tungsten-logo
Sign In
realvision-xl
realvision-xl

realvision-xl

7 stars
Version: v3.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
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/1c51ea0859a74f4ca062fbacfd2b5120/00000-102066472.webp
https://files.tungsten.run/uploads/a2f5b9f65345441ab7ad80246af4b50e/00001-102066473.webp
https://files.tungsten.run/uploads/fb656e3e1265416db37a7f5faf9c5da2/00002-102066474.webp
This example was created by evevalentine2017
Finished in 183.9 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: girl, korean, cosplay, Swordsman, standing, perfect feet in medieval boots, castle background, photorealistic, best quality, ultra high res, extremely detailed eyes and face, full body, long legs, outdoors, large chest, Height 180cm, Full negative prompt: asymmetry, worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:04<00:58, 4.20s/it] 13%|█▎ | 2/15 [00:09<01:04, 5.00s/it] 20%|██ | 3/15 [00:15<01:03, 5.32s/it] 27%|██▋ | 4/15 [00:20<00:57, 5.21s/it] 33%|███▎ | 5/15 [00:26<00:54, 5.50s/it] 40%|████ | 6/15 [00:31<00:49, 5.49s/it] 47%|████▋ | 7/15 [00:37<00:44, 5.57s/it] 53%|█████▎ | 8/15 [00:43<00:38, 5.56s/it] 60%|██████ | 9/15 [00:48<00:32, 5.40s/it] 67%|██████▋ | 10/15 [00:53<00:26, 5.38s/it] 73%|███████▎ | 11/15 [00:58<00:21, 5.36s/it] 80%|████████ | 12/15 [01:03<00:14, 4.99s/it] 87%|████████▋ | 13/15 [01:08<00:10, 5.00s/it] 93%|█████████▎| 14/15 [01:11<00:04, 4.60s/it] 100%|██████████| 15/15 [01:13<00:00, 3.60s/it] 100%|██████████| 15/15 [01:13<00:00, 4.87s/it] Decoding latents in cuda:0... done in 2.31s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.9ms Speed: 3.2ms preprocess, 7.9ms inference, 21.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:10, 1.68s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.68s/it] 43%|████▎ | 3/7 [00:05<00:06, 1.66s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.51s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.53s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.40s/it] 100%|██████████| 7/7 [00:09<00:00, 1.06s/it] 100%|██████████| 7/7 [00:09<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 9.3ms Speed: 3.1ms preprocess, 9.3ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.61s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.65s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.65s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.51s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.53s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.39s/it] 100%|██████████| 7/7 [00:09<00:00, 1.06s/it] 100%|██████████| 7/7 [00:09<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.59s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.63s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.65s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.50s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.53s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.39s/it] 100%|██████████| 7/7 [00:09<00:00, 1.06s/it] 100%|██████████| 7/7 [00:09<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x640 3 hands, 7.3ms Speed: 3.1ms preprocess, 7.3ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.60s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.65s/it] 43%|████▎ | 3/7 [00:05<00:06, 1.72s/it] 57%|█████▋ | 4/7 [00:06<00:05, 1.74s/it] 71%|███████▏ | 5/7 [00:08<00:03, 1.68s/it] 86%|████████▌ | 6/7 [00:09<00:01, 1.50s/it] 100%|██████████| 7/7 [00:09<00:00, 1.13s/it] 100%|██████████| 7/7 [00:09<00:00, 1.42s/it] Decoding latents in cuda:0... done in 0.76s Move latents to cpu... done in 0.0s 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.61s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.64s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.66s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.51s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.54s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.41s/it] 100%|██████████| 7/7 [00:09<00:00, 1.07s/it] 100%|██████████| 7/7 [00:09<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.62s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.69s/it] 43%|████▎ | 3/7 [00:05<00:06, 1.69s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.54s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.56s/it] 86%|████████▌ | 6/7 [00:09<00:01, 1.43s/it] 100%|██████████| 7/7 [00:09<00:00, 1.10s/it] 100%|██████████| 7/7 [00:09<00:00, 1.36s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.9ms Speed: 3.2ms preprocess, 7.9ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.61s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.66s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.66s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.52s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.55s/it] 86%|████████▌ | 6/7 [00:09<00:01, 1.41s/it] 100%|██████████| 7/7 [00:09<00:00, 1.07s/it] 100%|██████████| 7/7 [00:09<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.76s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.1ms Speed: 3.0ms preprocess, 7.1ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.60s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.64s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.66s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.51s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.54s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.40s/it] 100%|██████████| 7/7 [00:09<00:00, 1.07s/it] 100%|██████████| 7/7 [00:09<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.66s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.69s/it] 43%|████▎ | 3/7 [00:05<00:06, 1.70s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.54s/it] 71%|███████▏ | 5/7 [00:08<00:03, 1.58s/it] 86%|████████▌ | 6/7 [00:09<00:01, 1.44s/it] 100%|██████████| 7/7 [00:09<00:00, 1.10s/it] 100%|██████████| 7/7 [00:09<00:00, 1.37s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
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/1c51ea0859a74f4ca062fbacfd2b5120/00000-102066472.webp
https://files.tungsten.run/uploads/a2f5b9f65345441ab7ad80246af4b50e/00001-102066473.webp
https://files.tungsten.run/uploads/fb656e3e1265416db37a7f5faf9c5da2/00002-102066474.webp
This example was created by evevalentine2017
Finished in 183.9 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: girl, korean, cosplay, Swordsman, standing, perfect feet in medieval boots, castle background, photorealistic, best quality, ultra high res, extremely detailed eyes and face, full body, long legs, outdoors, large chest, Height 180cm, Full negative prompt: asymmetry, worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:04<00:58, 4.20s/it] 13%|█▎ | 2/15 [00:09<01:04, 5.00s/it] 20%|██ | 3/15 [00:15<01:03, 5.32s/it] 27%|██▋ | 4/15 [00:20<00:57, 5.21s/it] 33%|███▎ | 5/15 [00:26<00:54, 5.50s/it] 40%|████ | 6/15 [00:31<00:49, 5.49s/it] 47%|████▋ | 7/15 [00:37<00:44, 5.57s/it] 53%|█████▎ | 8/15 [00:43<00:38, 5.56s/it] 60%|██████ | 9/15 [00:48<00:32, 5.40s/it] 67%|██████▋ | 10/15 [00:53<00:26, 5.38s/it] 73%|███████▎ | 11/15 [00:58<00:21, 5.36s/it] 80%|████████ | 12/15 [01:03<00:14, 4.99s/it] 87%|████████▋ | 13/15 [01:08<00:10, 5.00s/it] 93%|█████████▎| 14/15 [01:11<00:04, 4.60s/it] 100%|██████████| 15/15 [01:13<00:00, 3.60s/it] 100%|██████████| 15/15 [01:13<00:00, 4.87s/it] Decoding latents in cuda:0... done in 2.31s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.9ms Speed: 3.2ms preprocess, 7.9ms inference, 21.3ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:10, 1.68s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.68s/it] 43%|████▎ | 3/7 [00:05<00:06, 1.66s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.51s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.53s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.40s/it] 100%|██████████| 7/7 [00:09<00:00, 1.06s/it] 100%|██████████| 7/7 [00:09<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 1 hand, 9.3ms Speed: 3.1ms preprocess, 9.3ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.61s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.65s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.65s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.51s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.53s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.39s/it] 100%|██████████| 7/7 [00:09<00:00, 1.06s/it] 100%|██████████| 7/7 [00:09<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.59s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.63s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.65s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.50s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.53s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.39s/it] 100%|██████████| 7/7 [00:09<00:00, 1.06s/it] 100%|██████████| 7/7 [00:09<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x640 3 hands, 7.3ms Speed: 3.1ms preprocess, 7.3ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.60s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.65s/it] 43%|████▎ | 3/7 [00:05<00:06, 1.72s/it] 57%|█████▋ | 4/7 [00:06<00:05, 1.74s/it] 71%|███████▏ | 5/7 [00:08<00:03, 1.68s/it] 86%|████████▌ | 6/7 [00:09<00:01, 1.50s/it] 100%|██████████| 7/7 [00:09<00:00, 1.13s/it] 100%|██████████| 7/7 [00:09<00:00, 1.42s/it] Decoding latents in cuda:0... done in 0.76s Move latents to cpu... done in 0.0s 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.61s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.64s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.66s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.51s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.54s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.41s/it] 100%|██████████| 7/7 [00:09<00:00, 1.07s/it] 100%|██████████| 7/7 [00:09<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.62s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.69s/it] 43%|████▎ | 3/7 [00:05<00:06, 1.69s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.54s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.56s/it] 86%|████████▌ | 6/7 [00:09<00:01, 1.43s/it] 100%|██████████| 7/7 [00:09<00:00, 1.10s/it] 100%|██████████| 7/7 [00:09<00:00, 1.36s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.9ms Speed: 3.2ms preprocess, 7.9ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.61s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.66s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.66s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.52s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.55s/it] 86%|████████▌ | 6/7 [00:09<00:01, 1.41s/it] 100%|██████████| 7/7 [00:09<00:00, 1.07s/it] 100%|██████████| 7/7 [00:09<00:00, 1.34s/it] Decoding latents in cuda:0... done in 0.76s Move latents to cpu... done in 0.0s 0: 640x640 2 hands, 7.1ms Speed: 3.0ms preprocess, 7.1ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.60s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.64s/it] 43%|████▎ | 3/7 [00:04<00:06, 1.66s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.51s/it] 71%|███████▏ | 5/7 [00:07<00:03, 1.54s/it] 86%|████████▌ | 6/7 [00:08<00:01, 1.40s/it] 100%|██████████| 7/7 [00:09<00:00, 1.07s/it] 100%|██████████| 7/7 [00:09<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:01<00:09, 1.66s/it] 29%|██▊ | 2/7 [00:03<00:08, 1.69s/it] 43%|████▎ | 3/7 [00:05<00:06, 1.70s/it] 57%|█████▋ | 4/7 [00:06<00:04, 1.54s/it] 71%|███████▏ | 5/7 [00:08<00:03, 1.58s/it] 86%|████████▌ | 6/7 [00:09<00:01, 1.44s/it] 100%|██████████| 7/7 [00:09<00:00, 1.10s/it] 100%|██████████| 7/7 [00:09<00:00, 1.37s/it] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s Uploading outputs... Finished.