Version: photoRealSlimA
Input
Output
This example was created by sparks
Finished in 113.4 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: painting by Yoshitaka Amano, Art nouveau frame, Japanese woodcut, 1800s Victorian painting, a female soldier, neon-pastel medieval battlefield, dynamic Scene, medium full shot, dutch angle,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0>
Full negative prompt: Clear, high quality, absence of JPEG artifacts, well-framed, devoid of watermarks, signatures, distortions, or mutations, correct proportions, clear background, focused, free from painting, framing, drawing, sketching, camera-rendering, and cropping elements, no watermarks, logos, barcodes, UI elements, signatures, text, labels, errors, titles, stickers, markings, speech bubbles, lines, low resolution, low quality, amateurish, low-rated, phone photography, wedding-related, framed, painted, Tumblr-style, and HDR or Terragen effects, without high contrast, Chinese characters, NSFW content, yellow tint, pubic hair, sketch duplications, oversized eyes, text, logos, or monochromatic tones
0%| | 0/40 [00:00<?, ?it/s]
2%|▎ | 1/40 [00:03<02:26, 3.75s/it]
5%|▌ | 2/40 [00:06<01:59, 3.15s/it]
8%|▊ | 3/40 [00:09<01:53, 3.06s/it]
10%|█ | 4/40 [00:12<01:45, 2.93s/it]
12%|█▎ | 5/40 [00:15<01:41, 2.90s/it]
15%|█▌ | 6/40 [00:17<01:39, 2.92s/it]
18%|█▊ | 7/40 [00:20<01:35, 2.90s/it]
20%|██ | 8/40 [00:23<01:32, 2.90s/it]
22%|██▎ | 9/40 [00:26<01:28, 2.86s/it]
25%|██▌ | 10/40 [00:29<01:23, 2.80s/it]
28%|██▊ | 11/40 [00:31<01:21, 2.80s/it]
30%|███ | 12/40 [00:34<01:19, 2.83s/it]
32%|███▎ | 13/40 [00:37<01:15, 2.80s/it]
35%|███▌ | 14/40 [00:40<01:12, 2.79s/it]
38%|███▊ | 15/40 [00:43<01:08, 2.76s/it]
40%|████ | 16/40 [00:45<01:04, 2.71s/it]
42%|████▎ | 17/40 [00:48<01:01, 2.68s/it]
45%|████▌ | 18/40 [00:50<00:58, 2.67s/it]
48%|████▊ | 19/40 [00:53<00:54, 2.60s/it]
50%|█████ | 20/40 [00:55<00:51, 2.57s/it]
52%|█████▎ | 21/40 [00:58<00:50, 2.64s/it]
55%|█████▌ | 22/40 [01:01<00:47, 2.66s/it]
57%|█████▊ | 23/40 [01:03<00:43, 2.58s/it]
60%|██████ | 24/40 [01:06<00:40, 2.51s/it]
62%|██████▎ | 25/40 [01:08<00:38, 2.55s/it]
65%|██████▌ | 26/40 [01:11<00:37, 2.67s/it]
68%|██████▊ | 27/40 [01:14<00:35, 2.77s/it]
70%|███████ | 28/40 [01:18<00:35, 2.95s/it]
72%|███████▎ | 29/40 [01:20<00:30, 2.80s/it]
75%|███████▌ | 30/40 [01:23<00:27, 2.77s/it]
78%|███████▊ | 31/40 [01:25<00:23, 2.65s/it]
80%|████████ | 32/40 [01:27<00:20, 2.55s/it]
82%|████████▎ | 33/40 [01:30<00:17, 2.54s/it]
85%|████████▌ | 34/40 [01:32<00:14, 2.45s/it]
88%|████████▊ | 35/40 [01:34<00:12, 2.41s/it]
90%|█████████ | 36/40 [01:37<00:09, 2.44s/it]
92%|█████████▎| 37/40 [01:39<00:07, 2.39s/it]
95%|█████████▌| 38/40 [01:41<00:04, 2.30s/it]
98%|█████████▊| 39/40 [01:43<00:02, 2.04s/it]
100%|██████████| 40/40 [01:44<00:00, 1.82s/it]
100%|██████████| 40/40 [01:44<00:00, 2.61s/it]
Decoding latents in cuda:0...
done in 2.46s
Move latents to cpu...
done in 0.03s
Uploading outputs...
Finished.
This example was created by sparks
Finished in 113.4 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: painting by Yoshitaka Amano, Art nouveau frame, Japanese woodcut, 1800s Victorian painting, a female soldier, neon-pastel medieval battlefield, dynamic Scene, medium full shot, dutch angle,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0>
Full negative prompt: Clear, high quality, absence of JPEG artifacts, well-framed, devoid of watermarks, signatures, distortions, or mutations, correct proportions, clear background, focused, free from painting, framing, drawing, sketching, camera-rendering, and cropping elements, no watermarks, logos, barcodes, UI elements, signatures, text, labels, errors, titles, stickers, markings, speech bubbles, lines, low resolution, low quality, amateurish, low-rated, phone photography, wedding-related, framed, painted, Tumblr-style, and HDR or Terragen effects, without high contrast, Chinese characters, NSFW content, yellow tint, pubic hair, sketch duplications, oversized eyes, text, logos, or monochromatic tones
0%| | 0/40 [00:00<?, ?it/s]
2%|▎ | 1/40 [00:03<02:26, 3.75s/it]
5%|▌ | 2/40 [00:06<01:59, 3.15s/it]
8%|▊ | 3/40 [00:09<01:53, 3.06s/it]
10%|█ | 4/40 [00:12<01:45, 2.93s/it]
12%|█▎ | 5/40 [00:15<01:41, 2.90s/it]
15%|█▌ | 6/40 [00:17<01:39, 2.92s/it]
18%|█▊ | 7/40 [00:20<01:35, 2.90s/it]
20%|██ | 8/40 [00:23<01:32, 2.90s/it]
22%|██▎ | 9/40 [00:26<01:28, 2.86s/it]
25%|██▌ | 10/40 [00:29<01:23, 2.80s/it]
28%|██▊ | 11/40 [00:31<01:21, 2.80s/it]
30%|███ | 12/40 [00:34<01:19, 2.83s/it]
32%|███▎ | 13/40 [00:37<01:15, 2.80s/it]
35%|███▌ | 14/40 [00:40<01:12, 2.79s/it]
38%|███▊ | 15/40 [00:43<01:08, 2.76s/it]
40%|████ | 16/40 [00:45<01:04, 2.71s/it]
42%|████▎ | 17/40 [00:48<01:01, 2.68s/it]
45%|████▌ | 18/40 [00:50<00:58, 2.67s/it]
48%|████▊ | 19/40 [00:53<00:54, 2.60s/it]
50%|█████ | 20/40 [00:55<00:51, 2.57s/it]
52%|█████▎ | 21/40 [00:58<00:50, 2.64s/it]
55%|█████▌ | 22/40 [01:01<00:47, 2.66s/it]
57%|█████▊ | 23/40 [01:03<00:43, 2.58s/it]
60%|██████ | 24/40 [01:06<00:40, 2.51s/it]
62%|██████▎ | 25/40 [01:08<00:38, 2.55s/it]
65%|██████▌ | 26/40 [01:11<00:37, 2.67s/it]
68%|██████▊ | 27/40 [01:14<00:35, 2.77s/it]
70%|███████ | 28/40 [01:18<00:35, 2.95s/it]
72%|███████▎ | 29/40 [01:20<00:30, 2.80s/it]
75%|███████▌ | 30/40 [01:23<00:27, 2.77s/it]
78%|███████▊ | 31/40 [01:25<00:23, 2.65s/it]
80%|████████ | 32/40 [01:27<00:20, 2.55s/it]
82%|████████▎ | 33/40 [01:30<00:17, 2.54s/it]
85%|████████▌ | 34/40 [01:32<00:14, 2.45s/it]
88%|████████▊ | 35/40 [01:34<00:12, 2.41s/it]
90%|█████████ | 36/40 [01:37<00:09, 2.44s/it]
92%|█████████▎| 37/40 [01:39<00:07, 2.39s/it]
95%|█████████▌| 38/40 [01:41<00:04, 2.30s/it]
98%|█████████▊| 39/40 [01:43<00:02, 2.04s/it]
100%|██████████| 40/40 [01:44<00:00, 1.82s/it]
100%|██████████| 40/40 [01:44<00:00, 2.61s/it]
Decoding latents in cuda:0...
done in 2.46s
Move latents to cpu...
done in 0.03s
Uploading outputs...
Finished.