 4.96it/s] 30%|███ | 6/20 [00:01<00:02, 4.76it/s] 35%|███▌ | 7/20 [00:01<00:02, 4.80it/s] 40%|████ | 8/20 [00:01<00:02, 4.84it/s] 45%|████▌ | 9/20 [00:01<00:02, 4.86it/s] 50%|█████ | 10/20 [00:02<00:02, 4.90it/s] 55%|█████▌ | 11/20 [00:02<00:01, 4.70it/s] 60%|██████ | 12/20 [00:02<00:01, 4.72it/s] 65%|██████▌ | 13/20 [00:02<00:01, 4.78it/s] 70%|███████ | 14/20 [00:02<00:01, 4.78it/s] 75%|███████▌ | 15/20 [00:03<00:01, 4.84it/s] 80%|████████ | 16/20 [00:03<00:00, 4.72it/s] 85%|████████▌ | 17/20 [00:03<00:00, 4.76it/s] 90%|█████████ | 18/20 [00:03<00:00, 4.81it/s] 95%|█████████▌| 19/20 [00:03<00:00, 4.85it/s] 100%|██████████| 20/20 [00:04<00:00, 4.92it/s] 100%|██████████| 20/20 [00:04<00:00, 4.83it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.2ms Speed: 2.8ms preprocess, 7.2ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:04, 4.44it/s] 10%|█ | 2/20 [00:00<00:03, 4.71it/s] 15%|█▌ | 3/20 [00:00<00:03, 4.81it/s] 20%|██ | 4/20 [00:00<00:03, 4.85it/s] 25%|██▌ | 5/20 [00:01<00:03, 4.88it/s] 30%|███ | 6/20 [00:01<00:02, 4.80it/s] 35%|███▌ | 7/20 [00:01<00:02, 4.84it/s] 40%|████ | 8/20 [00:01<00:02, 4.88it/s] 45%|████▌ | 9/20 [00:01<00:02, 4.90it/s] 50%|█████ | 10/20 [00:02<00:02, 4.92it/s] 55%|█████▌ | 11/20 [00:02<00:01, 4.81it/s] 60%|██████ | 12/20 [00:02<00:01, 4.85it/s] 65%|██████▌ | 13/20 [00:02<00:01, 4.87it/s] 70%|███████ | 14/20 [00:02<00:01, 4.88it/s] 75%|███████▌ | 15/20 [00:03<00:01, 4.89it/s] 80%|████████ | 16/20 [00:03<00:00, 4.73it/s] 85%|████████▌ | 17/20 [00:03<00:00, 4.78it/s] 90%|█████████ | 18/20 [00:03<00:00, 4.82it/s] 95%|█████████▌| 19/20 [00:03<00:00, 4.85it/s] 100%|██████████| 20/20 [00:04<00:00, 4.91it/s] 100%|██████████| 20/20 [00:04<00:00, 4.85it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s Uploading outputs... Finished.