Version: v4.0
Input
Output
This example was created by sparks
Finished in 59.6 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: 1girl, teen (white sailor-fuku, short sleeve, deep blue collar, deep blue skirt, red neckerchief:1.5), (cute, sweet, tareme, red glasses, black hair:1.4) (smile:1.2) long hair, straight hear, bangs pinned back, short tall, cowboy shot (in classroom, hands behind back:1.5) (stand up:1.2), japanese, japanese idol, black eyes (best quality, ultra high res, Realistic, RAW photo, real person, portrait photography, photorealistic, detailed skin, fair skin, beautiful detailed eyes) , <lora:add-detail-xl:1.0>
Full negative prompt: elf, animal ear, skinny, choker (mask) (hands:1.4) worst quality, low quality, normal quality, out of focus, blurry, bokeh, ugly, bad anatomy, error, lowres, missing limb, bad hands, missing fingers, extra digit, fewer digits (monochrome, grayscale, backlight:1.4)
0%| | 0/40 [00:00<?, ?it/s]
2%|▎ | 1/40 [00:02<01:44, 2.69s/it]
5%|▌ | 2/40 [00:03<01:10, 1.86s/it]
8%|▊ | 3/40 [00:05<00:58, 1.59s/it]
10%|█ | 4/40 [00:06<00:52, 1.47s/it]
12%|█▎ | 5/40 [00:07<00:48, 1.40s/it]
15%|█▌ | 6/40 [00:09<00:46, 1.36s/it]
18%|█▊ | 7/40 [00:10<00:43, 1.33s/it]
20%|██ | 8/40 [00:11<00:41, 1.31s/it]
22%|██▎ | 9/40 [00:12<00:40, 1.30s/it]
25%|██▌ | 10/40 [00:14<00:38, 1.29s/it]
28%|██▊ | 11/40 [00:15<00:37, 1.29s/it]
30%|███ | 12/40 [00:16<00:35, 1.28s/it]
32%|███▎ | 13/40 [00:17<00:34, 1.28s/it]
35%|███▌ | 14/40 [00:19<00:33, 1.28s/it]
38%|███▊ | 15/40 [00:20<00:31, 1.28s/it]
40%|████ | 16/40 [00:21<00:30, 1.29s/it]
42%|████▎ | 17/40 [00:23<00:29, 1.30s/it]
45%|████▌ | 18/40 [00:24<00:28, 1.30s/it]
48%|████▊ | 19/40 [00:25<00:27, 1.30s/it]
50%|█████ | 20/40 [00:27<00:25, 1.29s/it]
52%|█████▎ | 21/40 [00:28<00:24, 1.29s/it]
55%|█████▌ | 22/40 [00:29<00:23, 1.28s/it]
57%|█████▊ | 23/40 [00:30<00:21, 1.28s/it]
60%|██████ | 24/40 [00:32<00:20, 1.28s/it]
62%|██████▎ | 25/40 [00:33<00:19, 1.27s/it]
65%|██████▌ | 26/40 [00:34<00:17, 1.27s/it]
68%|██████▊ | 27/40 [00:35<00:16, 1.28s/it]
70%|███████ | 28/40 [00:37<00:15, 1.28s/it]
72%|███████▎ | 29/40 [00:38<00:14, 1.28s/it]
75%|███████▌ | 30/40 [00:39<00:12, 1.28s/it]
78%|███████▊ | 31/40 [00:41<00:11, 1.28s/it]
80%|████████ | 32/40 [00:42<00:10, 1.28s/it]
82%|████████▎ | 33/40 [00:43<00:08, 1.28s/it]
85%|████████▌ | 34/40 [00:44<00:07, 1.27s/it]
88%|████████▊ | 35/40 [00:46<00:06, 1.27s/it]
90%|█████████ | 36/40 [00:47<00:05, 1.27s/it]
92%|█████████▎| 37/40 [00:48<00:03, 1.27s/it]
95%|█████████▌| 38/40 [00:49<00:02, 1.27s/it]
98%|█████████▊| 39/40 [00:51<00:01, 1.27s/it]
100%|██████████| 40/40 [00:52<00:00, 1.26s/it]
100%|██████████| 40/40 [00:52<00:00, 1.31s/it]
Decoding latents in cuda:0...
done in 2.4s
Move latents to cpu...
done in 0.03s
This example was created by sparks
Finished in 59.6 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: 1girl, teen (white sailor-fuku, short sleeve, deep blue collar, deep blue skirt, red neckerchief:1.5), (cute, sweet, tareme, red glasses, black hair:1.4) (smile:1.2) long hair, straight hear, bangs pinned back, short tall, cowboy shot (in classroom, hands behind back:1.5) (stand up:1.2), japanese, japanese idol, black eyes (best quality, ultra high res, Realistic, RAW photo, real person, portrait photography, photorealistic, detailed skin, fair skin, beautiful detailed eyes) , <lora:add-detail-xl:1.0>
Full negative prompt: elf, animal ear, skinny, choker (mask) (hands:1.4) worst quality, low quality, normal quality, out of focus, blurry, bokeh, ugly, bad anatomy, error, lowres, missing limb, bad hands, missing fingers, extra digit, fewer digits (monochrome, grayscale, backlight:1.4)
0%| | 0/40 [00:00<?, ?it/s]
2%|▎ | 1/40 [00:02<01:44, 2.69s/it]
5%|▌ | 2/40 [00:03<01:10, 1.86s/it]
8%|▊ | 3/40 [00:05<00:58, 1.59s/it]
10%|█ | 4/40 [00:06<00:52, 1.47s/it]
12%|█▎ | 5/40 [00:07<00:48, 1.40s/it]
15%|█▌ | 6/40 [00:09<00:46, 1.36s/it]
18%|█▊ | 7/40 [00:10<00:43, 1.33s/it]
20%|██ | 8/40 [00:11<00:41, 1.31s/it]
22%|██▎ | 9/40 [00:12<00:40, 1.30s/it]
25%|██▌ | 10/40 [00:14<00:38, 1.29s/it]
28%|██▊ | 11/40 [00:15<00:37, 1.29s/it]
30%|███ | 12/40 [00:16<00:35, 1.28s/it]
32%|███▎ | 13/40 [00:17<00:34, 1.28s/it]
35%|███▌ | 14/40 [00:19<00:33, 1.28s/it]
38%|███▊ | 15/40 [00:20<00:31, 1.28s/it]
40%|████ | 16/40 [00:21<00:30, 1.29s/it]
42%|████▎ | 17/40 [00:23<00:29, 1.30s/it]
45%|████▌ | 18/40 [00:24<00:28, 1.30s/it]
48%|████▊ | 19/40 [00:25<00:27, 1.30s/it]
50%|█████ | 20/40 [00:27<00:25, 1.29s/it]
52%|█████▎ | 21/40 [00:28<00:24, 1.29s/it]
55%|█████▌ | 22/40 [00:29<00:23, 1.28s/it]
57%|█████▊ | 23/40 [00:30<00:21, 1.28s/it]
60%|██████ | 24/40 [00:32<00:20, 1.28s/it]
62%|██████▎ | 25/40 [00:33<00:19, 1.27s/it]
65%|██████▌ | 26/40 [00:34<00:17, 1.27s/it]
68%|██████▊ | 27/40 [00:35<00:16, 1.28s/it]
70%|███████ | 28/40 [00:37<00:15, 1.28s/it]
72%|███████▎ | 29/40 [00:38<00:14, 1.28s/it]
75%|███████▌ | 30/40 [00:39<00:12, 1.28s/it]
78%|███████▊ | 31/40 [00:41<00:11, 1.28s/it]
80%|████████ | 32/40 [00:42<00:10, 1.28s/it]
82%|████████▎ | 33/40 [00:43<00:08, 1.28s/it]
85%|████████▌ | 34/40 [00:44<00:07, 1.27s/it]
88%|████████▊ | 35/40 [00:46<00:06, 1.27s/it]
90%|█████████ | 36/40 [00:47<00:05, 1.27s/it]
92%|█████████▎| 37/40 [00:48<00:03, 1.27s/it]
95%|█████████▌| 38/40 [00:49<00:02, 1.27s/it]
98%|█████████▊| 39/40 [00:51<00:01, 1.27s/it]
100%|██████████| 40/40 [00:52<00:00, 1.26s/it]
100%|██████████| 40/40 [00:52<00:00, 1.31s/it]
Decoding latents in cuda:0...
done in 2.4s
Move latents to cpu...
done in 0.03s