tungsten-logo
Sign In
realvision-xl
realvision-xl

realvision-xl

7 stars
Version: v3.0
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
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/60ed0843a3a943f39b65b25aa1f8f097/00000-868093862.webp
https://files.tungsten.run/uploads/50683856fe6243f9bdfb043621f8057e/00001-868093863.webp
https://files.tungsten.run/uploads/39350c0573134c40a0d33d72680883e7/00002-868093864.webp
This example was created by evevalentine2017
Finished in 299.2 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: a strong 28-year-old senegalese powerlifter bodybuilder male , with short military haircut, glazed face, mindless expression, wearing a robotic suit, wearing a skin tight black latex robotic suit with gray latex details, standing at attention posture, on a modern futuristic street, looking to the camera, detailed face, Cinematic, Photoshoot, Shot on 25mm lens, Depth of Field, Tilt Blur, Shutter Speed 1/1000, F/22, White Balance, 32k, Super-Resolution, Pro Photo RGB, Half rear Lighting, Backlight, Dramatic Lighting, Incandescent, Soft Lighting, Volumetric, Conte-Jour, Global Illumination, Screen Space Global Illumination, Scattering, Shadows, Rough, Shimmering, Lumen Reflections, Screen Space Reflections, Diffraction Grading, Chromatic Aberration, GB Displacement, Scan Lines, Ambient Occlusion, Anti-Aliasing, FKAA, TXAA, RTX, SSAO, OpenGL-Shader, Post Processing, Post-Production, Cell Shading, Tone Mapping, CGI, VFX, SFX, insanely detailed and intricate, hyper maximalist, elegant, dynamic pose, photography, volumetric, ultra-detailed, intricate details, super detailed, ambient Full negative prompt: worst quality, extra fingers, missing fingers, poorly rendered hands, mutation, deformed iris, deformed pupils, deformed limbs, missing limbs, amputee, amputated limbs, watermark, logo , text, piercing, big eyes , teeth, cartoon, shallow depth of field, makeup 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:04<02:00, 4.02s/it] 6%|▋ | 2/31 [00:09<02:16, 4.71s/it] 10%|▉ | 3/31 [00:14<02:21, 5.07s/it] 13%|█▎ | 4/31 [00:20<02:20, 5.20s/it] 16%|█▌ | 5/31 [00:25<02:14, 5.19s/it] 19%|█▉ | 6/31 [00:30<02:11, 5.27s/it] 23%|██▎ | 7/31 [00:36<02:07, 5.29s/it] 26%|██▌ | 8/31 [00:41<02:02, 5.31s/it] 29%|██▉ | 9/31 [00:46<01:56, 5.28s/it] 32%|███▏ | 10/31 [00:52<01:55, 5.48s/it] 35%|███▌ | 11/31 [00:57<01:47, 5.38s/it] 39%|███▊ | 12/31 [01:03<01:42, 5.37s/it] 42%|████▏ | 13/31 [01:08<01:35, 5.31s/it] 45%|████▌ | 14/31 [01:13<01:30, 5.32s/it] 48%|████▊ | 15/31 [01:18<01:23, 5.19s/it] 52%|█████▏ | 16/31 [01:23<01:17, 5.16s/it] 55%|█████▍ | 17/31 [01:28<01:12, 5.16s/it] 58%|█████▊ | 18/31 [01:32<01:03, 4.86s/it] 61%|██████▏ | 19/31 [01:37<00:58, 4.84s/it] 65%|██████▍ | 20/31 [01:42<00:53, 4.90s/it] 68%|██████▊ | 21/31 [01:47<00:49, 4.91s/it] 71%|███████ | 22/31 [01:52<00:44, 4.91s/it] 74%|███████▍ | 23/31 [01:58<00:41, 5.21s/it] 77%|███████▋ | 24/31 [02:02<00:34, 4.95s/it] 81%|████████ | 25/31 [02:07<00:30, 5.02s/it] 84%|████████▍ | 26/31 [02:11<00:23, 4.67s/it] 87%|████████▋ | 27/31 [02:15<00:17, 4.46s/it] 90%|█████████ | 28/31 [02:19<00:13, 4.36s/it] 94%|█████████▎| 29/31 [02:24<00:08, 4.45s/it] 97%|█████████▋| 30/31 [02:27<00:04, 4.10s/it] 100%|██████████| 31/31 [02:29<00:00, 3.24s/it] 100%|██████████| 31/31 [02:29<00:00, 4.81s/it] Decoding latents in cuda:0... done in 2.34s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 20.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:02<00:26, 2.06s/it] 14%|█▍ | 2/14 [00:04<00:24, 2.01s/it] 21%|██▏ | 3/14 [00:06<00:22, 2.07s/it] 29%|██▊ | 4/14 [00:08<00:21, 2.16s/it] 36%|███▌ | 5/14 [00:10<00:19, 2.16s/it] 43%|████▎ | 6/14 [00:12<00:17, 2.15s/it] 50%|█████ | 7/14 [00:14<00:14, 2.01s/it] 57%|█████▋ | 8/14 [00:16<00:12, 2.01s/it] 64%|██████▍ | 9/14 [00:18<00:09, 1.91s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.85s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.82s/it] 86%|████████▌ | 12/14 [00:23<00:03, 1.87s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.76s/it] 100%|██████████| 14/14 [00:25<00:00, 1.42s/it] 100%|██████████| 14/14 [00:25<00:00, 1.84s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 12.9ms Speed: 4.6ms preprocess, 12.9ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.5ms Speed: 3.0ms preprocess, 7.5ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:24, 1.86s/it] 14%|█▍ | 2/14 [00:03<00:24, 2.02s/it] 21%|██▏ | 3/14 [00:06<00:22, 2.05s/it] 29%|██▊ | 4/14 [00:08<00:20, 2.05s/it] 36%|███▌ | 5/14 [00:10<00:18, 2.07s/it] 43%|████▎ | 6/14 [00:12<00:16, 2.09s/it] 50%|█████ | 7/14 [00:14<00:13, 1.96s/it] 57%|█████▋ | 8/14 [00:16<00:12, 2.01s/it] 64%|██████▍ | 9/14 [00:17<00:09, 1.91s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.87s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.91s/it] 86%|████████▌ | 12/14 [00:23<00:03, 1.97s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.87s/it] 100%|██████████| 14/14 [00:26<00:00, 1.51s/it] 100%|██████████| 14/14 [00:26<00:00, 1.86s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.5ms Speed: 3.6ms preprocess, 7.5ms inference, 2.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:24, 1.89s/it] 14%|█▍ | 2/14 [00:03<00:23, 1.97s/it] 21%|██▏ | 3/14 [00:05<00:22, 2.01s/it] 29%|██▊ | 4/14 [00:08<00:20, 2.05s/it] 36%|███▌ | 5/14 [00:10<00:18, 2.11s/it] 43%|████▎ | 6/14 [00:12<00:17, 2.14s/it] 50%|█████ | 7/14 [00:14<00:14, 2.03s/it] 57%|█████▋ | 8/14 [00:16<00:12, 2.02s/it] 64%|██████▍ | 9/14 [00:18<00:09, 1.92s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.87s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.84s/it] 86%|████████▌ | 12/14 [00:23<00:03, 1.88s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.77s/it] 100%|██████████| 14/14 [00:25<00:00, 1.42s/it] 100%|██████████| 14/14 [00:25<00:00, 1.83s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:23, 1.81s/it] 14%|█▍ | 2/14 [00:03<00:22, 1.91s/it] 21%|██▏ | 3/14 [00:05<00:21, 1.98s/it] 29%|██▊ | 4/14 [00:07<00:20, 2.01s/it] 36%|███▌ | 5/14 [00:09<00:18, 2.03s/it] 43%|████▎ | 6/14 [00:12<00:16, 2.07s/it] 50%|█████ | 7/14 [00:13<00:13, 1.97s/it] 57%|█████▋ | 8/14 [00:15<00:11, 2.00s/it] 64%|██████▍ | 9/14 [00:17<00:09, 1.92s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.88s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.88s/it] 86%|████████▌ | 12/14 [00:23<00:04, 2.02s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.86s/it] 100%|██████████| 14/14 [00:25<00:00, 1.49s/it] 100%|██████████| 14/14 [00:25<00:00, 1.84s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.1ms preprocess, 7.4ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:23, 1.81s/it] 14%|█▍ | 2/14 [00:03<00:23, 1.97s/it] 21%|██▏ | 3/14 [00:06<00:23, 2.14s/it] 29%|██▊ | 4/14 [00:08<00:21, 2.20s/it] 36%|███▌ | 5/14 [00:10<00:19, 2.15s/it] 43%|████▎ | 6/14 [00:12<00:17, 2.13s/it] 50%|█████ | 7/14 [00:14<00:13, 1.99s/it] 57%|█████▋ | 8/14 [00:16<00:11, 1.98s/it] 64%|██████▍ | 9/14 [00:18<00:09, 1.90s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.85s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.83s/it] 86%|████████▌ | 12/14 [00:23<00:03, 1.87s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.76s/it] 100%|██████████| 14/14 [00:25<00:00, 1.41s/it] 100%|██████████| 14/14 [00:25<00:00, 1.83s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.3ms preprocess, 7.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. 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
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/60ed0843a3a943f39b65b25aa1f8f097/00000-868093862.webp
https://files.tungsten.run/uploads/50683856fe6243f9bdfb043621f8057e/00001-868093863.webp
https://files.tungsten.run/uploads/39350c0573134c40a0d33d72680883e7/00002-868093864.webp
This example was created by evevalentine2017
Finished in 299.2 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: a strong 28-year-old senegalese powerlifter bodybuilder male , with short military haircut, glazed face, mindless expression, wearing a robotic suit, wearing a skin tight black latex robotic suit with gray latex details, standing at attention posture, on a modern futuristic street, looking to the camera, detailed face, Cinematic, Photoshoot, Shot on 25mm lens, Depth of Field, Tilt Blur, Shutter Speed 1/1000, F/22, White Balance, 32k, Super-Resolution, Pro Photo RGB, Half rear Lighting, Backlight, Dramatic Lighting, Incandescent, Soft Lighting, Volumetric, Conte-Jour, Global Illumination, Screen Space Global Illumination, Scattering, Shadows, Rough, Shimmering, Lumen Reflections, Screen Space Reflections, Diffraction Grading, Chromatic Aberration, GB Displacement, Scan Lines, Ambient Occlusion, Anti-Aliasing, FKAA, TXAA, RTX, SSAO, OpenGL-Shader, Post Processing, Post-Production, Cell Shading, Tone Mapping, CGI, VFX, SFX, insanely detailed and intricate, hyper maximalist, elegant, dynamic pose, photography, volumetric, ultra-detailed, intricate details, super detailed, ambient Full negative prompt: worst quality, extra fingers, missing fingers, poorly rendered hands, mutation, deformed iris, deformed pupils, deformed limbs, missing limbs, amputee, amputated limbs, watermark, logo , text, piercing, big eyes , teeth, cartoon, shallow depth of field, makeup 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:04<02:00, 4.02s/it] 6%|▋ | 2/31 [00:09<02:16, 4.71s/it] 10%|▉ | 3/31 [00:14<02:21, 5.07s/it] 13%|█▎ | 4/31 [00:20<02:20, 5.20s/it] 16%|█▌ | 5/31 [00:25<02:14, 5.19s/it] 19%|█▉ | 6/31 [00:30<02:11, 5.27s/it] 23%|██▎ | 7/31 [00:36<02:07, 5.29s/it] 26%|██▌ | 8/31 [00:41<02:02, 5.31s/it] 29%|██▉ | 9/31 [00:46<01:56, 5.28s/it] 32%|███▏ | 10/31 [00:52<01:55, 5.48s/it] 35%|███▌ | 11/31 [00:57<01:47, 5.38s/it] 39%|███▊ | 12/31 [01:03<01:42, 5.37s/it] 42%|████▏ | 13/31 [01:08<01:35, 5.31s/it] 45%|████▌ | 14/31 [01:13<01:30, 5.32s/it] 48%|████▊ | 15/31 [01:18<01:23, 5.19s/it] 52%|█████▏ | 16/31 [01:23<01:17, 5.16s/it] 55%|█████▍ | 17/31 [01:28<01:12, 5.16s/it] 58%|█████▊ | 18/31 [01:32<01:03, 4.86s/it] 61%|██████▏ | 19/31 [01:37<00:58, 4.84s/it] 65%|██████▍ | 20/31 [01:42<00:53, 4.90s/it] 68%|██████▊ | 21/31 [01:47<00:49, 4.91s/it] 71%|███████ | 22/31 [01:52<00:44, 4.91s/it] 74%|███████▍ | 23/31 [01:58<00:41, 5.21s/it] 77%|███████▋ | 24/31 [02:02<00:34, 4.95s/it] 81%|████████ | 25/31 [02:07<00:30, 5.02s/it] 84%|████████▍ | 26/31 [02:11<00:23, 4.67s/it] 87%|████████▋ | 27/31 [02:15<00:17, 4.46s/it] 90%|█████████ | 28/31 [02:19<00:13, 4.36s/it] 94%|█████████▎| 29/31 [02:24<00:08, 4.45s/it] 97%|█████████▋| 30/31 [02:27<00:04, 4.10s/it] 100%|██████████| 31/31 [02:29<00:00, 3.24s/it] 100%|██████████| 31/31 [02:29<00:00, 4.81s/it] Decoding latents in cuda:0... done in 2.34s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 20.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:02<00:26, 2.06s/it] 14%|█▍ | 2/14 [00:04<00:24, 2.01s/it] 21%|██▏ | 3/14 [00:06<00:22, 2.07s/it] 29%|██▊ | 4/14 [00:08<00:21, 2.16s/it] 36%|███▌ | 5/14 [00:10<00:19, 2.16s/it] 43%|████▎ | 6/14 [00:12<00:17, 2.15s/it] 50%|█████ | 7/14 [00:14<00:14, 2.01s/it] 57%|█████▋ | 8/14 [00:16<00:12, 2.01s/it] 64%|██████▍ | 9/14 [00:18<00:09, 1.91s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.85s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.82s/it] 86%|████████▌ | 12/14 [00:23<00:03, 1.87s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.76s/it] 100%|██████████| 14/14 [00:25<00:00, 1.42s/it] 100%|██████████| 14/14 [00:25<00:00, 1.84s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 12.9ms Speed: 4.6ms preprocess, 12.9ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.5ms Speed: 3.0ms preprocess, 7.5ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:24, 1.86s/it] 14%|█▍ | 2/14 [00:03<00:24, 2.02s/it] 21%|██▏ | 3/14 [00:06<00:22, 2.05s/it] 29%|██▊ | 4/14 [00:08<00:20, 2.05s/it] 36%|███▌ | 5/14 [00:10<00:18, 2.07s/it] 43%|████▎ | 6/14 [00:12<00:16, 2.09s/it] 50%|█████ | 7/14 [00:14<00:13, 1.96s/it] 57%|█████▋ | 8/14 [00:16<00:12, 2.01s/it] 64%|██████▍ | 9/14 [00:17<00:09, 1.91s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.87s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.91s/it] 86%|████████▌ | 12/14 [00:23<00:03, 1.97s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.87s/it] 100%|██████████| 14/14 [00:26<00:00, 1.51s/it] 100%|██████████| 14/14 [00:26<00:00, 1.86s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.5ms Speed: 3.6ms preprocess, 7.5ms inference, 2.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:24, 1.89s/it] 14%|█▍ | 2/14 [00:03<00:23, 1.97s/it] 21%|██▏ | 3/14 [00:05<00:22, 2.01s/it] 29%|██▊ | 4/14 [00:08<00:20, 2.05s/it] 36%|███▌ | 5/14 [00:10<00:18, 2.11s/it] 43%|████▎ | 6/14 [00:12<00:17, 2.14s/it] 50%|█████ | 7/14 [00:14<00:14, 2.03s/it] 57%|█████▋ | 8/14 [00:16<00:12, 2.02s/it] 64%|██████▍ | 9/14 [00:18<00:09, 1.92s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.87s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.84s/it] 86%|████████▌ | 12/14 [00:23<00:03, 1.88s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.77s/it] 100%|██████████| 14/14 [00:25<00:00, 1.42s/it] 100%|██████████| 14/14 [00:25<00:00, 1.83s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:23, 1.81s/it] 14%|█▍ | 2/14 [00:03<00:22, 1.91s/it] 21%|██▏ | 3/14 [00:05<00:21, 1.98s/it] 29%|██▊ | 4/14 [00:07<00:20, 2.01s/it] 36%|███▌ | 5/14 [00:09<00:18, 2.03s/it] 43%|████▎ | 6/14 [00:12<00:16, 2.07s/it] 50%|█████ | 7/14 [00:13<00:13, 1.97s/it] 57%|█████▋ | 8/14 [00:15<00:11, 2.00s/it] 64%|██████▍ | 9/14 [00:17<00:09, 1.92s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.88s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.88s/it] 86%|████████▌ | 12/14 [00:23<00:04, 2.02s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.86s/it] 100%|██████████| 14/14 [00:25<00:00, 1.49s/it] 100%|██████████| 14/14 [00:25<00:00, 1.84s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.1ms preprocess, 7.4ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:23, 1.81s/it] 14%|█▍ | 2/14 [00:03<00:23, 1.97s/it] 21%|██▏ | 3/14 [00:06<00:23, 2.14s/it] 29%|██▊ | 4/14 [00:08<00:21, 2.20s/it] 36%|███▌ | 5/14 [00:10<00:19, 2.15s/it] 43%|████▎ | 6/14 [00:12<00:17, 2.13s/it] 50%|█████ | 7/14 [00:14<00:13, 1.99s/it] 57%|█████▋ | 8/14 [00:16<00:11, 1.98s/it] 64%|██████▍ | 9/14 [00:18<00:09, 1.90s/it] 71%|███████▏ | 10/14 [00:19<00:07, 1.85s/it] 79%|███████▊ | 11/14 [00:21<00:05, 1.83s/it] 86%|████████▌ | 12/14 [00:23<00:03, 1.87s/it] 93%|█████████▎| 13/14 [00:25<00:01, 1.76s/it] 100%|██████████| 14/14 [00:25<00:00, 1.41s/it] 100%|██████████| 14/14 [00:25<00:00, 1.83s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.3ms preprocess, 7.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.