tungsten-logo
Sign In
White Mechas with Realistic Mech
realistic-mech:v1.0
evevalentine2017
evevalentine2017
·
Jan 4
347
Input
prompt
Specify things to see in the output
Award-winning professional designer, 3DMM raw photo of full body (ultra high quality, ultra detailed, ultra realistic, realistic, genius masterpiece) of (true realistic mirror metal reflection), (muscular transformer robot mecha), (ultra detailed ultra-sharp head, realistic texturing), new model design, hard surface structure, combination of carbon fiber and (white and red metallic paint: 1.3). The (chrome accents) glisten under the meticulous (studio lighting), adding an extra layer of (refinement) to the overall composition. Glowing armor lights, precision of its (aerodynamic design) and (tuned modifications). Each spoke is meticulously rendered, capturing the reflection of the (rich textures). The (glowing bright lights) filtering through the hard metal parts, (vibrant color), HDR (High Dynamic Range), Ray Tracing, NVIDIA RTX, Super-Resolution, Unreal 5, Subsurface scattering, PBR Texturing, Post-processing, Anisotropic Filtering, Depth-of-field, Maximum clarity and sharpness, Multi-layered textures, Albedo and Specular maps, Surface shading, Accurate simulation of light-material interaction, Perfect proportions, Octane Render, Two-tone lighting, Wide aperture, Low ISO, White balance, Rule of thirds, 8K RAW, Efficient Sub-Pixel, sub-pixel convolution, robot, mecha, shiny_metal:1
negative_prompt
Specify things to not see in the output
(worst quality, low quality:1.4), (bad_prompt_version2-neg:0.8), EasyNegativeV2, bad-hands-5, text, name, letters, watermark
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
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0.1
brightness
Adjust brightness
0.1
contrast
Adjust contrast
0
saturation
Adjust saturation
0
num_outputs
Number of output images
4
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
3957756725
width
Output image width
768
height
Output image height
768
reference_image
Image that the output should be similar to
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
32
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
clearvae_v2.3_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)
bad-hands-5.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
EasyNegativeV2.safetensors
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad_prompt_version2-neg.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/8c74b77b783d43df81185279ae0a604d/00000-3957756725.png
https://files.tungsten.run/uploads/5e7b04ca91504b6e8ff928e58fff694f/00001-3957756726.png
https://files.tungsten.run/uploads/401addb5ce50490ab0a301e3896733bb/00002-3957756727.png
https://files.tungsten.run/uploads/bd9e3cc2973746df851ac3ba04e338be/00003-3957756728.png
Finished in 48.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/clearvae_v2.3_fp16.safetensors Full prompt: Award-winning professional designer, 3DMM raw photo of full body (ultra high quality, ultra detailed, ultra realistic, realistic, genius masterpiece) of (true realistic mirror metal reflection), (muscular transformer robot mecha), (ultra detailed ultra-sharp head, realistic texturing), new model design, hard surface structure, combination of carbon fiber and (white and red metallic paint: 1.3). The (chrome accents) glisten under the meticulous (studio lighting), adding an extra layer of (refinement) to the overall composition. Glowing armor lights, precision of its (aerodynamic design) and (tuned modifications). Each spoke is meticulously rendered, capturing the reflection of the (rich textures). The (glowing bright lights) filtering through the hard metal parts, (vibrant color), HDR (High Dynamic Range), Ray Tracing, NVIDIA RTX, Super-Resolution, Unreal 5, Subsurface scattering, PBR Texturing, Post-processing, Anisotropic Filtering, Depth-of-field, Maximum clarity and sharpness, Multi-layered textures, Albedo and Specular maps, Surface shading, Accurate simulation of light-material interaction, Perfect proportions, Octane Render, Two-tone lighting, Wide aperture, Low ISO, White balance, Rule of thirds, 8K RAW, Efficient Sub-Pixel, sub-pixel convolution, robot, mecha, shiny_metal:1, (insane quality:1.5), (ultra detailed:1.5), (masterpiece:1.5), <lora:add_detail:0.1>, <lora:add_brightness:0.1> Full negative prompt: (worst quality, low quality:1.4), (bad_prompt_version2-neg:0.8), EasyNegativeV2, bad-hands-5, text, name, letters, watermark 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:01<00:39, 1.27s/it] 6%|▋ | 2/32 [00:01<00:27, 1.11it/s] 9%|▉ | 3/32 [00:02<00:22, 1.28it/s] 12%|█▎ | 4/32 [00:03<00:20, 1.38it/s] 16%|█▌ | 5/32 [00:03<00:18, 1.43it/s] 19%|█▉ | 6/32 [00:04<00:17, 1.47it/s] 22%|██▏ | 7/32 [00:05<00:16, 1.50it/s] 25%|██▌ | 8/32 [00:05<00:15, 1.52it/s] 28%|██▊ | 9/32 [00:06<00:15, 1.52it/s] 31%|███▏ | 10/32 [00:07<00:14, 1.53it/s] 34%|███▍ | 11/32 [00:07<00:13, 1.53it/s] 38%|███▊ | 12/32 [00:08<00:13, 1.54it/s] 41%|████ | 13/32 [00:09<00:12, 1.54it/s] 44%|████▍ | 14/32 [00:09<00:11, 1.54it/s] 47%|████▋ | 15/32 [00:10<00:11, 1.54it/s] 50%|█████ | 16/32 [00:10<00:10, 1.54it/s] 53%|█████▎ | 17/32 [00:11<00:09, 1.53it/s] 56%|█████▋ | 18/32 [00:12<00:09, 1.53it/s] 59%|█████▉ | 19/32 [00:12<00:08, 1.53it/s] 62%|██████▎ | 20/32 [00:13<00:07, 1.53it/s] 66%|██████▌ | 21/32 [00:14<00:07, 1.53it/s] 69%|██████▉ | 22/32 [00:14<00:06, 1.53it/s] 72%|███████▏ | 23/32 [00:15<00:05, 1.53it/s] 75%|███████▌ | 24/32 [00:16<00:05, 1.53it/s] 78%|███████▊ | 25/32 [00:16<00:04, 1.53it/s] 81%|████████▏ | 26/32 [00:17<00:03, 1.53it/s] 84%|████████▍ | 27/32 [00:18<00:03, 1.53it/s] 88%|████████▊ | 28/32 [00:18<00:02, 1.53it/s] 91%|█████████ | 29/32 [00:19<00:01, 1.53it/s] 94%|█████████▍| 30/32 [00:20<00:01, 1.53it/s] 97%|█████████▋| 31/32 [00:20<00:00, 1.53it/s] 100%|██████████| 32/32 [00:21<00:00, 1.53it/s] 100%|██████████| 32/32 [00:21<00:00, 1.49it/s] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.02s 0: 640x640 (no detections), 7.6ms Speed: 3.5ms preprocess, 7.6ms inference, 9.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 9.2ms Speed: 2.8ms preprocess, 9.2ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 (no detections), 7.3ms Speed: 2.7ms preprocess, 7.3ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 (no detections), 7.1ms Speed: 2.7ms preprocess, 7.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 (no detections), 7.3ms Speed: 2.6ms preprocess, 7.3ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x640 1 hand, 7.1ms Speed: 2.7ms preprocess, 7.1ms inference, 11.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/18 [00:00<?, ?it/s] 6%|▌ | 1/18 [00:00<00:06, 2.66it/s] 11%|█ | 2/18 [00:00<00:04, 3.71it/s] 17%|█▋ | 3/18 [00:00<00:03, 4.15it/s] 22%|██▏ | 4/18 [00:00<00:03, 4.49it/s] 28%|██▊ | 5/18 [00:01<00:02, 4.69it/s] 33%|███▎ | 6/18 [00:01<00:02, 4.81it/s] 39%|███▉ | 7/18 [00:01<00:02, 4.92it/s] 44%|████▍ | 8/18 [00:01<00:02, 4.89it/s] 50%|█████ | 9/18 [00:01<00:01, 4.96it/s] 56%|█████▌ | 10/18 [00:02<00:01, 4.98it/s] 61%|██████ | 11/18 [00:02<00:01, 5.01it/s] 67%|██████▋ | 12/18 [00:02<00:01, 4.93it/s] 72%|███████▏ | 13/18 [00:02<00:01, 4.84it/s] 78%|███████▊ | 14/18 [00:02<00:00, 4.92it/s] 83%|████████▎ | 15/18 [00:03<00:00, 4.85it/s] 89%|████████▉ | 16/18 [00:03<00:00, 4.93it/s] 94%|█████████▍| 17/18 [00:03<00:00, 4.94it/s] 100%|██████████| 18/18 [00:03<00:00, 4.92it/s] 100%|██████████| 18/18 [00:03<00:00, 4.74it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.1ms Speed: 2.8ms preprocess, 7.1ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/18 [00:00<?, ?it/s] 6%|▌ | 1/18 [00:00<00:03, 5.03it/s] 11%|█ | 2/18 [00:00<00:03, 4.94it/s] 17%|█▋ | 3/18 [00:00<00:03, 4.96it/s] 22%|██▏ | 4/18 [00:00<00:02, 4.95it/s] 28%|██▊ | 5/18 [00:01<00:02, 5.02it/s] 33%|███▎ | 6/18 [00:01<00:02, 5.03it/s] 39%|███▉ | 7/18 [00:01<00:02, 5.06it/s] 44%|████▍ | 8/18 [00:01<00:02, 4.96it/s] 50%|█████ | 9/18 [00:01<00:01, 5.03it/s] 56%|█████▌ | 10/18 [00:01<00:01, 5.05it/s] 61%|██████ | 11/18 [00:02<00:01, 5.02it/s] 67%|██████▋ | 12/18 [00:02<00:01, 5.05it/s] 72%|███████▏ | 13/18 [00:02<00:01, 4.97it/s] 78%|███████▊ | 14/18 [00:02<00:00, 5.01it/s] 83%|████████▎ | 15/18 [00:03<00:00, 4.95it/s] 89%|████████▉ | 16/18 [00:03<00:00, 4.41it/s] 94%|█████████▍| 17/18 [00:03<00:00, 4.58it/s] 100%|██████████| 18/18 [00:03<00:00, 4.74it/s] 100%|██████████| 18/18 [00:03<00:00, 4.89it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 6.9ms Speed: 2.7ms preprocess, 6.9ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/18 [00:00<?, ?it/s] 6%|▌ | 1/18 [00:00<00:03, 5.18it/s] 11%|█ | 2/18 [00:00<00:03, 5.17it/s] 17%|█▋ | 3/18 [00:00<00:02, 5.16it/s] 22%|██▏ | 4/18 [00:00<00:02, 4.94it/s] 28%|██▊ | 5/18 [00:01<00:02, 4.87it/s] 33%|███▎ | 6/18 [00:01<00:02, 4.98it/s] 39%|███▉ | 7/18 [00:01<00:02, 5.03it/s] 44%|████▍ | 8/18 [00:01<00:01, 5.01it/s] 50%|█████ | 9/18 [00:01<00:01, 4.95it/s] 56%|█████▌ | 10/18 [00:01<00:01, 5.00it/s] 61%|██████ | 11/18 [00:02<00:01, 5.04it/s] 67%|██████▋ | 12/18 [00:02<00:01, 5.08it/s] 72%|███████▏ | 13/18 [00:02<00:00, 5.10it/s] 78%|███████▊ | 14/18 [00:02<00:00, 5.06it/s] 83%|████████▎ | 15/18 [00:02<00:00, 5.08it/s] 89%|████████▉ | 16/18 [00:03<00:00, 5.09it/s] 94%|█████████▍| 17/18 [00:03<00:00, 5.10it/s] 100%|██████████| 18/18 [00:03<00:00, 5.05it/s] 100%|██████████| 18/18 [00:03<00:00, 5.04it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt
Specify things to see in the output
Award-winning professional designer, 3DMM raw photo of full body (ultra high quality, ultra detailed, ultra realistic, realistic, genius masterpiece) of (true realistic mirror metal reflection), (muscular transformer robot mecha), (ultra detailed ultra-sharp head, realistic texturing), new model design, hard surface structure, combination of carbon fiber and (white and red metallic paint: 1.3). The (chrome accents) glisten under the meticulous (studio lighting), adding an extra layer of (refinement) to the overall composition. Glowing armor lights, precision of its (aerodynamic design) and (tuned modifications). Each spoke is meticulously rendered, capturing the reflection of the (rich textures). The (glowing bright lights) filtering through the hard metal parts, (vibrant color), HDR (High Dynamic Range), Ray Tracing, NVIDIA RTX, Super-Resolution, Unreal 5, Subsurface scattering, PBR Texturing, Post-processing, Anisotropic Filtering, Depth-of-field, Maximum clarity and sharpness, Multi-layered textures, Albedo and Specular maps, Surface shading, Accurate simulation of light-material interaction, Perfect proportions, Octane Render, Two-tone lighting, Wide aperture, Low ISO, White balance, Rule of thirds, 8K RAW, Efficient Sub-Pixel, sub-pixel convolution, robot, mecha, shiny_metal:1
negative_prompt
Specify things to not see in the output
(worst quality, low quality:1.4), (bad_prompt_version2-neg:0.8), EasyNegativeV2, bad-hands-5, text, name, letters, watermark
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
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0.1
brightness
Adjust brightness
0.1
contrast
Adjust contrast
0
saturation
Adjust saturation
0
num_outputs
Number of output images
4
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
3957756725
width
Output image width
768
height
Output image height
768
reference_image
Image that the output should be similar to
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
32
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
clearvae_v2.3_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)
bad-hands-5.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
EasyNegativeV2.safetensors
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad_prompt_version2-neg.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/8c74b77b783d43df81185279ae0a604d/00000-3957756725.png
https://files.tungsten.run/uploads/5e7b04ca91504b6e8ff928e58fff694f/00001-3957756726.png
https://files.tungsten.run/uploads/401addb5ce50490ab0a301e3896733bb/00002-3957756727.png
https://files.tungsten.run/uploads/bd9e3cc2973746df851ac3ba04e338be/00003-3957756728.png
Finished in 48.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/clearvae_v2.3_fp16.safetensors Full prompt: Award-winning professional designer, 3DMM raw photo of full body (ultra high quality, ultra detailed, ultra realistic, realistic, genius masterpiece) of (true realistic mirror metal reflection), (muscular transformer robot mecha), (ultra detailed ultra-sharp head, realistic texturing), new model design, hard surface structure, combination of carbon fiber and (white and red metallic paint: 1.3). The (chrome accents) glisten under the meticulous (studio lighting), adding an extra layer of (refinement) to the overall composition. Glowing armor lights, precision of its (aerodynamic design) and (tuned modifications). Each spoke is meticulously rendered, capturing the reflection of the (rich textures). The (glowing bright lights) filtering through the hard metal parts, (vibrant color), HDR (High Dynamic Range), Ray Tracing, NVIDIA RTX, Super-Resolution, Unreal 5, Subsurface scattering, PBR Texturing, Post-processing, Anisotropic Filtering, Depth-of-field, Maximum clarity and sharpness, Multi-layered textures, Albedo and Specular maps, Surface shading, Accurate simulation of light-material interaction, Perfect proportions, Octane Render, Two-tone lighting, Wide aperture, Low ISO, White balance, Rule of thirds, 8K RAW, Efficient Sub-Pixel, sub-pixel convolution, robot, mecha, shiny_metal:1, (insane quality:1.5), (ultra detailed:1.5), (masterpiece:1.5), <lora:add_detail:0.1>, <lora:add_brightness:0.1> Full negative prompt: (worst quality, low quality:1.4), (bad_prompt_version2-neg:0.8), EasyNegativeV2, bad-hands-5, text, name, letters, watermark 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:01<00:39, 1.27s/it] 6%|▋ | 2/32 [00:01<00:27, 1.11it/s] 9%|▉ | 3/32 [00:02<00:22, 1.28it/s] 12%|█▎ | 4/32 [00:03<00:20, 1.38it/s] 16%|█▌ | 5/32 [00:03<00:18, 1.43it/s] 19%|█▉ | 6/32 [00:04<00:17, 1.47it/s] 22%|██▏ | 7/32 [00:05<00:16, 1.50it/s] 25%|██▌ | 8/32 [00:05<00:15, 1.52it/s] 28%|██▊ | 9/32 [00:06<00:15, 1.52it/s] 31%|███▏ | 10/32 [00:07<00:14, 1.53it/s] 34%|███▍ | 11/32 [00:07<00:13, 1.53it/s] 38%|███▊ | 12/32 [00:08<00:13, 1.54it/s] 41%|████ | 13/32 [00:09<00:12, 1.54it/s] 44%|████▍ | 14/32 [00:09<00:11, 1.54it/s] 47%|████▋ | 15/32 [00:10<00:11, 1.54it/s] 50%|█████ | 16/32 [00:10<00:10, 1.54it/s] 53%|█████▎ | 17/32 [00:11<00:09, 1.53it/s] 56%|█████▋ | 18/32 [00:12<00:09, 1.53it/s] 59%|█████▉ | 19/32 [00:12<00:08, 1.53it/s] 62%|██████▎ | 20/32 [00:13<00:07, 1.53it/s] 66%|██████▌ | 21/32 [00:14<00:07, 1.53it/s] 69%|██████▉ | 22/32 [00:14<00:06, 1.53it/s] 72%|███████▏ | 23/32 [00:15<00:05, 1.53it/s] 75%|███████▌ | 24/32 [00:16<00:05, 1.53it/s] 78%|███████▊ | 25/32 [00:16<00:04, 1.53it/s] 81%|████████▏ | 26/32 [00:17<00:03, 1.53it/s] 84%|████████▍ | 27/32 [00:18<00:03, 1.53it/s] 88%|████████▊ | 28/32 [00:18<00:02, 1.53it/s] 91%|█████████ | 29/32 [00:19<00:01, 1.53it/s] 94%|█████████▍| 30/32 [00:20<00:01, 1.53it/s] 97%|█████████▋| 31/32 [00:20<00:00, 1.53it/s] 100%|██████████| 32/32 [00:21<00:00, 1.53it/s] 100%|██████████| 32/32 [00:21<00:00, 1.49it/s] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.02s 0: 640x640 (no detections), 7.6ms Speed: 3.5ms preprocess, 7.6ms inference, 9.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 9.2ms Speed: 2.8ms preprocess, 9.2ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 (no detections), 7.3ms Speed: 2.7ms preprocess, 7.3ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 (no detections), 7.1ms Speed: 2.7ms preprocess, 7.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 (no detections), 7.3ms Speed: 2.6ms preprocess, 7.3ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x640 1 hand, 7.1ms Speed: 2.7ms preprocess, 7.1ms inference, 11.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/18 [00:00<?, ?it/s] 6%|▌ | 1/18 [00:00<00:06, 2.66it/s] 11%|█ | 2/18 [00:00<00:04, 3.71it/s] 17%|█▋ | 3/18 [00:00<00:03, 4.15it/s] 22%|██▏ | 4/18 [00:00<00:03, 4.49it/s] 28%|██▊ | 5/18 [00:01<00:02, 4.69it/s] 33%|███▎ | 6/18 [00:01<00:02, 4.81it/s] 39%|███▉ | 7/18 [00:01<00:02, 4.92it/s] 44%|████▍ | 8/18 [00:01<00:02, 4.89it/s] 50%|█████ | 9/18 [00:01<00:01, 4.96it/s] 56%|█████▌ | 10/18 [00:02<00:01, 4.98it/s] 61%|██████ | 11/18 [00:02<00:01, 5.01it/s] 67%|██████▋ | 12/18 [00:02<00:01, 4.93it/s] 72%|███████▏ | 13/18 [00:02<00:01, 4.84it/s] 78%|███████▊ | 14/18 [00:02<00:00, 4.92it/s] 83%|████████▎ | 15/18 [00:03<00:00, 4.85it/s] 89%|████████▉ | 16/18 [00:03<00:00, 4.93it/s] 94%|█████████▍| 17/18 [00:03<00:00, 4.94it/s] 100%|██████████| 18/18 [00:03<00:00, 4.92it/s] 100%|██████████| 18/18 [00:03<00:00, 4.74it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.1ms Speed: 2.8ms preprocess, 7.1ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/18 [00:00<?, ?it/s] 6%|▌ | 1/18 [00:00<00:03, 5.03it/s] 11%|█ | 2/18 [00:00<00:03, 4.94it/s] 17%|█▋ | 3/18 [00:00<00:03, 4.96it/s] 22%|██▏ | 4/18 [00:00<00:02, 4.95it/s] 28%|██▊ | 5/18 [00:01<00:02, 5.02it/s] 33%|███▎ | 6/18 [00:01<00:02, 5.03it/s] 39%|███▉ | 7/18 [00:01<00:02, 5.06it/s] 44%|████▍ | 8/18 [00:01<00:02, 4.96it/s] 50%|█████ | 9/18 [00:01<00:01, 5.03it/s] 56%|█████▌ | 10/18 [00:01<00:01, 5.05it/s] 61%|██████ | 11/18 [00:02<00:01, 5.02it/s] 67%|██████▋ | 12/18 [00:02<00:01, 5.05it/s] 72%|███████▏ | 13/18 [00:02<00:01, 4.97it/s] 78%|███████▊ | 14/18 [00:02<00:00, 5.01it/s] 83%|████████▎ | 15/18 [00:03<00:00, 4.95it/s] 89%|████████▉ | 16/18 [00:03<00:00, 4.41it/s] 94%|█████████▍| 17/18 [00:03<00:00, 4.58it/s] 100%|██████████| 18/18 [00:03<00:00, 4.74it/s] 100%|██████████| 18/18 [00:03<00:00, 4.89it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 6.9ms Speed: 2.7ms preprocess, 6.9ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/18 [00:00<?, ?it/s] 6%|▌ | 1/18 [00:00<00:03, 5.18it/s] 11%|█ | 2/18 [00:00<00:03, 5.17it/s] 17%|█▋ | 3/18 [00:00<00:02, 5.16it/s] 22%|██▏ | 4/18 [00:00<00:02, 4.94it/s] 28%|██▊ | 5/18 [00:01<00:02, 4.87it/s] 33%|███▎ | 6/18 [00:01<00:02, 4.98it/s] 39%|███▉ | 7/18 [00:01<00:02, 5.03it/s] 44%|████▍ | 8/18 [00:01<00:01, 5.01it/s] 50%|█████ | 9/18 [00:01<00:01, 4.95it/s] 56%|█████▌ | 10/18 [00:01<00:01, 5.00it/s] 61%|██████ | 11/18 [00:02<00:01, 5.04it/s] 67%|██████▋ | 12/18 [00:02<00:01, 5.08it/s] 72%|███████▏ | 13/18 [00:02<00:00, 5.10it/s] 78%|███████▊ | 14/18 [00:02<00:00, 5.06it/s] 83%|████████▎ | 15/18 [00:02<00:00, 5.08it/s] 89%|████████▉ | 16/18 [00:03<00:00, 5.09it/s] 94%|█████████▍| 17/18 [00:03<00:00, 5.10it/s] 100%|██████████| 18/18 [00:03<00:00, 5.05it/s] 100%|██████████| 18/18 [00:03<00:00, 5.04it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s Uploading outputs... Finished.