Version: v5Hyper
Input
Output
This example was created by sparks
Finished in 16.6 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: (best quality, 4K, 8K, high-resolution, masterpiece), ultra-detailed, photorealistic, young woman, vibrant neon hair, geometric Art Deco patterns on face, surreal dream-like setting, mirror-like floors, mirror-like walls, reflections, posing, intricate facial designs, modern fashion, ethereal lighting, digital art, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0>
Full negative prompt: worst quality, low quality, normal quality, lowres, bad anatomy, jpeg artifacts, tilted head, bad hands, missing fingers, extra digit, fewer digits, missing arms, missing legs, extra arms, low details, oversaturated, undersaturated, overexposed, underexposed, bad photo, bad photography, bad art, watermark, signature, text font, username, logo, words, letters, digits, autograph, trademark
0%| | 0/8 [00:00<?, ?it/s]
12%|█▎ | 1/8 [00:02<00:17, 2.50s/it]
25%|██▌ | 2/8 [00:03<00:09, 1.57s/it]
38%|███▊ | 3/8 [00:04<00:06, 1.27s/it]
50%|█████ | 4/8 [00:05<00:04, 1.13s/it]
62%|██████▎ | 5/8 [00:06<00:03, 1.06s/it]
75%|███████▌ | 6/8 [00:07<00:02, 1.01s/it]
88%|████████▊ | 7/8 [00:08<00:00, 1.02it/s]
100%|██████████| 8/8 [00:08<00:00, 1.05it/s]
100%|██████████| 8/8 [00:08<00:00, 1.12s/it]
Decoding latents in cuda:0...
done in 1.79s
Move latents to cpu...
done in 0.02s
This example was created by sparks
Finished in 16.6 seconds
Setting up the model...
Preparing inputs...
Processing...
Loading VAE weight: models/VAE/sdxl_vae.safetensors
Full prompt: (best quality, 4K, 8K, high-resolution, masterpiece), ultra-detailed, photorealistic, young woman, vibrant neon hair, geometric Art Deco patterns on face, surreal dream-like setting, mirror-like floors, mirror-like walls, reflections, posing, intricate facial designs, modern fashion, ethereal lighting, digital art, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0>
Full negative prompt: worst quality, low quality, normal quality, lowres, bad anatomy, jpeg artifacts, tilted head, bad hands, missing fingers, extra digit, fewer digits, missing arms, missing legs, extra arms, low details, oversaturated, undersaturated, overexposed, underexposed, bad photo, bad photography, bad art, watermark, signature, text font, username, logo, words, letters, digits, autograph, trademark
0%| | 0/8 [00:00<?, ?it/s]
12%|█▎ | 1/8 [00:02<00:17, 2.50s/it]
25%|██▌ | 2/8 [00:03<00:09, 1.57s/it]
38%|███▊ | 3/8 [00:04<00:06, 1.27s/it]
50%|█████ | 4/8 [00:05<00:04, 1.13s/it]
62%|██████▎ | 5/8 [00:06<00:03, 1.06s/it]
75%|███████▌ | 6/8 [00:07<00:02, 1.01s/it]
88%|████████▊ | 7/8 [00:08<00:00, 1.02it/s]
100%|██████████| 8/8 [00:08<00:00, 1.05it/s]
100%|██████████| 8/8 [00:08<00:00, 1.12s/it]
Decoding latents in cuda:0...
done in 1.79s
Move latents to cpu...
done in 0.02s