Version: v1.4
Input
Output
This example was created by sparks
Finished in 117.9 seconds
Setting up the model...
Preparing inputs...
Processing...
Using seed 2232107657
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: a broken ruined cyborg girl in a landfill, robot, beautiful face, body is broken with scars and holes, laying on the ground, 8K, (dynamic perspective), sharp focus, extremely detailed eyes and face, beautiful detailed eyes, hyperpunk scene, cinematic lighting, reflective transparent iridescent opaque jacket, long transparent iridescent RGB hair, ((masterpiece, best quality)), niji, from above, upper body, navel, sachin teng, realism, hyperrealistic, (shallow depth of field, frontal bokeh, light particles flying in air, volumetric light, light caustics, refraction, reflection, v-ray, ray tracing:1.15)
Full negative prompt: makeup, (inconsistent body in background, too long limbs, redundant arm, extra fingers, finger missing, inconsistent anatomy, anatomical defects, deformed eyes, malformed cornea, poorly drawn eyes, deformed eyes, incorrect cornea, absurd eyes, cross-eyed, deformed body, bad hands, incorrect anatomy:1.3), sharp focus on background, blurry image, (no emotions, poker face:1.1), blurry, illustration, drawing, poorly drawn body, poorly drawn nipples, artificial smooth unnatural skin, unreal picture, plastic look, plastic skin, digital art image, underwear, panties, thong
0%| | 0/22 [00:00<?, ?it/s]
5%|▍ | 1/22 [00:03<01:09, 3.30s/it]
9%|▉ | 2/22 [00:06<01:06, 3.31s/it]
14%|█▎ | 3/22 [00:09<01:03, 3.32s/it]
18%|█▊ | 4/22 [00:13<01:00, 3.34s/it]
23%|██▎ | 5/22 [00:16<00:56, 3.35s/it]
27%|██▋ | 6/22 [00:20<00:53, 3.36s/it]
32%|███▏ | 7/22 [00:23<00:50, 3.35s/it]
36%|███▋ | 8/22 [00:26<00:46, 3.35s/it]
41%|████ | 9/22 [00:30<00:43, 3.36s/it]
45%|████▌ | 10/22 [00:33<00:40, 3.36s/it]
50%|█████ | 11/22 [00:36<00:36, 3.36s/it]
55%|█████▍ | 12/22 [00:40<00:33, 3.36s/it]
59%|█████▉ | 13/22 [00:43<00:30, 3.35s/it]
64%|██████▎ | 14/22 [00:46<00:26, 3.34s/it]
68%|██████▊ | 15/22 [00:50<00:23, 3.33s/it]
73%|███████▎ | 16/22 [00:53<00:19, 3.32s/it]
77%|███████▋ | 17/22 [00:56<00:16, 3.32s/it]
82%|████████▏ | 18/22 [01:00<00:13, 3.32s/it]
86%|████████▋ | 19/22 [01:03<00:09, 3.32s/it]
91%|█████████ | 20/22 [01:06<00:06, 3.32s/it]
95%|█████████▌| 21/22 [01:10<00:03, 3.32s/it]
100%|██████████| 22/22 [01:11<00:00, 2.81s/it]
100%|██████████| 22/22 [01:11<00:00, 3.26s/it]
Decoding latents in cuda:0...
done in 2.87s
Move latents to cpu...
done in 0.03s
0: 576x640 1 face, 156.4ms
Speed: 3.1ms preprocess, 156.4ms inference, 31.0ms postprocess per image at shape (1, 3, 576, 640)
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:00<00:05, 1.01it/s]
29%|██▊ | 2/7 [00:01<00:04, 1.03it/s]
43%|████▎ | 3/7 [00:02<00:03, 1.04it/s]
57%|█████▋ | 4/7 [00:03<00:02, 1.04it/s]
71%|███████▏ | 5/7 [00:04<00:01, 1.04it/s]
86%|████████▌ | 6/7 [00:05<00:00, 1.04it/s]
100%|██████████| 7/7 [00:06<00:00, 1.24it/s]
100%|██████████| 7/7 [00:06<00:00, 1.12it/s]
Decoding latents in cuda:0...
done in 0.94s
Move latents to cpu...
done in 0.0s
0: 576x640 (no detections), 101.9ms
Speed: 2.9ms preprocess, 101.9ms inference, 0.8ms postprocess per image at shape (1, 3, 576, 640)
[-] ADetailer: nothing detected on image 1 with 2nd settings.
0: 576x640 1 face, 8.1ms
Speed: 2.8ms preprocess, 8.1ms inference, 1.3ms postprocess per image at shape (1, 3, 576, 640)
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:00<00:05, 1.05it/s]
29%|██▊ | 2/7 [00:01<00:04, 1.04it/s]
43%|████▎ | 3/7 [00:02<00:03, 1.04it/s]
57%|█████▋ | 4/7 [00:03<00:02, 1.04it/s]
71%|███████▏ | 5/7 [00:04<00:01, 1.04it/s]
86%|████████▌ | 6/7 [00:05<00:00, 1.03it/s]
100%|██████████| 7/7 [00:06<00:00, 1.24it/s]
100%|██████████| 7/7 [00:06<00:00, 1.12it/s]
Decoding latents in cuda:0...
done in 0.95s
Move latents to cpu...
done in 0.0s
0: 576x640 (no detections), 7.9ms
Speed: 3.0ms preprocess, 7.9ms inference, 0.8ms postprocess per image at shape (1, 3, 576, 640)
[-] ADetailer: nothing detected on image 2 with 2nd settings.
0: 576x640 2 faces, 8.2ms
Speed: 2.8ms preprocess, 8.2ms inference, 1.6ms postprocess per image at shape (1, 3, 576, 640)
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:00<00:05, 1.04it/s]
29%|██▊ | 2/7 [00:01<00:04, 1.04it/s]
43%|████▎ | 3/7 [00:02<00:03, 1.03it/s]
57%|█████▋ | 4/7 [00:03<00:02, 1.03it/s]
71%|███████▏ | 5/7 [00:04<00:01, 1.03it/s]
86%|████████▌ | 6/7 [00:05<00:00, 1.03it/s]
100%|██████████| 7/7 [00:06<00:00, 1.23it/s]
100%|██████████| 7/7 [00:06<00:00, 1.11it/s]
Decoding latents in cuda:0...
done in 0.95s
Move latents to cpu...
done in 0.0s
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:00<00:05, 1.02it/s]
29%|██▊ | 2/7 [00:01<00:04, 1.02it/s]
43%|████▎ | 3/7 [00:02<00:03, 1.02it/s]
57%|█████▋ | 4/7 [00:03<00:02, 1.02it/s]
71%|███████▏ | 5/7 [00:04<00:01, 1.02it/s]
86%|████████▌ | 6/7 [00:05<00:00, 1.02it/s]
100%|██████████| 7/7 [00:06<00:00, 1.22it/s]
100%|██████████| 7/7 [00:06<00:00, 1.10it/s]
Decoding latents in cuda:0...
done in 0.97s
Move latents to cpu...
done in 0.0s
0: 576x640 (no detections), 7.8ms
Speed: 2.8ms preprocess, 7.8ms inference, 0.7ms postprocess per image at shape (1, 3, 576, 640)
[-] ADetailer: nothing detected on image 3 with 2nd settings.
Uploading outputs...
Finished.
This example was created by sparks
Finished in 117.9 seconds
Setting up the model...
Preparing inputs...
Processing...
Using seed 2232107657
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: a broken ruined cyborg girl in a landfill, robot, beautiful face, body is broken with scars and holes, laying on the ground, 8K, (dynamic perspective), sharp focus, extremely detailed eyes and face, beautiful detailed eyes, hyperpunk scene, cinematic lighting, reflective transparent iridescent opaque jacket, long transparent iridescent RGB hair, ((masterpiece, best quality)), niji, from above, upper body, navel, sachin teng, realism, hyperrealistic, (shallow depth of field, frontal bokeh, light particles flying in air, volumetric light, light caustics, refraction, reflection, v-ray, ray tracing:1.15)
Full negative prompt: makeup, (inconsistent body in background, too long limbs, redundant arm, extra fingers, finger missing, inconsistent anatomy, anatomical defects, deformed eyes, malformed cornea, poorly drawn eyes, deformed eyes, incorrect cornea, absurd eyes, cross-eyed, deformed body, bad hands, incorrect anatomy:1.3), sharp focus on background, blurry image, (no emotions, poker face:1.1), blurry, illustration, drawing, poorly drawn body, poorly drawn nipples, artificial smooth unnatural skin, unreal picture, plastic look, plastic skin, digital art image, underwear, panties, thong
0%| | 0/22 [00:00<?, ?it/s]
5%|▍ | 1/22 [00:03<01:09, 3.30s/it]
9%|▉ | 2/22 [00:06<01:06, 3.31s/it]
14%|█▎ | 3/22 [00:09<01:03, 3.32s/it]
18%|█▊ | 4/22 [00:13<01:00, 3.34s/it]
23%|██▎ | 5/22 [00:16<00:56, 3.35s/it]
27%|██▋ | 6/22 [00:20<00:53, 3.36s/it]
32%|███▏ | 7/22 [00:23<00:50, 3.35s/it]
36%|███▋ | 8/22 [00:26<00:46, 3.35s/it]
41%|████ | 9/22 [00:30<00:43, 3.36s/it]
45%|████▌ | 10/22 [00:33<00:40, 3.36s/it]
50%|█████ | 11/22 [00:36<00:36, 3.36s/it]
55%|█████▍ | 12/22 [00:40<00:33, 3.36s/it]
59%|█████▉ | 13/22 [00:43<00:30, 3.35s/it]
64%|██████▎ | 14/22 [00:46<00:26, 3.34s/it]
68%|██████▊ | 15/22 [00:50<00:23, 3.33s/it]
73%|███████▎ | 16/22 [00:53<00:19, 3.32s/it]
77%|███████▋ | 17/22 [00:56<00:16, 3.32s/it]
82%|████████▏ | 18/22 [01:00<00:13, 3.32s/it]
86%|████████▋ | 19/22 [01:03<00:09, 3.32s/it]
91%|█████████ | 20/22 [01:06<00:06, 3.32s/it]
95%|█████████▌| 21/22 [01:10<00:03, 3.32s/it]
100%|██████████| 22/22 [01:11<00:00, 2.81s/it]
100%|██████████| 22/22 [01:11<00:00, 3.26s/it]
Decoding latents in cuda:0...
done in 2.87s
Move latents to cpu...
done in 0.03s
0: 576x640 1 face, 156.4ms
Speed: 3.1ms preprocess, 156.4ms inference, 31.0ms postprocess per image at shape (1, 3, 576, 640)
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:00<00:05, 1.01it/s]
29%|██▊ | 2/7 [00:01<00:04, 1.03it/s]
43%|████▎ | 3/7 [00:02<00:03, 1.04it/s]
57%|█████▋ | 4/7 [00:03<00:02, 1.04it/s]
71%|███████▏ | 5/7 [00:04<00:01, 1.04it/s]
86%|████████▌ | 6/7 [00:05<00:00, 1.04it/s]
100%|██████████| 7/7 [00:06<00:00, 1.24it/s]
100%|██████████| 7/7 [00:06<00:00, 1.12it/s]
Decoding latents in cuda:0...
done in 0.94s
Move latents to cpu...
done in 0.0s
0: 576x640 (no detections), 101.9ms
Speed: 2.9ms preprocess, 101.9ms inference, 0.8ms postprocess per image at shape (1, 3, 576, 640)
[-] ADetailer: nothing detected on image 1 with 2nd settings.
0: 576x640 1 face, 8.1ms
Speed: 2.8ms preprocess, 8.1ms inference, 1.3ms postprocess per image at shape (1, 3, 576, 640)
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:00<00:05, 1.05it/s]
29%|██▊ | 2/7 [00:01<00:04, 1.04it/s]
43%|████▎ | 3/7 [00:02<00:03, 1.04it/s]
57%|█████▋ | 4/7 [00:03<00:02, 1.04it/s]
71%|███████▏ | 5/7 [00:04<00:01, 1.04it/s]
86%|████████▌ | 6/7 [00:05<00:00, 1.03it/s]
100%|██████████| 7/7 [00:06<00:00, 1.24it/s]
100%|██████████| 7/7 [00:06<00:00, 1.12it/s]
Decoding latents in cuda:0...
done in 0.95s
Move latents to cpu...
done in 0.0s
0: 576x640 (no detections), 7.9ms
Speed: 3.0ms preprocess, 7.9ms inference, 0.8ms postprocess per image at shape (1, 3, 576, 640)
[-] ADetailer: nothing detected on image 2 with 2nd settings.
0: 576x640 2 faces, 8.2ms
Speed: 2.8ms preprocess, 8.2ms inference, 1.6ms postprocess per image at shape (1, 3, 576, 640)
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:00<00:05, 1.04it/s]
29%|██▊ | 2/7 [00:01<00:04, 1.04it/s]
43%|████▎ | 3/7 [00:02<00:03, 1.03it/s]
57%|█████▋ | 4/7 [00:03<00:02, 1.03it/s]
71%|███████▏ | 5/7 [00:04<00:01, 1.03it/s]
86%|████████▌ | 6/7 [00:05<00:00, 1.03it/s]
100%|██████████| 7/7 [00:06<00:00, 1.23it/s]
100%|██████████| 7/7 [00:06<00:00, 1.11it/s]
Decoding latents in cuda:0...
done in 0.95s
Move latents to cpu...
done in 0.0s
0%| | 0/7 [00:00<?, ?it/s]
14%|█▍ | 1/7 [00:00<00:05, 1.02it/s]
29%|██▊ | 2/7 [00:01<00:04, 1.02it/s]
43%|████▎ | 3/7 [00:02<00:03, 1.02it/s]
57%|█████▋ | 4/7 [00:03<00:02, 1.02it/s]
71%|███████▏ | 5/7 [00:04<00:01, 1.02it/s]
86%|████████▌ | 6/7 [00:05<00:00, 1.02it/s]
100%|██████████| 7/7 [00:06<00:00, 1.22it/s]
100%|██████████| 7/7 [00:06<00:00, 1.10it/s]
Decoding latents in cuda:0...
done in 0.97s
Move latents to cpu...
done in 0.0s
0: 576x640 (no detections), 7.8ms
Speed: 2.8ms preprocess, 7.8ms inference, 0.7ms postprocess per image at shape (1, 3, 576, 640)
[-] ADetailer: nothing detected on image 3 with 2nd settings.
Uploading outputs...
Finished.