Version: v1.0
Input
Output
This example was created by evevalentine2017
Finished in 127.6 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: (anime style), 2D, plain colors, japanese animation, Gandalf in Hobbiton, standing, waving
Full negative prompt: realistic, real life, lifelike, photo
0%| | 0/20 [00:00<?, ?it/s]
5%|▌ | 1/20 [00:02<00:56, 2.99s/it]
10%|█ | 2/20 [00:07<01:05, 3.64s/it]
15%|█▌ | 3/20 [00:12<01:13, 4.33s/it]
20%|██ | 4/20 [00:16<01:07, 4.19s/it]
25%|██▌ | 5/20 [00:20<01:03, 4.26s/it]
30%|███ | 6/20 [00:24<00:58, 4.21s/it]
35%|███▌ | 7/20 [00:28<00:54, 4.17s/it]
40%|████ | 8/20 [00:32<00:50, 4.18s/it]
45%|████▌ | 9/20 [00:37<00:45, 4.15s/it]
50%|█████ | 10/20 [00:41<00:41, 4.10s/it]
55%|█████▌ | 11/20 [00:45<00:37, 4.13s/it]
60%|██████ | 12/20 [00:49<00:32, 4.04s/it]
65%|██████▌ | 13/20 [00:52<00:27, 3.99s/it]
70%|███████ | 14/20 [00:56<00:23, 3.99s/it]
75%|███████▌ | 15/20 [01:00<00:19, 3.97s/it]
80%|████████ | 16/20 [01:04<00:15, 3.92s/it]
85%|████████▌ | 17/20 [01:08<00:11, 3.89s/it]
90%|█████████ | 18/20 [01:12<00:07, 3.88s/it]
95%|█████████▌| 19/20 [01:15<00:03, 3.51s/it]
100%|██████████| 20/20 [01:16<00:00, 2.75s/it]
100%|██████████| 20/20 [01:16<00:00, 3.80s/it]
Decoding latents in cuda:0...
done in 1.77s
Move latents to cpu...
done in 0.02s
0: 640x480 1 face, 159.9ms
Speed: 3.1ms preprocess, 159.9ms inference, 20.8ms postprocess per image at shape (1, 3, 640, 480)
This example was created by evevalentine2017
Finished in 127.6 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: (anime style), 2D, plain colors, japanese animation, Gandalf in Hobbiton, standing, waving
Full negative prompt: realistic, real life, lifelike, photo
0%| | 0/20 [00:00<?, ?it/s]
5%|▌ | 1/20 [00:02<00:56, 2.99s/it]
10%|█ | 2/20 [00:07<01:05, 3.64s/it]
15%|█▌ | 3/20 [00:12<01:13, 4.33s/it]
20%|██ | 4/20 [00:16<01:07, 4.19s/it]
25%|██▌ | 5/20 [00:20<01:03, 4.26s/it]
30%|███ | 6/20 [00:24<00:58, 4.21s/it]
35%|███▌ | 7/20 [00:28<00:54, 4.17s/it]
40%|████ | 8/20 [00:32<00:50, 4.18s/it]
45%|████▌ | 9/20 [00:37<00:45, 4.15s/it]
50%|█████ | 10/20 [00:41<00:41, 4.10s/it]
55%|█████▌ | 11/20 [00:45<00:37, 4.13s/it]
60%|██████ | 12/20 [00:49<00:32, 4.04s/it]
65%|██████▌ | 13/20 [00:52<00:27, 3.99s/it]
70%|███████ | 14/20 [00:56<00:23, 3.99s/it]
75%|███████▌ | 15/20 [01:00<00:19, 3.97s/it]
80%|████████ | 16/20 [01:04<00:15, 3.92s/it]
85%|████████▌ | 17/20 [01:08<00:11, 3.89s/it]
90%|█████████ | 18/20 [01:12<00:07, 3.88s/it]
95%|█████████▌| 19/20 [01:15<00:03, 3.51s/it]
100%|██████████| 20/20 [01:16<00:00, 2.75s/it]
100%|██████████| 20/20 [01:16<00:00, 3.80s/it]
Decoding latents in cuda:0...
done in 1.77s
Move latents to cpu...
done in 0.02s
0: 640x480 1 face, 159.9ms
Speed: 3.1ms preprocess, 159.9ms inference, 20.8ms postprocess per image at shape (1, 3, 640, 480)