Valiant Stallion -Realistic PD
Valiant Stallion -Realistic PD
42 stars
4 running now
Version: v3.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
PonyDetailV20
Pony Detail V20
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
Output
https://files.tungsten.run/uploads/b5cee33e2b614ee095bf7f068a8b7127/output-75702bcaaa28456b854563689b6e319d-00000-268815779.webp
https://files.tungsten.run/uploads/5881a838ad0143c6b652f8fb73b35fdb/output-f626d09079e94df08587e7adfa94e7d5-00001-268815780.webp
https://files.tungsten.run/uploads/f385b2ce98d24ce791e99f6082e55107/output-b6652311142441648dab194fd13eaa96-00002-268815781.webp
This example was created by zennerhenric
Finished in 83.0 seconds
Using seed 268815779 Loading VAE weight: models/VAE/fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors Full prompt: Hires, Detailed, Absurdres, absurdres, detailed, hires, cinematic photo, dramatic lighting, dynamic pose, woman in kimono, cyberpunk, yellow_sun, teal background, Full negative prompt: low quality, lowres, bad anatomy, normal quality, worst quality, 3D, render, illustration, drawing, comic, watermark, greyscale, monochrome, nails, text, logo 0%| | 0/48 [00:00<?, ?it/s] 2%|▏ | 1/48 [00:00<00:45, 1.03it/s] 4%|▍ | 2/48 [00:01<00:45, 1.01it/s] 6%|▋ | 3/48 [00:02<00:44, 1.01it/s] 8%|▊ | 4/48 [00:03<00:43, 1.01it/s] 10%|█ | 5/48 [00:04<00:42, 1.01it/s] 12%|█▎ | 6/48 [00:05<00:41, 1.01it/s] 15%|█▍ | 7/48 [00:06<00:40, 1.01it/s] 17%|█▋ | 8/48 [00:07<00:39, 1.00it/s] 19%|█▉ | 9/48 [00:08<00:38, 1.00it/s] 21%|██ | 10/48 [00:09<00:37, 1.00it/s] 23%|██▎ | 11/48 [00:10<00:36, 1.01it/s] 25%|██▌ | 12/48 [00:11<00:35, 1.01it/s] 27%|██▋ | 13/48 [00:12<00:34, 1.01it/s] 29%|██▉ | 14/48 [00:13<00:33, 1.01it/s] 31%|███▏ | 15/48 [00:14<00:32, 1.00it/s] 33%|███▎ | 16/48 [00:15<00:31, 1.00it/s] 35%|███▌ | 17/48 [00:16<00:30, 1.00it/s] 38%|███▊ | 18/48 [00:17<00:29, 1.00it/s] 40%|███▉ | 19/48 [00:18<00:28, 1.00it/s] 42%|████▏ | 20/48 [00:19<00:27, 1.00it/s] 44%|████▍ | 21/48 [00:20<00:26, 1.00it/s] 46%|████▌ | 22/48 [00:21<00:25, 1.01it/s] 48%|████▊ | 23/48 [00:22<00:24, 1.01it/s] 50%|█████ | 24/48 [00:23<00:23, 1.01it/s] 52%|█████▏ | 25/48 [00:24<00:22, 1.01it/s] 54%|█████▍ | 26/48 [00:25<00:21, 1.01it/s] 56%|█████▋ | 27/48 [00:26<00:20, 1.00it/s] 58%|█████▊ | 28/48 [00:27<00:19, 1.01it/s] 60%|██████ | 29/48 [00:28<00:18, 1.01it/s] 62%|██████▎ | 30/48 [00:29<00:17, 1.00it/s] 65%|██████▍ | 31/48 [00:30<00:16, 1.01it/s] 67%|██████▋ | 32/48 [00:32<00:17, 1.09s/it] 69%|██████▉ | 33/48 [00:33<00:15, 1.05s/it] 71%|███████ | 34/48 [00:34<00:14, 1.04s/it] 73%|███████▎ | 35/48 [00:35<00:13, 1.02s/it] 75%|███████▌ | 36/48 [00:36<00:12, 1.02s/it] 77%|███████▋ | 37/48 [00:37<00:11, 1.01s/it] 79%|███████▉ | 38/48 [00:38<00:10, 1.01s/it] 81%|████████▏ | 39/48 [00:39<00:09, 1.00s/it] 83%|████████▎ | 40/48 [00:40<00:08, 1.00s/it] 85%|████████▌ | 41/48 [00:41<00:07, 1.00s/it] 88%|████████▊ | 42/48 [00:42<00:06, 1.00s/it] 90%|████████▉ | 43/48 [00:43<00:05, 1.00s/it] 92%|█████████▏| 44/48 [00:44<00:04, 1.00s/it] 94%|█████████▍| 45/48 [00:45<00:03, 1.00s/it] 96%|█████████▌| 46/48 [00:46<00:02, 1.00s/it] 98%|█████████▊| 47/48 [00:47<00:01, 1.01s/it] 100%|██████████| 48/48 [00:48<00:00, 1.00s/it] 100%|██████████| 48/48 [00:48<00:00, 1.00s/it] Decoding latents in cuda:0... done in 1.77s Move latents to cpu... done in 0.02s 0: 640x480 1 face, 156.8ms Speed: 2.6ms preprocess, 156.8ms inference, 28.5ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:07, 2.08it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.53it/s] 18%|█▊ | 3/17 [00:01<00:05, 2.72it/s] 24%|██▎ | 4/17 [00:01<00:04, 2.83it/s] 29%|██▉ | 5/17 [00:01<00:04, 2.88it/s] 35%|███▌ | 6/17 [00:02<00:03, 2.92it/s] 41%|████ | 7/17 [00:02<00:03, 2.95it/s] 47%|████▋ | 8/17 [00:02<00:03, 2.96it/s] 53%|█████▎ | 9/17 [00:03<00:02, 2.98it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.99it/s] 65%|██████▍ | 11/17 [00:03<00:02, 2.99it/s] 71%|███████ | 12/17 [00:04<00:01, 2.99it/s] 76%|███████▋ | 13/17 [00:04<00:01, 2.99it/s] 82%|████████▏ | 14/17 [00:04<00:01, 2.99it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.95it/s] 94%|█████████▍| 16/17 [00:05<00:00, 2.95it/s] 100%|██████████| 17/17 [00:05<00:00, 2.97it/s] 100%|██████████| 17/17 [00:05<00:00, 2.91it/s] Decoding latents in cuda:0... done in 0.59s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 20.0ms Speed: 4.0ms preprocess, 20.0ms inference, 3.0ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:11, 1.45it/s] 12%|█▏ | 2/17 [00:01<00:10, 1.47it/s] 18%|█▊ | 3/17 [00:02<00:09, 1.47it/s] 24%|██▎ | 4/17 [00:02<00:08, 1.46it/s] 29%|██▉ | 5/17 [00:03<00:08, 1.41it/s] 35%|███▌ | 6/17 [00:04<00:07, 1.38it/s] 41%|████ | 7/17 [00:04<00:07, 1.37it/s] 47%|████▋ | 8/17 [00:05<00:05, 1.64it/s] 53%|█████▎ | 9/17 [00:05<00:04, 1.89it/s] 59%|█████▉ | 10/17 [00:06<00:03, 2.09it/s] 65%|██████▍ | 11/17 [00:06<00:02, 2.25it/s] 71%|███████ | 12/17 [00:06<00:02, 2.40it/s] 76%|███████▋ | 13/17 [00:07<00:01, 2.53it/s] 82%|████████▏ | 14/17 [00:07<00:01, 2.59it/s] 88%|████████▊ | 15/17 [00:07<00:00, 2.65it/s] 94%|█████████▍| 16/17 [00:08<00:00, 2.64it/s] 100%|██████████| 17/17 [00:08<00:00, 2.66it/s] 100%|██████████| 17/17 [00:08<00:00, 1.98it/s] Decoding latents in cuda:0... done in 0.59s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 16.8ms Speed: 3.7ms preprocess, 16.8ms inference, 2.1ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:05, 2.97it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.97it/s] 18%|█▊ | 3/17 [00:01<00:04, 2.95it/s] 24%|██▎ | 4/17 [00:01<00:04, 2.97it/s] 29%|██▉ | 5/17 [00:01<00:04, 2.97it/s] 35%|███▌ | 6/17 [00:02<00:03, 2.95it/s] 41%|████ | 7/17 [00:02<00:03, 2.95it/s] 47%|████▋ | 8/17 [00:02<00:03, 2.95it/s] 53%|█████▎ | 9/17 [00:03<00:02, 2.94it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.95it/s] 65%|██████▍ | 11/17 [00:03<00:02, 2.95it/s] 71%|███████ | 12/17 [00:04<00:01, 2.75it/s] 76%|███████▋ | 13/17 [00:04<00:01, 2.81it/s] 82%|████████▏ | 14/17 [00:04<00:01, 2.85it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.88it/s] 94%|█████████▍| 16/17 [00:05<00:00, 2.91it/s] 100%|██████████| 17/17 [00:05<00:00, 2.91it/s] 100%|██████████| 17/17 [00:05<00:00, 2.91it/s] Decoding latents in cuda:0... done in 0.6s Move latents to cpu... done in 0.0s Uploading files.. Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
PonyDetailV20
Pony Detail V20
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
https://files.tungsten.run/uploads/b5cee33e2b614ee095bf7f068a8b7127/output-75702bcaaa28456b854563689b6e319d-00000-268815779.webp
https://files.tungsten.run/uploads/5881a838ad0143c6b652f8fb73b35fdb/output-f626d09079e94df08587e7adfa94e7d5-00001-268815780.webp
https://files.tungsten.run/uploads/f385b2ce98d24ce791e99f6082e55107/output-b6652311142441648dab194fd13eaa96-00002-268815781.webp
This example was created by zennerhenric
Finished in 83.0 seconds
Using seed 268815779 Loading VAE weight: models/VAE/fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors Full prompt: Hires, Detailed, Absurdres, absurdres, detailed, hires, cinematic photo, dramatic lighting, dynamic pose, woman in kimono, cyberpunk, yellow_sun, teal background, Full negative prompt: low quality, lowres, bad anatomy, normal quality, worst quality, 3D, render, illustration, drawing, comic, watermark, greyscale, monochrome, nails, text, logo 0%| | 0/48 [00:00<?, ?it/s] 2%|▏ | 1/48 [00:00<00:45, 1.03it/s] 4%|▍ | 2/48 [00:01<00:45, 1.01it/s] 6%|▋ | 3/48 [00:02<00:44, 1.01it/s] 8%|▊ | 4/48 [00:03<00:43, 1.01it/s] 10%|█ | 5/48 [00:04<00:42, 1.01it/s] 12%|█▎ | 6/48 [00:05<00:41, 1.01it/s] 15%|█▍ | 7/48 [00:06<00:40, 1.01it/s] 17%|█▋ | 8/48 [00:07<00:39, 1.00it/s] 19%|█▉ | 9/48 [00:08<00:38, 1.00it/s] 21%|██ | 10/48 [00:09<00:37, 1.00it/s] 23%|██▎ | 11/48 [00:10<00:36, 1.01it/s] 25%|██▌ | 12/48 [00:11<00:35, 1.01it/s] 27%|██▋ | 13/48 [00:12<00:34, 1.01it/s] 29%|██▉ | 14/48 [00:13<00:33, 1.01it/s] 31%|███▏ | 15/48 [00:14<00:32, 1.00it/s] 33%|███▎ | 16/48 [00:15<00:31, 1.00it/s] 35%|███▌ | 17/48 [00:16<00:30, 1.00it/s] 38%|███▊ | 18/48 [00:17<00:29, 1.00it/s] 40%|███▉ | 19/48 [00:18<00:28, 1.00it/s] 42%|████▏ | 20/48 [00:19<00:27, 1.00it/s] 44%|████▍ | 21/48 [00:20<00:26, 1.00it/s] 46%|████▌ | 22/48 [00:21<00:25, 1.01it/s] 48%|████▊ | 23/48 [00:22<00:24, 1.01it/s] 50%|█████ | 24/48 [00:23<00:23, 1.01it/s] 52%|█████▏ | 25/48 [00:24<00:22, 1.01it/s] 54%|█████▍ | 26/48 [00:25<00:21, 1.01it/s] 56%|█████▋ | 27/48 [00:26<00:20, 1.00it/s] 58%|█████▊ | 28/48 [00:27<00:19, 1.01it/s] 60%|██████ | 29/48 [00:28<00:18, 1.01it/s] 62%|██████▎ | 30/48 [00:29<00:17, 1.00it/s] 65%|██████▍ | 31/48 [00:30<00:16, 1.01it/s] 67%|██████▋ | 32/48 [00:32<00:17, 1.09s/it] 69%|██████▉ | 33/48 [00:33<00:15, 1.05s/it] 71%|███████ | 34/48 [00:34<00:14, 1.04s/it] 73%|███████▎ | 35/48 [00:35<00:13, 1.02s/it] 75%|███████▌ | 36/48 [00:36<00:12, 1.02s/it] 77%|███████▋ | 37/48 [00:37<00:11, 1.01s/it] 79%|███████▉ | 38/48 [00:38<00:10, 1.01s/it] 81%|████████▏ | 39/48 [00:39<00:09, 1.00s/it] 83%|████████▎ | 40/48 [00:40<00:08, 1.00s/it] 85%|████████▌ | 41/48 [00:41<00:07, 1.00s/it] 88%|████████▊ | 42/48 [00:42<00:06, 1.00s/it] 90%|████████▉ | 43/48 [00:43<00:05, 1.00s/it] 92%|█████████▏| 44/48 [00:44<00:04, 1.00s/it] 94%|█████████▍| 45/48 [00:45<00:03, 1.00s/it] 96%|█████████▌| 46/48 [00:46<00:02, 1.00s/it] 98%|█████████▊| 47/48 [00:47<00:01, 1.01s/it] 100%|██████████| 48/48 [00:48<00:00, 1.00s/it] 100%|██████████| 48/48 [00:48<00:00, 1.00s/it] Decoding latents in cuda:0... done in 1.77s Move latents to cpu... done in 0.02s 0: 640x480 1 face, 156.8ms Speed: 2.6ms preprocess, 156.8ms inference, 28.5ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:07, 2.08it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.53it/s] 18%|█▊ | 3/17 [00:01<00:05, 2.72it/s] 24%|██▎ | 4/17 [00:01<00:04, 2.83it/s] 29%|██▉ | 5/17 [00:01<00:04, 2.88it/s] 35%|███▌ | 6/17 [00:02<00:03, 2.92it/s] 41%|████ | 7/17 [00:02<00:03, 2.95it/s] 47%|████▋ | 8/17 [00:02<00:03, 2.96it/s] 53%|█████▎ | 9/17 [00:03<00:02, 2.98it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.99it/s] 65%|██████▍ | 11/17 [00:03<00:02, 2.99it/s] 71%|███████ | 12/17 [00:04<00:01, 2.99it/s] 76%|███████▋ | 13/17 [00:04<00:01, 2.99it/s] 82%|████████▏ | 14/17 [00:04<00:01, 2.99it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.95it/s] 94%|█████████▍| 16/17 [00:05<00:00, 2.95it/s] 100%|██████████| 17/17 [00:05<00:00, 2.97it/s] 100%|██████████| 17/17 [00:05<00:00, 2.91it/s] Decoding latents in cuda:0... done in 0.59s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 20.0ms Speed: 4.0ms preprocess, 20.0ms inference, 3.0ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:11, 1.45it/s] 12%|█▏ | 2/17 [00:01<00:10, 1.47it/s] 18%|█▊ | 3/17 [00:02<00:09, 1.47it/s] 24%|██▎ | 4/17 [00:02<00:08, 1.46it/s] 29%|██▉ | 5/17 [00:03<00:08, 1.41it/s] 35%|███▌ | 6/17 [00:04<00:07, 1.38it/s] 41%|████ | 7/17 [00:04<00:07, 1.37it/s] 47%|████▋ | 8/17 [00:05<00:05, 1.64it/s] 53%|█████▎ | 9/17 [00:05<00:04, 1.89it/s] 59%|█████▉ | 10/17 [00:06<00:03, 2.09it/s] 65%|██████▍ | 11/17 [00:06<00:02, 2.25it/s] 71%|███████ | 12/17 [00:06<00:02, 2.40it/s] 76%|███████▋ | 13/17 [00:07<00:01, 2.53it/s] 82%|████████▏ | 14/17 [00:07<00:01, 2.59it/s] 88%|████████▊ | 15/17 [00:07<00:00, 2.65it/s] 94%|█████████▍| 16/17 [00:08<00:00, 2.64it/s] 100%|██████████| 17/17 [00:08<00:00, 2.66it/s] 100%|██████████| 17/17 [00:08<00:00, 1.98it/s] Decoding latents in cuda:0... done in 0.59s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 16.8ms Speed: 3.7ms preprocess, 16.8ms inference, 2.1ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:05, 2.97it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.97it/s] 18%|█▊ | 3/17 [00:01<00:04, 2.95it/s] 24%|██▎ | 4/17 [00:01<00:04, 2.97it/s] 29%|██▉ | 5/17 [00:01<00:04, 2.97it/s] 35%|███▌ | 6/17 [00:02<00:03, 2.95it/s] 41%|████ | 7/17 [00:02<00:03, 2.95it/s] 47%|████▋ | 8/17 [00:02<00:03, 2.95it/s] 53%|█████▎ | 9/17 [00:03<00:02, 2.94it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.95it/s] 65%|██████▍ | 11/17 [00:03<00:02, 2.95it/s] 71%|███████ | 12/17 [00:04<00:01, 2.75it/s] 76%|███████▋ | 13/17 [00:04<00:01, 2.81it/s] 82%|████████▏ | 14/17 [00:04<00:01, 2.85it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.88it/s] 94%|█████████▍| 16/17 [00:05<00:00, 2.91it/s] 100%|██████████| 17/17 [00:05<00:00, 2.91it/s] 100%|██████████| 17/17 [00:05<00:00, 2.91it/s] Decoding latents in cuda:0... done in 0.6s Move latents to cpu... done in 0.0s Uploading files.. Finished.