tungsten-logo
Sign In
Cyborg Construction with Hephaistos SD XL
hephaistos-sd-xl:v3.3
evevalentine2017
evevalentine2017
·
Jan 19
368
Input
prompt
Specify things to see in the output
a very beautiful cyborg made of transparent glossy glass skin surrounded with glowing tubes inside an incubator of a futuristic hospital bio lab, rendered by beeple, by syd meade, by android jones, by yoanne lossel, by artgerm and greg rutkowski, space art concept, sci-fi, digital art, unreal engine, wlop, trending artstation, RAW photo, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
negative_prompt
Specify things to not see in the output
blurry, logo, text, watermark, sign, caption
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1024
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
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
378092565
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
DPM++ 2M SDE Karras
samping_steps
Number of denoising steps
80
cfg_scale
Scale for classifier-free guidance
8
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
sdxl_vae.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)
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.
false
Output
https://files.tungsten.run/uploads/7fe40a1746704eac8b0f2c76062a9c4e/00000-378092565.webp
https://files.tungsten.run/uploads/1c499544ff8841479e5d843477ca46cc/00001-378092566.webp
https://files.tungsten.run/uploads/9b59773a8ace429ebc2f1e21f475db09/00002-378092567.webp
Finished in 324.6 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a very beautiful cyborg made of transparent glossy glass skin surrounded with glowing tubes inside an incubator of a futuristic hospital bio lab, rendered by beeple, by syd meade, by android jones, by yoanne lossel, by artgerm and greg rutkowski, space art concept, sci-fi, digital art, unreal engine, wlop, trending artstation, RAW photo, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 Full negative prompt: blurry, logo, text, watermark, sign, caption 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:02<02:40, 2.03s/it] 2%|▎ | 2/80 [00:04<03:04, 2.37s/it] 4%|▍ | 3/80 [00:07<03:16, 2.56s/it] 5%|▌ | 4/80 [00:10<03:22, 2.66s/it] 6%|▋ | 5/80 [00:12<03:16, 2.62s/it] 8%|▊ | 6/80 [00:15<03:16, 2.66s/it] 9%|▉ | 7/80 [00:18<03:15, 2.68s/it] 10%|█ | 8/80 [00:20<03:12, 2.67s/it] 11%|█▏ | 9/80 [00:23<03:11, 2.69s/it] 12%|█▎ | 10/80 [00:26<03:03, 2.62s/it] 14%|█▍ | 11/80 [00:28<02:58, 2.58s/it] 15%|█▌ | 12/80 [00:31<02:54, 2.56s/it] 16%|█▋ | 13/80 [00:33<02:57, 2.66s/it] 18%|█▊ | 14/80 [00:36<02:55, 2.66s/it] 19%|█▉ | 15/80 [00:39<03:02, 2.80s/it] 20%|██ | 16/80 [00:42<02:54, 2.72s/it] 21%|██▏ | 17/80 [00:45<02:51, 2.73s/it] 22%|██▎ | 18/80 [00:47<02:46, 2.69s/it] 24%|██▍ | 19/80 [00:50<02:40, 2.63s/it] 25%|██▌ | 20/80 [00:52<02:37, 2.63s/it] 26%|██▋ | 21/80 [00:55<02:34, 2.61s/it] 28%|██▊ | 22/80 [00:57<02:29, 2.57s/it] 29%|██▉ | 23/80 [01:00<02:27, 2.58s/it] 30%|███ | 24/80 [01:03<02:25, 2.59s/it] 31%|███▏ | 25/80 [01:05<02:24, 2.63s/it] 32%|███▎ | 26/80 [01:08<02:23, 2.66s/it] 34%|███▍ | 27/80 [01:10<02:18, 2.61s/it] 35%|███▌ | 28/80 [01:13<02:16, 2.63s/it] 36%|███▋ | 29/80 [01:16<02:14, 2.64s/it] 38%|███▊ | 30/80 [01:18<02:10, 2.61s/it] 39%|███▉ | 31/80 [01:21<02:05, 2.56s/it] 40%|████ | 32/80 [01:23<02:02, 2.56s/it] 41%|████▏ | 33/80 [01:26<02:00, 2.56s/it] 42%|████▎ | 34/80 [01:28<01:55, 2.52s/it] 44%|████▍ | 35/80 [01:31<01:57, 2.62s/it] 45%|████▌ | 36/80 [01:34<01:55, 2.63s/it] 46%|████▋ | 37/80 [01:36<01:52, 2.62s/it] 48%|████▊ | 38/80 [01:39<01:47, 2.56s/it] 49%|████▉ | 39/80 [01:42<01:46, 2.60s/it] 50%|█████ | 40/80 [01:44<01:42, 2.56s/it] 51%|█████▏ | 41/80 [01:47<01:38, 2.53s/it] 52%|█████▎ | 42/80 [01:49<01:33, 2.47s/it] 54%|█████▍ | 43/80 [01:51<01:29, 2.41s/it] 55%|█████▌ | 44/80 [01:54<01:30, 2.51s/it] 56%|█████▋ | 45/80 [01:56<01:27, 2.50s/it] 57%|█████▊ | 46/80 [01:59<01:25, 2.52s/it] 59%|█████▉ | 47/80 [02:01<01:22, 2.51s/it] 60%|██████ | 48/80 [02:04<01:21, 2.56s/it] 61%|██████▏ | 49/80 [02:07<01:18, 2.53s/it] 62%|██████▎ | 50/80 [02:09<01:17, 2.57s/it] 64%|██████▍ | 51/80 [02:12<01:15, 2.59s/it] 65%|██████▌ | 52/80 [02:14<01:12, 2.58s/it] 66%|██████▋ | 53/80 [02:17<01:07, 2.51s/it] 68%|██████▊ | 54/80 [02:19<01:04, 2.46s/it] 69%|██████▉ | 55/80 [02:22<01:02, 2.50s/it] 70%|███████ | 56/80 [02:24<00:59, 2.48s/it] 71%|███████▏ | 57/80 [02:26<00:56, 2.45s/it] 72%|███████▎ | 58/80 [02:29<00:53, 2.42s/it] 74%|███████▍ | 59/80 [02:32<00:52, 2.50s/it] 75%|███████▌ | 60/80 [02:34<00:48, 2.45s/it] 76%|███████▋ | 61/80 [02:36<00:45, 2.40s/it] 78%|███████▊ | 62/80 [02:39<00:44, 2.46s/it] 79%|███████▉ | 63/80 [02:41<00:41, 2.41s/it] 80%|████████ | 64/80 [02:44<00:39, 2.47s/it] 81%|████████▏ | 65/80 [02:46<00:36, 2.43s/it] 82%|████████▎ | 66/80 [02:48<00:32, 2.32s/it] 84%|████████▍ | 67/80 [02:50<00:29, 2.30s/it] 85%|████████▌ | 68/80 [02:53<00:28, 2.34s/it] 86%|████████▋ | 69/80 [02:55<00:25, 2.30s/it] 88%|████████▊ | 70/80 [02:57<00:23, 2.36s/it] 89%|████████▉ | 71/80 [03:00<00:20, 2.30s/it] 90%|█████████ | 72/80 [03:02<00:18, 2.29s/it] 91%|█████████▏| 73/80 [03:04<00:15, 2.20s/it] 92%|█████████▎| 74/80 [03:06<00:13, 2.24s/it] 94%|█████████▍| 75/80 [03:08<00:11, 2.22s/it] 95%|█████████▌| 76/80 [03:11<00:09, 2.27s/it] 96%|█████████▋| 77/80 [03:13<00:06, 2.20s/it] 98%|█████████▊| 78/80 [03:15<00:04, 2.22s/it] 99%|█████████▉| 79/80 [03:16<00:01, 1.96s/it] 100%|██████████| 80/80 [03:18<00:00, 1.74s/it] 100%|██████████| 80/80 [03:18<00:00, 2.48s/it] Decoding latents in cuda:0... done in 2.37s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.7ms Speed: 3.2ms preprocess, 7.7ms inference, 20.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/37 [00:00<?, ?it/s] 3%|▎ | 1/37 [00:01<00:44, 1.25s/it] 5%|▌ | 2/37 [00:02<00:38, 1.11s/it] 8%|▊ | 3/37 [00:03<00:36, 1.08s/it] 11%|█ | 4/37 [00:04<00:34, 1.05s/it] 14%|█▎ | 5/37 [00:05<00:33, 1.05s/it] 16%|█▌ | 6/37 [00:06<00:31, 1.03s/it] 19%|█▉ | 7/37 [00:07<00:31, 1.04s/it] 22%|██▏ | 8/37 [00:08<00:29, 1.03s/it] 24%|██▍ | 9/37 [00:09<00:28, 1.03s/it] 27%|██▋ | 10/37 [00:10<00:27, 1.02s/it] 30%|██▉ | 11/37 [00:11<00:26, 1.00s/it] 32%|███▏ | 12/37 [00:12<00:25, 1.02s/it] 35%|███▌ | 13/37 [00:13<00:24, 1.02s/it] 38%|███▊ | 14/37 [00:14<00:23, 1.02s/it] 41%|████ | 15/37 [00:15<00:22, 1.02s/it] 43%|████▎ | 16/37 [00:16<00:22, 1.06s/it] 46%|████▌ | 17/37 [00:17<00:20, 1.03s/it] 49%|████▊ | 18/37 [00:18<00:19, 1.01s/it] 51%|█████▏ | 19/37 [00:19<00:18, 1.05s/it] 54%|█████▍ | 20/37 [00:20<00:17, 1.03s/it] 57%|█████▋ | 21/37 [00:21<00:16, 1.03s/it] 59%|█████▉ | 22/37 [00:22<00:15, 1.01s/it] 62%|██████▏ | 23/37 [00:23<00:13, 1.02it/s] 65%|██████▍ | 24/37 [00:24<00:12, 1.04it/s] 68%|██████▊ | 25/37 [00:25<00:11, 1.03it/s] 70%|███████ | 26/37 [00:26<00:10, 1.05it/s] 73%|███████▎ | 27/37 [00:27<00:09, 1.02it/s] 76%|███████▌ | 28/37 [00:28<00:08, 1.04it/s] 78%|███████▊ | 29/37 [00:29<00:07, 1.04it/s] 81%|████████ | 30/37 [00:30<00:06, 1.08it/s] 84%|████████▍ | 31/37 [00:31<00:05, 1.07it/s] 86%|████████▋ | 32/37 [00:32<00:04, 1.07it/s] 89%|████████▉ | 33/37 [00:33<00:03, 1.06it/s] 92%|█████████▏| 34/37 [00:33<00:02, 1.09it/s] 95%|█████████▍| 35/37 [00:34<00:01, 1.08it/s] 97%|█████████▋| 36/37 [00:35<00:00, 1.19it/s] 100%|██████████| 37/37 [00:36<00:00, 1.30it/s] 100%|██████████| 37/37 [00:36<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), 8.0ms Speed: 3.5ms preprocess, 8.0ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/37 [00:00<?, ?it/s] 3%|▎ | 1/37 [00:01<00:39, 1.10s/it] 5%|▌ | 2/37 [00:02<00:36, 1.04s/it] 8%|▊ | 3/37 [00:03<00:35, 1.03s/it] 11%|█ | 4/37 [00:04<00:33, 1.01s/it] 14%|█▎ | 5/37 [00:05<00:32, 1.03s/it] 16%|█▌ | 6/37 [00:06<00:31, 1.01s/it] 19%|█▉ | 7/37 [00:07<00:30, 1.03s/it] 22%|██▏ | 8/37 [00:08<00:29, 1.02s/it] 24%|██▍ | 9/37 [00:09<00:28, 1.03s/it] 27%|██▋ | 10/37 [00:10<00:27, 1.01s/it] 30%|██▉ | 11/37 [00:11<00:26, 1.01s/it] 32%|███▏ | 12/37 [00:12<00:25, 1.03s/it] 35%|███▌ | 13/37 [00:13<00:24, 1.02s/it] 38%|███▊ | 14/37 [00:14<00:23, 1.02s/it] 41%|████ | 15/37 [00:15<00:22, 1.01s/it] 43%|████▎ | 16/37 [00:16<00:21, 1.04s/it] 46%|████▌ | 17/37 [00:17<00:20, 1.02s/it] 49%|████▊ | 18/37 [00:18<00:19, 1.00s/it] 51%|█████▏ | 19/37 [00:19<00:18, 1.01s/it] 54%|█████▍ | 20/37 [00:20<00:17, 1.01s/it] 57%|█████▋ | 21/37 [00:21<00:16, 1.01s/it] 59%|█████▉ | 22/37 [00:22<00:14, 1.00it/s] 62%|██████▏ | 23/37 [00:23<00:13, 1.04it/s] 65%|██████▍ | 24/37 [00:24<00:12, 1.01it/s] 68%|██████▊ | 25/37 [00:25<00:12, 1.03s/it] 70%|███████ | 26/37 [00:26<00:11, 1.08s/it] 73%|███████▎ | 27/37 [00:27<00:10, 1.06s/it] 76%|███████▌ | 28/37 [00:28<00:09, 1.02s/it] 78%|███████▊ | 29/37 [00:29<00:08, 1.03s/it] 81%|████████ | 30/37 [00:30<00:06, 1.02it/s] 84%|████████▍ | 31/37 [00:31<00:05, 1.01it/s] 86%|████████▋ | 32/37 [00:32<00:04, 1.03it/s] 89%|████████▉ | 33/37 [00:33<00:03, 1.03it/s] 92%|█████████▏| 34/37 [00:34<00:02, 1.07it/s] 95%|█████████▍| 35/37 [00:35<00:01, 1.06it/s] 97%|█████████▋| 36/37 [00:35<00:00, 1.17it/s] 100%|██████████| 37/37 [00:36<00:00, 1.27it/s] 100%|██████████| 37/37 [00:36<00:00, 1.01it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.0ms preprocess, 7.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.6ms Speed: 3.0ms preprocess, 7.6ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/37 [00:00<?, ?it/s] 3%|▎ | 1/37 [00:01<00:39, 1.10s/it] 5%|▌ | 2/37 [00:02<00:36, 1.05s/it] 8%|▊ | 3/37 [00:03<00:35, 1.05s/it] 11%|█ | 4/37 [00:04<00:33, 1.03s/it] 14%|█▎ | 5/37 [00:05<00:33, 1.04s/it] 16%|█▌ | 6/37 [00:06<00:31, 1.02s/it] 19%|█▉ | 7/37 [00:07<00:31, 1.05s/it] 22%|██▏ | 8/37 [00:08<00:29, 1.03s/it] 24%|██▍ | 9/37 [00:09<00:29, 1.04s/it] 27%|██▋ | 10/37 [00:10<00:27, 1.02s/it] 30%|██▉ | 11/37 [00:11<00:26, 1.03s/it] 32%|███▏ | 12/37 [00:12<00:26, 1.04s/it] 35%|███▌ | 13/37 [00:13<00:25, 1.05s/it] 38%|███▊ | 14/37 [00:14<00:24, 1.05s/it] 41%|████ | 15/37 [00:15<00:23, 1.05s/it] 43%|████▎ | 16/37 [00:16<00:22, 1.07s/it] 46%|████▌ | 17/37 [00:17<00:20, 1.04s/it] 49%|████▊ | 18/37 [00:18<00:19, 1.02s/it] 51%|█████▏ | 19/37 [00:19<00:18, 1.03s/it] 54%|█████▍ | 20/37 [00:20<00:17, 1.01s/it] 57%|█████▋ | 21/37 [00:21<00:16, 1.03s/it] 59%|█████▉ | 22/37 [00:22<00:15, 1.03s/it] 62%|██████▏ | 23/37 [00:23<00:13, 1.01it/s] 65%|██████▍ | 24/37 [00:24<00:12, 1.01it/s] 68%|██████▊ | 25/37 [00:25<00:12, 1.01s/it] 70%|███████ | 26/37 [00:26<00:10, 1.00it/s] 73%|███████▎ | 27/37 [00:27<00:10, 1.00s/it] 76%|███████▌ | 28/37 [00:28<00:08, 1.02it/s] 78%|███████▊ | 29/37 [00:29<00:07, 1.02it/s] 81%|████████ | 30/37 [00:30<00:06, 1.04it/s] 84%|████████▍ | 31/37 [00:31<00:05, 1.02it/s] 86%|████████▋ | 32/37 [00:32<00:04, 1.03it/s] 89%|████████▉ | 33/37 [00:33<00:03, 1.02it/s] 92%|█████████▏| 34/37 [00:34<00:02, 1.04it/s] 95%|█████████▍| 35/37 [00:35<00:01, 1.03it/s] 97%|█████████▋| 36/37 [00:36<00:00, 1.14it/s] 100%|██████████| 37/37 [00:36<00:00, 1.26it/s] 100%|██████████| 37/37 [00:36<00:00, 1.01it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.2ms preprocess, 7.2ms 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
a very beautiful cyborg made of transparent glossy glass skin surrounded with glowing tubes inside an incubator of a futuristic hospital bio lab, rendered by beeple, by syd meade, by android jones, by yoanne lossel, by artgerm and greg rutkowski, space art concept, sci-fi, digital art, unreal engine, wlop, trending artstation, RAW photo, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
negative_prompt
Specify things to not see in the output
blurry, logo, text, watermark, sign, caption
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1024
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
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
378092565
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
DPM++ 2M SDE Karras
samping_steps
Number of denoising steps
80
cfg_scale
Scale for classifier-free guidance
8
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
sdxl_vae.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)
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.
false
https://files.tungsten.run/uploads/7fe40a1746704eac8b0f2c76062a9c4e/00000-378092565.webp
https://files.tungsten.run/uploads/1c499544ff8841479e5d843477ca46cc/00001-378092566.webp
https://files.tungsten.run/uploads/9b59773a8ace429ebc2f1e21f475db09/00002-378092567.webp
Finished in 324.6 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a very beautiful cyborg made of transparent glossy glass skin surrounded with glowing tubes inside an incubator of a futuristic hospital bio lab, rendered by beeple, by syd meade, by android jones, by yoanne lossel, by artgerm and greg rutkowski, space art concept, sci-fi, digital art, unreal engine, wlop, trending artstation, RAW photo, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 Full negative prompt: blurry, logo, text, watermark, sign, caption 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:02<02:40, 2.03s/it] 2%|▎ | 2/80 [00:04<03:04, 2.37s/it] 4%|▍ | 3/80 [00:07<03:16, 2.56s/it] 5%|▌ | 4/80 [00:10<03:22, 2.66s/it] 6%|▋ | 5/80 [00:12<03:16, 2.62s/it] 8%|▊ | 6/80 [00:15<03:16, 2.66s/it] 9%|▉ | 7/80 [00:18<03:15, 2.68s/it] 10%|█ | 8/80 [00:20<03:12, 2.67s/it] 11%|█▏ | 9/80 [00:23<03:11, 2.69s/it] 12%|█▎ | 10/80 [00:26<03:03, 2.62s/it] 14%|█▍ | 11/80 [00:28<02:58, 2.58s/it] 15%|█▌ | 12/80 [00:31<02:54, 2.56s/it] 16%|█▋ | 13/80 [00:33<02:57, 2.66s/it] 18%|█▊ | 14/80 [00:36<02:55, 2.66s/it] 19%|█▉ | 15/80 [00:39<03:02, 2.80s/it] 20%|██ | 16/80 [00:42<02:54, 2.72s/it] 21%|██▏ | 17/80 [00:45<02:51, 2.73s/it] 22%|██▎ | 18/80 [00:47<02:46, 2.69s/it] 24%|██▍ | 19/80 [00:50<02:40, 2.63s/it] 25%|██▌ | 20/80 [00:52<02:37, 2.63s/it] 26%|██▋ | 21/80 [00:55<02:34, 2.61s/it] 28%|██▊ | 22/80 [00:57<02:29, 2.57s/it] 29%|██▉ | 23/80 [01:00<02:27, 2.58s/it] 30%|███ | 24/80 [01:03<02:25, 2.59s/it] 31%|███▏ | 25/80 [01:05<02:24, 2.63s/it] 32%|███▎ | 26/80 [01:08<02:23, 2.66s/it] 34%|███▍ | 27/80 [01:10<02:18, 2.61s/it] 35%|███▌ | 28/80 [01:13<02:16, 2.63s/it] 36%|███▋ | 29/80 [01:16<02:14, 2.64s/it] 38%|███▊ | 30/80 [01:18<02:10, 2.61s/it] 39%|███▉ | 31/80 [01:21<02:05, 2.56s/it] 40%|████ | 32/80 [01:23<02:02, 2.56s/it] 41%|████▏ | 33/80 [01:26<02:00, 2.56s/it] 42%|████▎ | 34/80 [01:28<01:55, 2.52s/it] 44%|████▍ | 35/80 [01:31<01:57, 2.62s/it] 45%|████▌ | 36/80 [01:34<01:55, 2.63s/it] 46%|████▋ | 37/80 [01:36<01:52, 2.62s/it] 48%|████▊ | 38/80 [01:39<01:47, 2.56s/it] 49%|████▉ | 39/80 [01:42<01:46, 2.60s/it] 50%|█████ | 40/80 [01:44<01:42, 2.56s/it] 51%|█████▏ | 41/80 [01:47<01:38, 2.53s/it] 52%|█████▎ | 42/80 [01:49<01:33, 2.47s/it] 54%|█████▍ | 43/80 [01:51<01:29, 2.41s/it] 55%|█████▌ | 44/80 [01:54<01:30, 2.51s/it] 56%|█████▋ | 45/80 [01:56<01:27, 2.50s/it] 57%|█████▊ | 46/80 [01:59<01:25, 2.52s/it] 59%|█████▉ | 47/80 [02:01<01:22, 2.51s/it] 60%|██████ | 48/80 [02:04<01:21, 2.56s/it] 61%|██████▏ | 49/80 [02:07<01:18, 2.53s/it] 62%|██████▎ | 50/80 [02:09<01:17, 2.57s/it] 64%|██████▍ | 51/80 [02:12<01:15, 2.59s/it] 65%|██████▌ | 52/80 [02:14<01:12, 2.58s/it] 66%|██████▋ | 53/80 [02:17<01:07, 2.51s/it] 68%|██████▊ | 54/80 [02:19<01:04, 2.46s/it] 69%|██████▉ | 55/80 [02:22<01:02, 2.50s/it] 70%|███████ | 56/80 [02:24<00:59, 2.48s/it] 71%|███████▏ | 57/80 [02:26<00:56, 2.45s/it] 72%|███████▎ | 58/80 [02:29<00:53, 2.42s/it] 74%|███████▍ | 59/80 [02:32<00:52, 2.50s/it] 75%|███████▌ | 60/80 [02:34<00:48, 2.45s/it] 76%|███████▋ | 61/80 [02:36<00:45, 2.40s/it] 78%|███████▊ | 62/80 [02:39<00:44, 2.46s/it] 79%|███████▉ | 63/80 [02:41<00:41, 2.41s/it] 80%|████████ | 64/80 [02:44<00:39, 2.47s/it] 81%|████████▏ | 65/80 [02:46<00:36, 2.43s/it] 82%|████████▎ | 66/80 [02:48<00:32, 2.32s/it] 84%|████████▍ | 67/80 [02:50<00:29, 2.30s/it] 85%|████████▌ | 68/80 [02:53<00:28, 2.34s/it] 86%|████████▋ | 69/80 [02:55<00:25, 2.30s/it] 88%|████████▊ | 70/80 [02:57<00:23, 2.36s/it] 89%|████████▉ | 71/80 [03:00<00:20, 2.30s/it] 90%|█████████ | 72/80 [03:02<00:18, 2.29s/it] 91%|█████████▏| 73/80 [03:04<00:15, 2.20s/it] 92%|█████████▎| 74/80 [03:06<00:13, 2.24s/it] 94%|█████████▍| 75/80 [03:08<00:11, 2.22s/it] 95%|█████████▌| 76/80 [03:11<00:09, 2.27s/it] 96%|█████████▋| 77/80 [03:13<00:06, 2.20s/it] 98%|█████████▊| 78/80 [03:15<00:04, 2.22s/it] 99%|█████████▉| 79/80 [03:16<00:01, 1.96s/it] 100%|██████████| 80/80 [03:18<00:00, 1.74s/it] 100%|██████████| 80/80 [03:18<00:00, 2.48s/it] Decoding latents in cuda:0... done in 2.37s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.7ms Speed: 3.2ms preprocess, 7.7ms inference, 20.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/37 [00:00<?, ?it/s] 3%|▎ | 1/37 [00:01<00:44, 1.25s/it] 5%|▌ | 2/37 [00:02<00:38, 1.11s/it] 8%|▊ | 3/37 [00:03<00:36, 1.08s/it] 11%|█ | 4/37 [00:04<00:34, 1.05s/it] 14%|█▎ | 5/37 [00:05<00:33, 1.05s/it] 16%|█▌ | 6/37 [00:06<00:31, 1.03s/it] 19%|█▉ | 7/37 [00:07<00:31, 1.04s/it] 22%|██▏ | 8/37 [00:08<00:29, 1.03s/it] 24%|██▍ | 9/37 [00:09<00:28, 1.03s/it] 27%|██▋ | 10/37 [00:10<00:27, 1.02s/it] 30%|██▉ | 11/37 [00:11<00:26, 1.00s/it] 32%|███▏ | 12/37 [00:12<00:25, 1.02s/it] 35%|███▌ | 13/37 [00:13<00:24, 1.02s/it] 38%|███▊ | 14/37 [00:14<00:23, 1.02s/it] 41%|████ | 15/37 [00:15<00:22, 1.02s/it] 43%|████▎ | 16/37 [00:16<00:22, 1.06s/it] 46%|████▌ | 17/37 [00:17<00:20, 1.03s/it] 49%|████▊ | 18/37 [00:18<00:19, 1.01s/it] 51%|█████▏ | 19/37 [00:19<00:18, 1.05s/it] 54%|█████▍ | 20/37 [00:20<00:17, 1.03s/it] 57%|█████▋ | 21/37 [00:21<00:16, 1.03s/it] 59%|█████▉ | 22/37 [00:22<00:15, 1.01s/it] 62%|██████▏ | 23/37 [00:23<00:13, 1.02it/s] 65%|██████▍ | 24/37 [00:24<00:12, 1.04it/s] 68%|██████▊ | 25/37 [00:25<00:11, 1.03it/s] 70%|███████ | 26/37 [00:26<00:10, 1.05it/s] 73%|███████▎ | 27/37 [00:27<00:09, 1.02it/s] 76%|███████▌ | 28/37 [00:28<00:08, 1.04it/s] 78%|███████▊ | 29/37 [00:29<00:07, 1.04it/s] 81%|████████ | 30/37 [00:30<00:06, 1.08it/s] 84%|████████▍ | 31/37 [00:31<00:05, 1.07it/s] 86%|████████▋ | 32/37 [00:32<00:04, 1.07it/s] 89%|████████▉ | 33/37 [00:33<00:03, 1.06it/s] 92%|█████████▏| 34/37 [00:33<00:02, 1.09it/s] 95%|█████████▍| 35/37 [00:34<00:01, 1.08it/s] 97%|█████████▋| 36/37 [00:35<00:00, 1.19it/s] 100%|██████████| 37/37 [00:36<00:00, 1.30it/s] 100%|██████████| 37/37 [00:36<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), 8.0ms Speed: 3.5ms preprocess, 8.0ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/37 [00:00<?, ?it/s] 3%|▎ | 1/37 [00:01<00:39, 1.10s/it] 5%|▌ | 2/37 [00:02<00:36, 1.04s/it] 8%|▊ | 3/37 [00:03<00:35, 1.03s/it] 11%|█ | 4/37 [00:04<00:33, 1.01s/it] 14%|█▎ | 5/37 [00:05<00:32, 1.03s/it] 16%|█▌ | 6/37 [00:06<00:31, 1.01s/it] 19%|█▉ | 7/37 [00:07<00:30, 1.03s/it] 22%|██▏ | 8/37 [00:08<00:29, 1.02s/it] 24%|██▍ | 9/37 [00:09<00:28, 1.03s/it] 27%|██▋ | 10/37 [00:10<00:27, 1.01s/it] 30%|██▉ | 11/37 [00:11<00:26, 1.01s/it] 32%|███▏ | 12/37 [00:12<00:25, 1.03s/it] 35%|███▌ | 13/37 [00:13<00:24, 1.02s/it] 38%|███▊ | 14/37 [00:14<00:23, 1.02s/it] 41%|████ | 15/37 [00:15<00:22, 1.01s/it] 43%|████▎ | 16/37 [00:16<00:21, 1.04s/it] 46%|████▌ | 17/37 [00:17<00:20, 1.02s/it] 49%|████▊ | 18/37 [00:18<00:19, 1.00s/it] 51%|█████▏ | 19/37 [00:19<00:18, 1.01s/it] 54%|█████▍ | 20/37 [00:20<00:17, 1.01s/it] 57%|█████▋ | 21/37 [00:21<00:16, 1.01s/it] 59%|█████▉ | 22/37 [00:22<00:14, 1.00it/s] 62%|██████▏ | 23/37 [00:23<00:13, 1.04it/s] 65%|██████▍ | 24/37 [00:24<00:12, 1.01it/s] 68%|██████▊ | 25/37 [00:25<00:12, 1.03s/it] 70%|███████ | 26/37 [00:26<00:11, 1.08s/it] 73%|███████▎ | 27/37 [00:27<00:10, 1.06s/it] 76%|███████▌ | 28/37 [00:28<00:09, 1.02s/it] 78%|███████▊ | 29/37 [00:29<00:08, 1.03s/it] 81%|████████ | 30/37 [00:30<00:06, 1.02it/s] 84%|████████▍ | 31/37 [00:31<00:05, 1.01it/s] 86%|████████▋ | 32/37 [00:32<00:04, 1.03it/s] 89%|████████▉ | 33/37 [00:33<00:03, 1.03it/s] 92%|█████████▏| 34/37 [00:34<00:02, 1.07it/s] 95%|█████████▍| 35/37 [00:35<00:01, 1.06it/s] 97%|█████████▋| 36/37 [00:35<00:00, 1.17it/s] 100%|██████████| 37/37 [00:36<00:00, 1.27it/s] 100%|██████████| 37/37 [00:36<00:00, 1.01it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.0ms preprocess, 7.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.6ms Speed: 3.0ms preprocess, 7.6ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/37 [00:00<?, ?it/s] 3%|▎ | 1/37 [00:01<00:39, 1.10s/it] 5%|▌ | 2/37 [00:02<00:36, 1.05s/it] 8%|▊ | 3/37 [00:03<00:35, 1.05s/it] 11%|█ | 4/37 [00:04<00:33, 1.03s/it] 14%|█▎ | 5/37 [00:05<00:33, 1.04s/it] 16%|█▌ | 6/37 [00:06<00:31, 1.02s/it] 19%|█▉ | 7/37 [00:07<00:31, 1.05s/it] 22%|██▏ | 8/37 [00:08<00:29, 1.03s/it] 24%|██▍ | 9/37 [00:09<00:29, 1.04s/it] 27%|██▋ | 10/37 [00:10<00:27, 1.02s/it] 30%|██▉ | 11/37 [00:11<00:26, 1.03s/it] 32%|███▏ | 12/37 [00:12<00:26, 1.04s/it] 35%|███▌ | 13/37 [00:13<00:25, 1.05s/it] 38%|███▊ | 14/37 [00:14<00:24, 1.05s/it] 41%|████ | 15/37 [00:15<00:23, 1.05s/it] 43%|████▎ | 16/37 [00:16<00:22, 1.07s/it] 46%|████▌ | 17/37 [00:17<00:20, 1.04s/it] 49%|████▊ | 18/37 [00:18<00:19, 1.02s/it] 51%|█████▏ | 19/37 [00:19<00:18, 1.03s/it] 54%|█████▍ | 20/37 [00:20<00:17, 1.01s/it] 57%|█████▋ | 21/37 [00:21<00:16, 1.03s/it] 59%|█████▉ | 22/37 [00:22<00:15, 1.03s/it] 62%|██████▏ | 23/37 [00:23<00:13, 1.01it/s] 65%|██████▍ | 24/37 [00:24<00:12, 1.01it/s] 68%|██████▊ | 25/37 [00:25<00:12, 1.01s/it] 70%|███████ | 26/37 [00:26<00:10, 1.00it/s] 73%|███████▎ | 27/37 [00:27<00:10, 1.00s/it] 76%|███████▌ | 28/37 [00:28<00:08, 1.02it/s] 78%|███████▊ | 29/37 [00:29<00:07, 1.02it/s] 81%|████████ | 30/37 [00:30<00:06, 1.04it/s] 84%|████████▍ | 31/37 [00:31<00:05, 1.02it/s] 86%|████████▋ | 32/37 [00:32<00:04, 1.03it/s] 89%|████████▉ | 33/37 [00:33<00:03, 1.02it/s] 92%|█████████▏| 34/37 [00:34<00:02, 1.04it/s] 95%|█████████▍| 35/37 [00:35<00:01, 1.03it/s] 97%|█████████▋| 36/37 [00:36<00:00, 1.14it/s] 100%|██████████| 37/37 [00:36<00:00, 1.26it/s] 100%|██████████| 37/37 [00:36<00:00, 1.01it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.2ms preprocess, 7.2ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.