tungsten-logo
Sign In
hephaistos-sd-xl
hephaistos-sd-xl

hephaistos-sd-xl

3 stars
Version: v3.3
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/e114fdf5a0a040929bf31175f05535d4/00000-1577184080.webp
https://files.tungsten.run/uploads/66996e56bedc4d558936ba72b9ef6c29/00001-1577184081.webp
https://files.tungsten.run/uploads/b549e025d865415a8dfd645c17e0413e/00002-1577184082.webp
This example was created by evevalentine2017
Finished in 287.4 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: sharp focus photo, goth, strong makeup, soaking wet nude skin with neon highlights, sparkling eyes, inside a dark alleyway, [short hair|bald], black lips, green eyes, large breasts, cyborg helmet with a Mohawk of thick multi-colored plastic cables coming out of it, cute frown, cute, close up, red gloves, upper body, realistic, 3d, intricate detail, cinematic shot, (detailed realistic cyberpunk background:1.3), realistic lighting, cinematic lighting. full body cyborg, dynamic action poses, rain, sharp focus, Full negative prompt: bad quality, worst quality, illustration, low contrast 0%| | 0/70 [00:00<?, ?it/s] 1%|▏ | 1/70 [00:02<02:19, 2.03s/it] 3%|▎ | 2/70 [00:04<02:39, 2.34s/it] 4%|▍ | 3/70 [00:07<02:50, 2.55s/it] 6%|▌ | 4/70 [00:10<02:51, 2.60s/it] 7%|▋ | 5/70 [00:12<02:51, 2.64s/it] 9%|▊ | 6/70 [00:15<02:51, 2.68s/it] 10%|█ | 7/70 [00:18<02:50, 2.71s/it] 11%|█▏ | 8/70 [00:20<02:46, 2.69s/it] 13%|█▎ | 9/70 [00:23<02:43, 2.68s/it] 14%|█▍ | 10/70 [00:26<02:37, 2.63s/it] 16%|█▌ | 11/70 [00:28<02:35, 2.64s/it] 17%|█▋ | 12/70 [00:31<02:34, 2.67s/it] 19%|█▊ | 13/70 [00:34<02:31, 2.65s/it] 20%|██ | 14/70 [00:36<02:29, 2.66s/it] 21%|██▏ | 15/70 [00:39<02:24, 2.63s/it] 23%|██▎ | 16/70 [00:42<02:23, 2.66s/it] 24%|██▍ | 17/70 [00:44<02:15, 2.55s/it] 26%|██▌ | 18/70 [00:46<02:08, 2.47s/it] 27%|██▋ | 19/70 [00:49<02:07, 2.51s/it] 29%|██▊ | 20/70 [00:51<02:07, 2.55s/it] 30%|███ | 21/70 [00:54<02:07, 2.60s/it] 31%|███▏ | 22/70 [00:57<02:05, 2.61s/it] 33%|███▎ | 23/70 [01:00<02:04, 2.66s/it] 34%|███▍ | 24/70 [01:02<02:00, 2.62s/it] 36%|███▌ | 25/70 [01:05<01:59, 2.65s/it] 37%|███▋ | 26/70 [01:07<01:53, 2.58s/it] 39%|███▊ | 27/70 [01:10<01:49, 2.54s/it] 40%|████ | 28/70 [01:12<01:47, 2.56s/it] 41%|████▏ | 29/70 [01:15<01:45, 2.58s/it] 43%|████▎ | 30/70 [01:18<01:43, 2.60s/it] 44%|████▍ | 31/70 [01:20<01:42, 2.62s/it] 46%|████▌ | 32/70 [01:23<01:40, 2.64s/it] 47%|████▋ | 33/70 [01:25<01:35, 2.57s/it] 49%|████▊ | 34/70 [01:28<01:33, 2.60s/it] 50%|█████ | 35/70 [01:30<01:28, 2.53s/it] 51%|█████▏ | 36/70 [01:33<01:26, 2.55s/it] 53%|█████▎ | 37/70 [01:35<01:22, 2.49s/it] 54%|█████▍ | 38/70 [01:38<01:19, 2.48s/it] 56%|█████▌ | 39/70 [01:40<01:18, 2.53s/it] 57%|█████▋ | 40/70 [01:43<01:15, 2.50s/it] 59%|█████▊ | 41/70 [01:45<01:12, 2.49s/it] 60%|██████ | 42/70 [01:48<01:10, 2.50s/it] 61%|██████▏ | 43/70 [01:50<01:06, 2.47s/it] 63%|██████▎ | 44/70 [01:53<01:03, 2.45s/it] 64%|██████▍ | 45/70 [01:55<01:01, 2.47s/it] 66%|██████▌ | 46/70 [01:58<01:00, 2.54s/it] 67%|██████▋ | 47/70 [02:00<00:57, 2.52s/it] 69%|██████▊ | 48/70 [02:03<00:55, 2.51s/it] 70%|███████ | 49/70 [02:05<00:50, 2.41s/it] 71%|███████▏ | 50/70 [02:07<00:48, 2.44s/it] 73%|███████▎ | 51/70 [02:10<00:46, 2.46s/it] 74%|███████▍ | 52/70 [02:13<00:44, 2.50s/it] 76%|███████▌ | 53/70 [02:15<00:41, 2.47s/it] 77%|███████▋ | 54/70 [02:17<00:39, 2.48s/it] 79%|███████▊ | 55/70 [02:20<00:36, 2.45s/it] 80%|████████ | 56/70 [02:22<00:34, 2.44s/it] 81%|████████▏ | 57/70 [02:25<00:31, 2.44s/it] 83%|████████▎ | 58/70 [02:27<00:28, 2.38s/it] 84%|████████▍ | 59/70 [02:29<00:25, 2.31s/it] 86%|████████▌ | 60/70 [02:31<00:22, 2.29s/it] 87%|████████▋ | 61/70 [02:34<00:21, 2.36s/it] 89%|████████▊ | 62/70 [02:36<00:18, 2.27s/it] 90%|█████████ | 63/70 [02:38<00:16, 2.30s/it] 91%|█████████▏| 64/70 [02:41<00:13, 2.28s/it] 93%|█████████▎| 65/70 [02:43<00:11, 2.34s/it] 94%|█████████▍| 66/70 [02:45<00:08, 2.21s/it] 96%|█████████▌| 67/70 [02:47<00:06, 2.23s/it] 97%|█████████▋| 68/70 [02:49<00:04, 2.19s/it] 99%|█████████▊| 69/70 [02:51<00:01, 1.96s/it] 100%|██████████| 70/70 [02:52<00:00, 1.74s/it] 100%|██████████| 70/70 [02:52<00:00, 2.46s/it] Decoding latents in cuda:0... done in 2.41s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.9ms Speed: 3.2ms preprocess, 7.9ms inference, 17.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:01<00:37, 1.22s/it] 6%|▋ | 2/32 [00:02<00:34, 1.13s/it] 9%|▉ | 3/32 [00:03<00:31, 1.10s/it] 12%|█▎ | 4/32 [00:04<00:30, 1.09s/it] 16%|█▌ | 5/32 [00:05<00:28, 1.06s/it] 19%|█▉ | 6/32 [00:06<00:27, 1.07s/it] 22%|██▏ | 7/32 [00:07<00:27, 1.08s/it] 25%|██▌ | 8/32 [00:08<00:26, 1.10s/it] 28%|██▊ | 9/32 [00:09<00:25, 1.10s/it] 31%|███▏ | 10/32 [00:10<00:23, 1.08s/it] 34%|███▍ | 11/32 [00:11<00:21, 1.03s/it] 38%|███▊ | 12/32 [00:12<00:20, 1.03s/it] 41%|████ | 13/32 [00:13<00:19, 1.04s/it] 44%|████▍ | 14/32 [00:15<00:19, 1.06s/it] 47%|████▋ | 15/32 [00:16<00:18, 1.08s/it] 50%|█████ | 16/32 [00:17<00:17, 1.09s/it] 53%|█████▎ | 17/32 [00:18<00:15, 1.06s/it] 56%|█████▋ | 18/32 [00:19<00:14, 1.05s/it] 59%|█████▉ | 19/32 [00:20<00:13, 1.03s/it] 62%|██████▎ | 20/32 [00:21<00:12, 1.01s/it] 66%|██████▌ | 21/32 [00:22<00:10, 1.00it/s] 69%|██████▉ | 22/32 [00:23<00:09, 1.02it/s] 72%|███████▏ | 23/32 [00:24<00:09, 1.00s/it] 75%|███████▌ | 24/32 [00:25<00:07, 1.01it/s] 78%|███████▊ | 25/32 [00:26<00:07, 1.04s/it] 81%|████████▏ | 26/32 [00:27<00:06, 1.03s/it] 84%|████████▍ | 27/32 [00:28<00:05, 1.05s/it] 88%|████████▊ | 28/32 [00:29<00:04, 1.01s/it] 91%|█████████ | 29/32 [00:30<00:03, 1.01s/it] 94%|█████████▍| 30/32 [00:31<00:01, 1.02it/s] 97%|█████████▋| 31/32 [00:31<00:00, 1.11it/s] 100%|██████████| 32/32 [00:32<00:00, 1.23it/s] 100%|██████████| 32/32 [00:32<00:00, 1.02s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.6ms Speed: 3.0ms preprocess, 7.6ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 8.2ms Speed: 3.0ms preprocess, 8.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:01<00:33, 1.09s/it] 6%|▋ | 2/32 [00:02<00:32, 1.08s/it] 9%|▉ | 3/32 [00:03<00:30, 1.07s/it] 12%|█▎ | 4/32 [00:04<00:30, 1.08s/it] 16%|█▌ | 5/32 [00:05<00:28, 1.06s/it] 19%|█▉ | 6/32 [00:06<00:27, 1.05s/it] 22%|██▏ | 7/32 [00:07<00:26, 1.07s/it] 25%|██▌ | 8/32 [00:08<00:26, 1.09s/it] 28%|██▊ | 9/32 [00:09<00:24, 1.07s/it] 31%|███▏ | 10/32 [00:10<00:23, 1.09s/it] 34%|███▍ | 11/32 [00:11<00:22, 1.05s/it] 38%|███▊ | 12/32 [00:12<00:21, 1.05s/it] 41%|████ | 13/32 [00:13<00:20, 1.05s/it] 44%|████▍ | 14/32 [00:14<00:19, 1.06s/it] 47%|████▋ | 15/32 [00:15<00:17, 1.06s/it] 50%|█████ | 16/32 [00:17<00:16, 1.05s/it] 53%|█████▎ | 17/32 [00:18<00:15, 1.04s/it] 56%|█████▋ | 18/32 [00:19<00:14, 1.04s/it] 59%|█████▉ | 19/32 [00:20<00:13, 1.03s/it] 62%|██████▎ | 20/32 [00:21<00:12, 1.01s/it] 66%|██████▌ | 21/32 [00:21<00:10, 1.01it/s] 69%|██████▉ | 22/32 [00:22<00:09, 1.02it/s] 72%|███████▏ | 23/32 [00:23<00:09, 1.00s/it] 75%|███████▌ | 24/32 [00:24<00:07, 1.01it/s] 78%|███████▊ | 25/32 [00:25<00:06, 1.01it/s] 81%|████████▏ | 26/32 [00:26<00:05, 1.02it/s] 84%|████████▍ | 27/32 [00:27<00:04, 1.00it/s] 88%|████████▊ | 28/32 [00:28<00:03, 1.05it/s] 91%|█████████ | 29/32 [00:29<00:02, 1.04it/s] 94%|█████████▍| 30/32 [00:30<00:01, 1.05it/s] 97%|█████████▋| 31/32 [00:31<00:00, 1.14it/s] 100%|██████████| 32/32 [00:32<00:00, 1.21it/s] 100%|██████████| 32/32 [00:32<00:00, 1.00s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.3ms Speed: 2.9ms preprocess, 7.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:01<00:33, 1.08s/it] 6%|▋ | 2/32 [00:02<00:31, 1.04s/it] 9%|▉ | 3/32 [00:03<00:29, 1.03s/it] 12%|█▎ | 4/32 [00:04<00:29, 1.04s/it] 16%|█▌ | 5/32 [00:05<00:27, 1.03s/it] 19%|█▉ | 6/32 [00:06<00:26, 1.03s/it] 22%|██▏ | 7/32 [00:07<00:26, 1.05s/it] 25%|██▌ | 8/32 [00:08<00:25, 1.08s/it] 28%|██▊ | 9/32 [00:09<00:24, 1.07s/it] 31%|███▏ | 10/32 [00:10<00:23, 1.06s/it] 34%|███▍ | 11/32 [00:11<00:21, 1.02s/it] 38%|███▊ | 12/32 [00:12<00:20, 1.02s/it] 41%|████ | 13/32 [00:13<00:19, 1.03s/it] 44%|████▍ | 14/32 [00:14<00:18, 1.04s/it] 47%|████▋ | 15/32 [00:15<00:17, 1.03s/it] 50%|█████ | 16/32 [00:16<00:16, 1.04s/it] 53%|█████▎ | 17/32 [00:17<00:15, 1.04s/it] 56%|█████▋ | 18/32 [00:18<00:14, 1.03s/it] 59%|█████▉ | 19/32 [00:19<00:13, 1.02s/it] 62%|██████▎ | 20/32 [00:20<00:12, 1.00s/it] 66%|██████▌ | 21/32 [00:21<00:10, 1.02it/s] 69%|██████▉ | 22/32 [00:22<00:09, 1.03it/s] 72%|███████▏ | 23/32 [00:23<00:08, 1.01it/s] 75%|███████▌ | 24/32 [00:24<00:07, 1.04it/s] 78%|███████▊ | 25/32 [00:25<00:06, 1.03it/s] 81%|████████▏ | 26/32 [00:26<00:05, 1.03it/s] 84%|████████▍ | 27/32 [00:27<00:04, 1.01it/s] 88%|████████▊ | 28/32 [00:28<00:03, 1.06it/s] 91%|█████████ | 29/32 [00:29<00:02, 1.05it/s] 94%|█████████▍| 30/32 [00:30<00:01, 1.07it/s] 97%|█████████▋| 31/32 [00:30<00:00, 1.16it/s] 100%|██████████| 32/32 [00:31<00:00, 1.27it/s] 100%|██████████| 32/32 [00:31<00:00, 1.02it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 0.7ms 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/e114fdf5a0a040929bf31175f05535d4/00000-1577184080.webp
https://files.tungsten.run/uploads/66996e56bedc4d558936ba72b9ef6c29/00001-1577184081.webp
https://files.tungsten.run/uploads/b549e025d865415a8dfd645c17e0413e/00002-1577184082.webp
This example was created by evevalentine2017
Finished in 287.4 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: sharp focus photo, goth, strong makeup, soaking wet nude skin with neon highlights, sparkling eyes, inside a dark alleyway, [short hair|bald], black lips, green eyes, large breasts, cyborg helmet with a Mohawk of thick multi-colored plastic cables coming out of it, cute frown, cute, close up, red gloves, upper body, realistic, 3d, intricate detail, cinematic shot, (detailed realistic cyberpunk background:1.3), realistic lighting, cinematic lighting. full body cyborg, dynamic action poses, rain, sharp focus, Full negative prompt: bad quality, worst quality, illustration, low contrast 0%| | 0/70 [00:00<?, ?it/s] 1%|▏ | 1/70 [00:02<02:19, 2.03s/it] 3%|▎ | 2/70 [00:04<02:39, 2.34s/it] 4%|▍ | 3/70 [00:07<02:50, 2.55s/it] 6%|▌ | 4/70 [00:10<02:51, 2.60s/it] 7%|▋ | 5/70 [00:12<02:51, 2.64s/it] 9%|▊ | 6/70 [00:15<02:51, 2.68s/it] 10%|█ | 7/70 [00:18<02:50, 2.71s/it] 11%|█▏ | 8/70 [00:20<02:46, 2.69s/it] 13%|█▎ | 9/70 [00:23<02:43, 2.68s/it] 14%|█▍ | 10/70 [00:26<02:37, 2.63s/it] 16%|█▌ | 11/70 [00:28<02:35, 2.64s/it] 17%|█▋ | 12/70 [00:31<02:34, 2.67s/it] 19%|█▊ | 13/70 [00:34<02:31, 2.65s/it] 20%|██ | 14/70 [00:36<02:29, 2.66s/it] 21%|██▏ | 15/70 [00:39<02:24, 2.63s/it] 23%|██▎ | 16/70 [00:42<02:23, 2.66s/it] 24%|██▍ | 17/70 [00:44<02:15, 2.55s/it] 26%|██▌ | 18/70 [00:46<02:08, 2.47s/it] 27%|██▋ | 19/70 [00:49<02:07, 2.51s/it] 29%|██▊ | 20/70 [00:51<02:07, 2.55s/it] 30%|███ | 21/70 [00:54<02:07, 2.60s/it] 31%|███▏ | 22/70 [00:57<02:05, 2.61s/it] 33%|███▎ | 23/70 [01:00<02:04, 2.66s/it] 34%|███▍ | 24/70 [01:02<02:00, 2.62s/it] 36%|███▌ | 25/70 [01:05<01:59, 2.65s/it] 37%|███▋ | 26/70 [01:07<01:53, 2.58s/it] 39%|███▊ | 27/70 [01:10<01:49, 2.54s/it] 40%|████ | 28/70 [01:12<01:47, 2.56s/it] 41%|████▏ | 29/70 [01:15<01:45, 2.58s/it] 43%|████▎ | 30/70 [01:18<01:43, 2.60s/it] 44%|████▍ | 31/70 [01:20<01:42, 2.62s/it] 46%|████▌ | 32/70 [01:23<01:40, 2.64s/it] 47%|████▋ | 33/70 [01:25<01:35, 2.57s/it] 49%|████▊ | 34/70 [01:28<01:33, 2.60s/it] 50%|█████ | 35/70 [01:30<01:28, 2.53s/it] 51%|█████▏ | 36/70 [01:33<01:26, 2.55s/it] 53%|█████▎ | 37/70 [01:35<01:22, 2.49s/it] 54%|█████▍ | 38/70 [01:38<01:19, 2.48s/it] 56%|█████▌ | 39/70 [01:40<01:18, 2.53s/it] 57%|█████▋ | 40/70 [01:43<01:15, 2.50s/it] 59%|█████▊ | 41/70 [01:45<01:12, 2.49s/it] 60%|██████ | 42/70 [01:48<01:10, 2.50s/it] 61%|██████▏ | 43/70 [01:50<01:06, 2.47s/it] 63%|██████▎ | 44/70 [01:53<01:03, 2.45s/it] 64%|██████▍ | 45/70 [01:55<01:01, 2.47s/it] 66%|██████▌ | 46/70 [01:58<01:00, 2.54s/it] 67%|██████▋ | 47/70 [02:00<00:57, 2.52s/it] 69%|██████▊ | 48/70 [02:03<00:55, 2.51s/it] 70%|███████ | 49/70 [02:05<00:50, 2.41s/it] 71%|███████▏ | 50/70 [02:07<00:48, 2.44s/it] 73%|███████▎ | 51/70 [02:10<00:46, 2.46s/it] 74%|███████▍ | 52/70 [02:13<00:44, 2.50s/it] 76%|███████▌ | 53/70 [02:15<00:41, 2.47s/it] 77%|███████▋ | 54/70 [02:17<00:39, 2.48s/it] 79%|███████▊ | 55/70 [02:20<00:36, 2.45s/it] 80%|████████ | 56/70 [02:22<00:34, 2.44s/it] 81%|████████▏ | 57/70 [02:25<00:31, 2.44s/it] 83%|████████▎ | 58/70 [02:27<00:28, 2.38s/it] 84%|████████▍ | 59/70 [02:29<00:25, 2.31s/it] 86%|████████▌ | 60/70 [02:31<00:22, 2.29s/it] 87%|████████▋ | 61/70 [02:34<00:21, 2.36s/it] 89%|████████▊ | 62/70 [02:36<00:18, 2.27s/it] 90%|█████████ | 63/70 [02:38<00:16, 2.30s/it] 91%|█████████▏| 64/70 [02:41<00:13, 2.28s/it] 93%|█████████▎| 65/70 [02:43<00:11, 2.34s/it] 94%|█████████▍| 66/70 [02:45<00:08, 2.21s/it] 96%|█████████▌| 67/70 [02:47<00:06, 2.23s/it] 97%|█████████▋| 68/70 [02:49<00:04, 2.19s/it] 99%|█████████▊| 69/70 [02:51<00:01, 1.96s/it] 100%|██████████| 70/70 [02:52<00:00, 1.74s/it] 100%|██████████| 70/70 [02:52<00:00, 2.46s/it] Decoding latents in cuda:0... done in 2.41s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.9ms Speed: 3.2ms preprocess, 7.9ms inference, 17.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:01<00:37, 1.22s/it] 6%|▋ | 2/32 [00:02<00:34, 1.13s/it] 9%|▉ | 3/32 [00:03<00:31, 1.10s/it] 12%|█▎ | 4/32 [00:04<00:30, 1.09s/it] 16%|█▌ | 5/32 [00:05<00:28, 1.06s/it] 19%|█▉ | 6/32 [00:06<00:27, 1.07s/it] 22%|██▏ | 7/32 [00:07<00:27, 1.08s/it] 25%|██▌ | 8/32 [00:08<00:26, 1.10s/it] 28%|██▊ | 9/32 [00:09<00:25, 1.10s/it] 31%|███▏ | 10/32 [00:10<00:23, 1.08s/it] 34%|███▍ | 11/32 [00:11<00:21, 1.03s/it] 38%|███▊ | 12/32 [00:12<00:20, 1.03s/it] 41%|████ | 13/32 [00:13<00:19, 1.04s/it] 44%|████▍ | 14/32 [00:15<00:19, 1.06s/it] 47%|████▋ | 15/32 [00:16<00:18, 1.08s/it] 50%|█████ | 16/32 [00:17<00:17, 1.09s/it] 53%|█████▎ | 17/32 [00:18<00:15, 1.06s/it] 56%|█████▋ | 18/32 [00:19<00:14, 1.05s/it] 59%|█████▉ | 19/32 [00:20<00:13, 1.03s/it] 62%|██████▎ | 20/32 [00:21<00:12, 1.01s/it] 66%|██████▌ | 21/32 [00:22<00:10, 1.00it/s] 69%|██████▉ | 22/32 [00:23<00:09, 1.02it/s] 72%|███████▏ | 23/32 [00:24<00:09, 1.00s/it] 75%|███████▌ | 24/32 [00:25<00:07, 1.01it/s] 78%|███████▊ | 25/32 [00:26<00:07, 1.04s/it] 81%|████████▏ | 26/32 [00:27<00:06, 1.03s/it] 84%|████████▍ | 27/32 [00:28<00:05, 1.05s/it] 88%|████████▊ | 28/32 [00:29<00:04, 1.01s/it] 91%|█████████ | 29/32 [00:30<00:03, 1.01s/it] 94%|█████████▍| 30/32 [00:31<00:01, 1.02it/s] 97%|█████████▋| 31/32 [00:31<00:00, 1.11it/s] 100%|██████████| 32/32 [00:32<00:00, 1.23it/s] 100%|██████████| 32/32 [00:32<00:00, 1.02s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.6ms Speed: 3.0ms preprocess, 7.6ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 8.2ms Speed: 3.0ms preprocess, 8.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:01<00:33, 1.09s/it] 6%|▋ | 2/32 [00:02<00:32, 1.08s/it] 9%|▉ | 3/32 [00:03<00:30, 1.07s/it] 12%|█▎ | 4/32 [00:04<00:30, 1.08s/it] 16%|█▌ | 5/32 [00:05<00:28, 1.06s/it] 19%|█▉ | 6/32 [00:06<00:27, 1.05s/it] 22%|██▏ | 7/32 [00:07<00:26, 1.07s/it] 25%|██▌ | 8/32 [00:08<00:26, 1.09s/it] 28%|██▊ | 9/32 [00:09<00:24, 1.07s/it] 31%|███▏ | 10/32 [00:10<00:23, 1.09s/it] 34%|███▍ | 11/32 [00:11<00:22, 1.05s/it] 38%|███▊ | 12/32 [00:12<00:21, 1.05s/it] 41%|████ | 13/32 [00:13<00:20, 1.05s/it] 44%|████▍ | 14/32 [00:14<00:19, 1.06s/it] 47%|████▋ | 15/32 [00:15<00:17, 1.06s/it] 50%|█████ | 16/32 [00:17<00:16, 1.05s/it] 53%|█████▎ | 17/32 [00:18<00:15, 1.04s/it] 56%|█████▋ | 18/32 [00:19<00:14, 1.04s/it] 59%|█████▉ | 19/32 [00:20<00:13, 1.03s/it] 62%|██████▎ | 20/32 [00:21<00:12, 1.01s/it] 66%|██████▌ | 21/32 [00:21<00:10, 1.01it/s] 69%|██████▉ | 22/32 [00:22<00:09, 1.02it/s] 72%|███████▏ | 23/32 [00:23<00:09, 1.00s/it] 75%|███████▌ | 24/32 [00:24<00:07, 1.01it/s] 78%|███████▊ | 25/32 [00:25<00:06, 1.01it/s] 81%|████████▏ | 26/32 [00:26<00:05, 1.02it/s] 84%|████████▍ | 27/32 [00:27<00:04, 1.00it/s] 88%|████████▊ | 28/32 [00:28<00:03, 1.05it/s] 91%|█████████ | 29/32 [00:29<00:02, 1.04it/s] 94%|█████████▍| 30/32 [00:30<00:01, 1.05it/s] 97%|█████████▋| 31/32 [00:31<00:00, 1.14it/s] 100%|██████████| 32/32 [00:32<00:00, 1.21it/s] 100%|██████████| 32/32 [00:32<00:00, 1.00s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.3ms Speed: 2.9ms preprocess, 7.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:01<00:33, 1.08s/it] 6%|▋ | 2/32 [00:02<00:31, 1.04s/it] 9%|▉ | 3/32 [00:03<00:29, 1.03s/it] 12%|█▎ | 4/32 [00:04<00:29, 1.04s/it] 16%|█▌ | 5/32 [00:05<00:27, 1.03s/it] 19%|█▉ | 6/32 [00:06<00:26, 1.03s/it] 22%|██▏ | 7/32 [00:07<00:26, 1.05s/it] 25%|██▌ | 8/32 [00:08<00:25, 1.08s/it] 28%|██▊ | 9/32 [00:09<00:24, 1.07s/it] 31%|███▏ | 10/32 [00:10<00:23, 1.06s/it] 34%|███▍ | 11/32 [00:11<00:21, 1.02s/it] 38%|███▊ | 12/32 [00:12<00:20, 1.02s/it] 41%|████ | 13/32 [00:13<00:19, 1.03s/it] 44%|████▍ | 14/32 [00:14<00:18, 1.04s/it] 47%|████▋ | 15/32 [00:15<00:17, 1.03s/it] 50%|█████ | 16/32 [00:16<00:16, 1.04s/it] 53%|█████▎ | 17/32 [00:17<00:15, 1.04s/it] 56%|█████▋ | 18/32 [00:18<00:14, 1.03s/it] 59%|█████▉ | 19/32 [00:19<00:13, 1.02s/it] 62%|██████▎ | 20/32 [00:20<00:12, 1.00s/it] 66%|██████▌ | 21/32 [00:21<00:10, 1.02it/s] 69%|██████▉ | 22/32 [00:22<00:09, 1.03it/s] 72%|███████▏ | 23/32 [00:23<00:08, 1.01it/s] 75%|███████▌ | 24/32 [00:24<00:07, 1.04it/s] 78%|███████▊ | 25/32 [00:25<00:06, 1.03it/s] 81%|████████▏ | 26/32 [00:26<00:05, 1.03it/s] 84%|████████▍ | 27/32 [00:27<00:04, 1.01it/s] 88%|████████▊ | 28/32 [00:28<00:03, 1.06it/s] 91%|█████████ | 29/32 [00:29<00:02, 1.05it/s] 94%|█████████▍| 30/32 [00:30<00:01, 1.07it/s] 97%|█████████▋| 31/32 [00:30<00:00, 1.16it/s] 100%|██████████| 32/32 [00:31<00:00, 1.27it/s] 100%|██████████| 32/32 [00:31<00:00, 1.02it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.