kamikun-mix
kamikun-mix
3 stars
Version: v1.1
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
saturation
Adjust saturation
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
Output
https://files.tungsten.run/uploads/64dffe713c2f401492a45dd8076610d1/00000-655819473.webp
https://files.tungsten.run/uploads/49e06bcdd34d4ac59ff5be119f7a72fe/00001-655819474.webp
https://files.tungsten.run/uploads/52f114603aea41c48421394cc481a9e8/00002-655819475.webp
https://files.tungsten.run/uploads/b501b326bf46436ba8830d44b741e5c9/00003-655819476.webp
This example was created by evevalentine2017
Finished in 53.8 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (masterpiece, best quality), RAW photo, (masterpiece, best quality), 1girl, kimono, cute, shrine, shrine maiden, japanese, upperbody, 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:-1.71>, <lora:add_saturation:-0.88> 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<00:46, 1.36s/it] 6%|▌ | 2/35 [00:02<00:31, 1.04it/s] 9%|▊ | 3/35 [00:02<00:26, 1.20it/s] 11%|█▏ | 4/35 [00:03<00:24, 1.29it/s] 14%|█▍ | 5/35 [00:04<00:22, 1.35it/s] 17%|█▋ | 6/35 [00:04<00:20, 1.39it/s] 20%|██ | 7/35 [00:05<00:19, 1.41it/s] 23%|██▎ | 8/35 [00:06<00:18, 1.42it/s] 26%|██▌ | 9/35 [00:06<00:18, 1.43it/s] 29%|██▊ | 10/35 [00:07<00:17, 1.44it/s] 31%|███▏ | 11/35 [00:08<00:16, 1.44it/s] 34%|███▍ | 12/35 [00:08<00:15, 1.45it/s] 37%|███▋ | 13/35 [00:09<00:15, 1.45it/s] 40%|████ | 14/35 [00:10<00:14, 1.44it/s] 43%|████▎ | 15/35 [00:10<00:13, 1.45it/s] 46%|████▌ | 16/35 [00:11<00:13, 1.44it/s] 49%|████▊ | 17/35 [00:12<00:12, 1.44it/s] 51%|█████▏ | 18/35 [00:13<00:11, 1.45it/s] 54%|█████▍ | 19/35 [00:13<00:11, 1.45it/s] 57%|█████▋ | 20/35 [00:14<00:10, 1.45it/s] 60%|██████ | 21/35 [00:15<00:09, 1.45it/s] 63%|██████▎ | 22/35 [00:15<00:08, 1.45it/s] 66%|██████▌ | 23/35 [00:16<00:08, 1.44it/s] 69%|██████▊ | 24/35 [00:17<00:07, 1.44it/s] 71%|███████▏ | 25/35 [00:17<00:06, 1.44it/s] 74%|███████▍ | 26/35 [00:18<00:06, 1.44it/s] 77%|███████▋ | 27/35 [00:19<00:05, 1.44it/s] 80%|████████ | 28/35 [00:19<00:04, 1.44it/s] 83%|████████▎ | 29/35 [00:20<00:04, 1.44it/s] 86%|████████▌ | 30/35 [00:21<00:03, 1.44it/s] 89%|████████▊ | 31/35 [00:22<00:02, 1.44it/s] 91%|█████████▏| 32/35 [00:22<00:02, 1.43it/s] 94%|█████████▍| 33/35 [00:23<00:01, 1.43it/s] 97%|█████████▋| 34/35 [00:24<00:00, 1.43it/s] 100%|██████████| 35/35 [00:24<00:00, 1.44it/s] 100%|██████████| 35/35 [00:24<00:00, 1.41it/s] Decoding latents in cuda:0... done in 0.99s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.2ms Speed: 3.3ms preprocess, 8.2ms inference, 37.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:05, 3.43it/s] 10%|█ | 2/20 [00:00<00:03, 4.69it/s] 15%|█▌ | 3/20 [00:00<00:03, 5.29it/s] 20%|██ | 4/20 [00:00<00:02, 5.65it/s] 25%|██▌ | 5/20 [00:00<00:02, 5.73it/s] 30%|███ | 6/20 [00:01<00:02, 5.81it/s] 35%|███▌ | 7/20 [00:01<00:02, 5.89it/s] 40%|████ | 8/20 [00:01<00:02, 5.96it/s] 45%|████▌ | 9/20 [00:01<00:01, 6.06it/s] 50%|█████ | 10/20 [00:01<00:01, 6.12it/s] 55%|█████▌ | 11/20 [00:01<00:01, 6.16it/s] 60%|██████ | 12/20 [00:02<00:01, 6.14it/s] 65%|██████▌ | 13/20 [00:02<00:01, 6.14it/s] 70%|███████ | 14/20 [00:02<00:00, 6.11it/s] 75%|███████▌ | 15/20 [00:02<00:00, 6.13it/s] 80%|████████ | 16/20 [00:02<00:00, 6.16it/s] 85%|████████▌ | 17/20 [00:02<00:00, 6.18it/s] 90%|█████████ | 18/20 [00:03<00:00, 6.15it/s] 95%|█████████▌| 19/20 [00:03<00:00, 6.16it/s] 100%|██████████| 20/20 [00:03<00:00, 6.19it/s] 100%|██████████| 20/20 [00:03<00:00, 5.93it/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: 2.8ms preprocess, 7.5ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:02, 6.54it/s] 10%|█ | 2/20 [00:00<00:02, 6.37it/s] 15%|█▌ | 3/20 [00:00<00:02, 6.33it/s] 20%|██ | 4/20 [00:00<00:02, 6.29it/s] 25%|██▌ | 5/20 [00:00<00:02, 6.29it/s] 30%|███ | 6/20 [00:00<00:02, 6.22it/s] 35%|███▌ | 7/20 [00:01<00:02, 6.14it/s] 40%|████ | 8/20 [00:01<00:01, 6.13it/s] 45%|████▌ | 9/20 [00:01<00:01, 6.06it/s] 50%|█████ | 10/20 [00:01<00:01, 6.13it/s] 55%|█████▌ | 11/20 [00:01<00:01, 6.09it/s] 60%|██████ | 12/20 [00:01<00:01, 6.11it/s] 65%|██████▌ | 13/20 [00:02<00:01, 6.08it/s] 70%|███████ | 14/20 [00:02<00:00, 6.08it/s] 75%|███████▌ | 15/20 [00:02<00:00, 6.12it/s] 80%|████████ | 16/20 [00:02<00:00, 6.12it/s] 85%|████████▌ | 17/20 [00:02<00:00, 6.17it/s] 90%|█████████ | 18/20 [00:02<00:00, 6.18it/s] 95%|█████████▌| 19/20 [00:03<00:00, 6.16it/s] 100%|██████████| 20/20 [00:03<00:00, 6.19it/s] 100%|██████████| 20/20 [00:03<00:00, 6.17it/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: 3.4ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:02, 6.55it/s] 10%|█ | 2/20 [00:00<00:02, 6.39it/s] 15%|█▌ | 3/20 [00:00<00:02, 6.33it/s] 20%|██ | 4/20 [00:00<00:02, 6.18it/s] 25%|██▌ | 5/20 [00:00<00:02, 6.21it/s] 30%|███ | 6/20 [00:00<00:02, 6.15it/s] 35%|███▌ | 7/20 [00:01<00:02, 6.12it/s] 40%|████ | 8/20 [00:01<00:01, 6.13it/s] 45%|████▌ | 9/20 [00:01<00:01, 6.14it/s] 50%|█████ | 10/20 [00:01<00:01, 6.16it/s] 55%|█████▌ | 11/20 [00:01<00:01, 6.17it/s] 60%|██████ | 12/20 [00:01<00:01, 6.17it/s] 65%|██████▌ | 13/20 [00:02<00:01, 6.16it/s] 70%|███████ | 14/20 [00:02<00:00, 6.15it/s] 75%|███████▌ | 15/20 [00:02<00:00, 6.15it/s] 80%|████████ | 16/20 [00:02<00:00, 6.16it/s] 85%|████████▌ | 17/20 [00:02<00:00, 6.17it/s] 90%|█████████ | 18/20 [00:02<00:00, 6.12it/s] 95%|█████████▌| 19/20 [00:03<00:00, 6.09it/s] 100%|██████████| 20/20 [00:03<00:00, 6.19it/s] 100%|██████████| 20/20 [00:03<00:00, 6.17it/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: 2.6ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:02, 6.57it/s] 10%|█ | 2/20 [00:00<00:02, 6.42it/s] 15%|█▌ | 3/20 [00:00<00:02, 6.37it/s] 20%|██ | 4/20 [00:00<00:02, 6.34it/s] 25%|██▌ | 5/20 [00:00<00:02, 6.32it/s] 30%|███ | 6/20 [00:00<00:02, 6.23it/s] 35%|███▌ | 7/20 [00:01<00:02, 6.13it/s] 40%|████ | 8/20 [00:01<00:01, 6.16it/s] 45%|████▌ | 9/20 [00:01<00:01, 6.17it/s] 50%|█████ | 10/20 [00:01<00:01, 6.15it/s] 55%|█████▌ | 11/20 [00:01<00:01, 6.19it/s] 60%|██████ | 12/20 [00:01<00:01, 6.17it/s] 65%|██████▌ | 13/20 [00:02<00:01, 6.13it/s] 70%|███████ | 14/20 [00:02<00:00, 6.13it/s] 75%|███████▌ | 15/20 [00:02<00:00, 6.14it/s] 80%|████████ | 16/20 [00:02<00:00, 6.11it/s] 85%|████████▌ | 17/20 [00:02<00:00, 6.12it/s] 90%|█████████ | 18/20 [00:02<00:00, 6.10it/s] 95%|█████████▌| 19/20 [00:03<00:00, 6.10it/s] 100%|██████████| 20/20 [00:03<00:00, 6.16it/s] 100%|██████████| 20/20 [00:03<00:00, 6.18it/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
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
saturation
Adjust saturation
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
https://files.tungsten.run/uploads/64dffe713c2f401492a45dd8076610d1/00000-655819473.webp
https://files.tungsten.run/uploads/49e06bcdd34d4ac59ff5be119f7a72fe/00001-655819474.webp
https://files.tungsten.run/uploads/52f114603aea41c48421394cc481a9e8/00002-655819475.webp
https://files.tungsten.run/uploads/b501b326bf46436ba8830d44b741e5c9/00003-655819476.webp
This example was created by evevalentine2017
Finished in 53.8 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (masterpiece, best quality), RAW photo, (masterpiece, best quality), 1girl, kimono, cute, shrine, shrine maiden, japanese, upperbody, 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:-1.71>, <lora:add_saturation:-0.88> 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<00:46, 1.36s/it] 6%|▌ | 2/35 [00:02<00:31, 1.04it/s] 9%|▊ | 3/35 [00:02<00:26, 1.20it/s] 11%|█▏ | 4/35 [00:03<00:24, 1.29it/s] 14%|█▍ | 5/35 [00:04<00:22, 1.35it/s] 17%|█▋ | 6/35 [00:04<00:20, 1.39it/s] 20%|██ | 7/35 [00:05<00:19, 1.41it/s] 23%|██▎ | 8/35 [00:06<00:18, 1.42it/s] 26%|██▌ | 9/35 [00:06<00:18, 1.43it/s] 29%|██▊ | 10/35 [00:07<00:17, 1.44it/s] 31%|███▏ | 11/35 [00:08<00:16, 1.44it/s] 34%|███▍ | 12/35 [00:08<00:15, 1.45it/s] 37%|███▋ | 13/35 [00:09<00:15, 1.45it/s] 40%|████ | 14/35 [00:10<00:14, 1.44it/s] 43%|████▎ | 15/35 [00:10<00:13, 1.45it/s] 46%|████▌ | 16/35 [00:11<00:13, 1.44it/s] 49%|████▊ | 17/35 [00:12<00:12, 1.44it/s] 51%|█████▏ | 18/35 [00:13<00:11, 1.45it/s] 54%|█████▍ | 19/35 [00:13<00:11, 1.45it/s] 57%|█████▋ | 20/35 [00:14<00:10, 1.45it/s] 60%|██████ | 21/35 [00:15<00:09, 1.45it/s] 63%|██████▎ | 22/35 [00:15<00:08, 1.45it/s] 66%|██████▌ | 23/35 [00:16<00:08, 1.44it/s] 69%|██████▊ | 24/35 [00:17<00:07, 1.44it/s] 71%|███████▏ | 25/35 [00:17<00:06, 1.44it/s] 74%|███████▍ | 26/35 [00:18<00:06, 1.44it/s] 77%|███████▋ | 27/35 [00:19<00:05, 1.44it/s] 80%|████████ | 28/35 [00:19<00:04, 1.44it/s] 83%|████████▎ | 29/35 [00:20<00:04, 1.44it/s] 86%|████████▌ | 30/35 [00:21<00:03, 1.44it/s] 89%|████████▊ | 31/35 [00:22<00:02, 1.44it/s] 91%|█████████▏| 32/35 [00:22<00:02, 1.43it/s] 94%|█████████▍| 33/35 [00:23<00:01, 1.43it/s] 97%|█████████▋| 34/35 [00:24<00:00, 1.43it/s] 100%|██████████| 35/35 [00:24<00:00, 1.44it/s] 100%|██████████| 35/35 [00:24<00:00, 1.41it/s] Decoding latents in cuda:0... done in 0.99s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 8.2ms Speed: 3.3ms preprocess, 8.2ms inference, 37.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:05, 3.43it/s] 10%|█ | 2/20 [00:00<00:03, 4.69it/s] 15%|█▌ | 3/20 [00:00<00:03, 5.29it/s] 20%|██ | 4/20 [00:00<00:02, 5.65it/s] 25%|██▌ | 5/20 [00:00<00:02, 5.73it/s] 30%|███ | 6/20 [00:01<00:02, 5.81it/s] 35%|███▌ | 7/20 [00:01<00:02, 5.89it/s] 40%|████ | 8/20 [00:01<00:02, 5.96it/s] 45%|████▌ | 9/20 [00:01<00:01, 6.06it/s] 50%|█████ | 10/20 [00:01<00:01, 6.12it/s] 55%|█████▌ | 11/20 [00:01<00:01, 6.16it/s] 60%|██████ | 12/20 [00:02<00:01, 6.14it/s] 65%|██████▌ | 13/20 [00:02<00:01, 6.14it/s] 70%|███████ | 14/20 [00:02<00:00, 6.11it/s] 75%|███████▌ | 15/20 [00:02<00:00, 6.13it/s] 80%|████████ | 16/20 [00:02<00:00, 6.16it/s] 85%|████████▌ | 17/20 [00:02<00:00, 6.18it/s] 90%|█████████ | 18/20 [00:03<00:00, 6.15it/s] 95%|█████████▌| 19/20 [00:03<00:00, 6.16it/s] 100%|██████████| 20/20 [00:03<00:00, 6.19it/s] 100%|██████████| 20/20 [00:03<00:00, 5.93it/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: 2.8ms preprocess, 7.5ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:02, 6.54it/s] 10%|█ | 2/20 [00:00<00:02, 6.37it/s] 15%|█▌ | 3/20 [00:00<00:02, 6.33it/s] 20%|██ | 4/20 [00:00<00:02, 6.29it/s] 25%|██▌ | 5/20 [00:00<00:02, 6.29it/s] 30%|███ | 6/20 [00:00<00:02, 6.22it/s] 35%|███▌ | 7/20 [00:01<00:02, 6.14it/s] 40%|████ | 8/20 [00:01<00:01, 6.13it/s] 45%|████▌ | 9/20 [00:01<00:01, 6.06it/s] 50%|█████ | 10/20 [00:01<00:01, 6.13it/s] 55%|█████▌ | 11/20 [00:01<00:01, 6.09it/s] 60%|██████ | 12/20 [00:01<00:01, 6.11it/s] 65%|██████▌ | 13/20 [00:02<00:01, 6.08it/s] 70%|███████ | 14/20 [00:02<00:00, 6.08it/s] 75%|███████▌ | 15/20 [00:02<00:00, 6.12it/s] 80%|████████ | 16/20 [00:02<00:00, 6.12it/s] 85%|████████▌ | 17/20 [00:02<00:00, 6.17it/s] 90%|█████████ | 18/20 [00:02<00:00, 6.18it/s] 95%|█████████▌| 19/20 [00:03<00:00, 6.16it/s] 100%|██████████| 20/20 [00:03<00:00, 6.19it/s] 100%|██████████| 20/20 [00:03<00:00, 6.17it/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: 3.4ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:02, 6.55it/s] 10%|█ | 2/20 [00:00<00:02, 6.39it/s] 15%|█▌ | 3/20 [00:00<00:02, 6.33it/s] 20%|██ | 4/20 [00:00<00:02, 6.18it/s] 25%|██▌ | 5/20 [00:00<00:02, 6.21it/s] 30%|███ | 6/20 [00:00<00:02, 6.15it/s] 35%|███▌ | 7/20 [00:01<00:02, 6.12it/s] 40%|████ | 8/20 [00:01<00:01, 6.13it/s] 45%|████▌ | 9/20 [00:01<00:01, 6.14it/s] 50%|█████ | 10/20 [00:01<00:01, 6.16it/s] 55%|█████▌ | 11/20 [00:01<00:01, 6.17it/s] 60%|██████ | 12/20 [00:01<00:01, 6.17it/s] 65%|██████▌ | 13/20 [00:02<00:01, 6.16it/s] 70%|███████ | 14/20 [00:02<00:00, 6.15it/s] 75%|███████▌ | 15/20 [00:02<00:00, 6.15it/s] 80%|████████ | 16/20 [00:02<00:00, 6.16it/s] 85%|████████▌ | 17/20 [00:02<00:00, 6.17it/s] 90%|█████████ | 18/20 [00:02<00:00, 6.12it/s] 95%|█████████▌| 19/20 [00:03<00:00, 6.09it/s] 100%|██████████| 20/20 [00:03<00:00, 6.19it/s] 100%|██████████| 20/20 [00:03<00:00, 6.17it/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: 2.6ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:02, 6.57it/s] 10%|█ | 2/20 [00:00<00:02, 6.42it/s] 15%|█▌ | 3/20 [00:00<00:02, 6.37it/s] 20%|██ | 4/20 [00:00<00:02, 6.34it/s] 25%|██▌ | 5/20 [00:00<00:02, 6.32it/s] 30%|███ | 6/20 [00:00<00:02, 6.23it/s] 35%|███▌ | 7/20 [00:01<00:02, 6.13it/s] 40%|████ | 8/20 [00:01<00:01, 6.16it/s] 45%|████▌ | 9/20 [00:01<00:01, 6.17it/s] 50%|█████ | 10/20 [00:01<00:01, 6.15it/s] 55%|█████▌ | 11/20 [00:01<00:01, 6.19it/s] 60%|██████ | 12/20 [00:01<00:01, 6.17it/s] 65%|██████▌ | 13/20 [00:02<00:01, 6.13it/s] 70%|███████ | 14/20 [00:02<00:00, 6.13it/s] 75%|███████▌ | 15/20 [00:02<00:00, 6.14it/s] 80%|████████ | 16/20 [00:02<00:00, 6.11it/s] 85%|████████▌ | 17/20 [00:02<00:00, 6.12it/s] 90%|█████████ | 18/20 [00:02<00:00, 6.10it/s] 95%|█████████▌| 19/20 [00:03<00:00, 6.10it/s] 100%|██████████| 20/20 [00:03<00:00, 6.16it/s] 100%|██████████| 20/20 [00:03<00:00, 6.18it/s] Decoding latents in cuda:0... done in 0.42s Move latents to cpu... done in 0.0s Uploading outputs... Finished.