Version: v1.0
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
saturation
Adjust saturation
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/ba01304066ae40ff935d5cb68e644d92/00000-3868250924.webp
https://files.tungsten.run/uploads/5cfa9b8c34db48d18fab16c06f47dc94/00001-3868250925.webp
https://files.tungsten.run/uploads/538a2e1ef24845d4be02494543511947/00002-3868250926.webp
https://files.tungsten.run/uploads/6e1e70121bec47819ec18b34f0612fa5/00003-3868250927.webp
This example was created by evevalentine2017
Finished in 75.5 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/clearvae_v2.3_fp16.safetensors Full prompt: (high quality, best quality), masterpiece, beach, sunset, toned, 2 pigtails, long hair, big fluffy hair, blonde hair, 1girl, tiny pink shiny bikini, navel, holding a bucket, shiny skin, <lora:add_detail:0.1> Full negative prompt: nsfw, nude, vagina, genitalia, loli, asian, ground, EasyNegativeV2, (artist name, signature, watermark:1.4), (ugly:1.2), (worst quality, poor details:1.4), blurry, large breasts, garters, garter belt, umbrella 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:53, 1.85s/it] 7%|▋ | 2/30 [00:03<00:42, 1.53s/it] 10%|█ | 3/30 [00:04<00:38, 1.42s/it] 13%|█▎ | 4/30 [00:05<00:35, 1.37s/it] 17%|█▋ | 5/30 [00:07<00:33, 1.35s/it] 20%|██ | 6/30 [00:08<00:31, 1.33s/it] 23%|██▎ | 7/30 [00:09<00:30, 1.32s/it] 27%|██▋ | 8/30 [00:10<00:29, 1.32s/it] 30%|███ | 9/30 [00:12<00:27, 1.31s/it] 33%|███▎ | 10/30 [00:13<00:26, 1.31s/it] 37%|███▋ | 11/30 [00:14<00:24, 1.31s/it] 40%|████ | 12/30 [00:16<00:23, 1.31s/it] 43%|████▎ | 13/30 [00:17<00:22, 1.31s/it] 47%|████▋ | 14/30 [00:18<00:20, 1.31s/it] 50%|█████ | 15/30 [00:20<00:19, 1.31s/it] 53%|█████▎ | 16/30 [00:21<00:18, 1.31s/it] 57%|█████▋ | 17/30 [00:22<00:17, 1.32s/it] 60%|██████ | 18/30 [00:24<00:15, 1.32s/it] 63%|██████▎ | 19/30 [00:25<00:14, 1.32s/it] 67%|██████▋ | 20/30 [00:26<00:13, 1.32s/it] 70%|███████ | 21/30 [00:28<00:11, 1.32s/it] 73%|███████▎ | 22/30 [00:29<00:10, 1.32s/it] 77%|███████▋ | 23/30 [00:30<00:09, 1.32s/it] 80%|████████ | 24/30 [00:32<00:07, 1.32s/it] 83%|████████▎ | 25/30 [00:33<00:06, 1.32s/it] 87%|████████▋ | 26/30 [00:34<00:05, 1.33s/it] 90%|█████████ | 27/30 [00:36<00:03, 1.32s/it] 93%|█████████▎| 28/30 [00:37<00:02, 1.32s/it] 97%|█████████▋| 29/30 [00:38<00:01, 1.32s/it] 100%|██████████| 30/30 [00:39<00:00, 1.13s/it] 100%|██████████| 30/30 [00:39<00:00, 1.31s/it] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.7ms Speed: 3.3ms preprocess, 7.7ms inference, 32.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:07, 2.22it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.74it/s] 18%|█▊ | 3/17 [00:01<00:04, 2.96it/s] 24%|██▎ | 4/17 [00:01<00:04, 3.03it/s] 29%|██▉ | 5/17 [00:01<00:03, 3.12it/s] 35%|███▌ | 6/17 [00:01<00:03, 3.17it/s] 41%|████ | 7/17 [00:02<00:03, 3.18it/s] 47%|████▋ | 8/17 [00:02<00:02, 3.20it/s] 53%|█████▎ | 9/17 [00:02<00:02, 3.22it/s] 59%|█████▉ | 10/17 [00:03<00:02, 3.22it/s] 65%|██████▍ | 11/17 [00:03<00:01, 3.22it/s] 71%|███████ | 12/17 [00:03<00:01, 3.24it/s] 76%|███████▋ | 13/17 [00:04<00:01, 3.24it/s] 82%|████████▏ | 14/17 [00:04<00:00, 3.23it/s] 88%|████████▊ | 15/17 [00:04<00:00, 3.24it/s] 94%|█████████▍| 16/17 [00:05<00:00, 3.23it/s] 100%|██████████| 17/17 [00:05<00:00, 3.79it/s] 100%|██████████| 17/17 [00:05<00:00, 3.25it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 2.9ms preprocess, 7.5ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:04, 3.37it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.33it/s] 18%|█▊ | 3/17 [00:00<00:04, 3.29it/s] 24%|██▎ | 4/17 [00:01<00:04, 3.23it/s] 29%|██▉ | 5/17 [00:01<00:03, 3.25it/s] 35%|███▌ | 6/17 [00:01<00:03, 3.26it/s] 41%|████ | 7/17 [00:02<00:03, 3.23it/s] 47%|████▋ | 8/17 [00:02<00:02, 3.23it/s] 53%|█████▎ | 9/17 [00:02<00:02, 3.24it/s] 59%|█████▉ | 10/17 [00:03<00:02, 3.22it/s] 65%|██████▍ | 11/17 [00:03<00:01, 3.23it/s] 71%|███████ | 12/17 [00:03<00:01, 3.24it/s] 76%|███████▋ | 13/17 [00:04<00:01, 3.23it/s] 82%|████████▏ | 14/17 [00:04<00:00, 3.23it/s] 88%|████████▊ | 15/17 [00:04<00:00, 3.24it/s] 94%|█████████▍| 16/17 [00:04<00:00, 3.24it/s] 100%|██████████| 17/17 [00:05<00:00, 3.81it/s] 100%|██████████| 17/17 [00:05<00:00, 3.34it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:04, 3.37it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.32it/s] 18%|█▊ | 3/17 [00:00<00:04, 3.28it/s] 24%|██▎ | 4/17 [00:01<00:04, 3.22it/s] 29%|██▉ | 5/17 [00:01<00:03, 3.24it/s] 35%|███▌ | 6/17 [00:01<00:03, 3.25it/s] 41%|████ | 7/17 [00:02<00:03, 3.22it/s] 47%|████▋ | 8/17 [00:02<00:02, 3.22it/s] 53%|█████▎ | 9/17 [00:02<00:02, 3.24it/s] 59%|█████▉ | 10/17 [00:03<00:02, 3.22it/s] 65%|██████▍ | 11/17 [00:03<00:01, 3.22it/s] 71%|███████ | 12/17 [00:03<00:01, 3.23it/s] 76%|███████▋ | 13/17 [00:04<00:01, 3.22it/s] 82%|████████▏ | 14/17 [00:04<00:00, 3.21it/s] 88%|████████▊ | 15/17 [00:04<00:00, 3.23it/s] 94%|█████████▍| 16/17 [00:04<00:00, 3.22it/s] 100%|██████████| 17/17 [00:05<00:00, 3.78it/s] 100%|██████████| 17/17 [00:05<00:00, 3.33it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.3ms Speed: 2.7ms preprocess, 7.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:04, 3.38it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.32it/s] 18%|█▊ | 3/17 [00:00<00:04, 3.27it/s] 24%|██▎ | 4/17 [00:01<00:04, 3.23it/s] 29%|██▉ | 5/17 [00:01<00:03, 3.24it/s] 35%|███▌ | 6/17 [00:01<00:03, 3.24it/s] 41%|████ | 7/17 [00:02<00:03, 3.20it/s] 47%|████▋ | 8/17 [00:02<00:02, 3.21it/s] 53%|█████▎ | 9/17 [00:02<00:02, 3.22it/s] 59%|█████▉ | 10/17 [00:03<00:02, 3.21it/s] 65%|██████▍ | 11/17 [00:03<00:01, 3.21it/s] 71%|███████ | 12/17 [00:03<00:01, 3.22it/s] 76%|███████▋ | 13/17 [00:04<00:01, 3.21it/s] 82%|████████▏ | 14/17 [00:04<00:00, 3.20it/s] 88%|████████▊ | 15/17 [00:04<00:00, 3.22it/s] 94%|█████████▍| 16/17 [00:04<00:00, 3.21it/s] 100%|██████████| 17/17 [00:05<00:00, 3.76it/s] 100%|██████████| 17/17 [00:05<00:00, 3.32it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 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
saturation
Adjust saturation
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/ba01304066ae40ff935d5cb68e644d92/00000-3868250924.webp
https://files.tungsten.run/uploads/5cfa9b8c34db48d18fab16c06f47dc94/00001-3868250925.webp
https://files.tungsten.run/uploads/538a2e1ef24845d4be02494543511947/00002-3868250926.webp
https://files.tungsten.run/uploads/6e1e70121bec47819ec18b34f0612fa5/00003-3868250927.webp
This example was created by evevalentine2017
Finished in 75.5 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/clearvae_v2.3_fp16.safetensors Full prompt: (high quality, best quality), masterpiece, beach, sunset, toned, 2 pigtails, long hair, big fluffy hair, blonde hair, 1girl, tiny pink shiny bikini, navel, holding a bucket, shiny skin, <lora:add_detail:0.1> Full negative prompt: nsfw, nude, vagina, genitalia, loli, asian, ground, EasyNegativeV2, (artist name, signature, watermark:1.4), (ugly:1.2), (worst quality, poor details:1.4), blurry, large breasts, garters, garter belt, umbrella 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:53, 1.85s/it] 7%|▋ | 2/30 [00:03<00:42, 1.53s/it] 10%|█ | 3/30 [00:04<00:38, 1.42s/it] 13%|█▎ | 4/30 [00:05<00:35, 1.37s/it] 17%|█▋ | 5/30 [00:07<00:33, 1.35s/it] 20%|██ | 6/30 [00:08<00:31, 1.33s/it] 23%|██▎ | 7/30 [00:09<00:30, 1.32s/it] 27%|██▋ | 8/30 [00:10<00:29, 1.32s/it] 30%|███ | 9/30 [00:12<00:27, 1.31s/it] 33%|███▎ | 10/30 [00:13<00:26, 1.31s/it] 37%|███▋ | 11/30 [00:14<00:24, 1.31s/it] 40%|████ | 12/30 [00:16<00:23, 1.31s/it] 43%|████▎ | 13/30 [00:17<00:22, 1.31s/it] 47%|████▋ | 14/30 [00:18<00:20, 1.31s/it] 50%|█████ | 15/30 [00:20<00:19, 1.31s/it] 53%|█████▎ | 16/30 [00:21<00:18, 1.31s/it] 57%|█████▋ | 17/30 [00:22<00:17, 1.32s/it] 60%|██████ | 18/30 [00:24<00:15, 1.32s/it] 63%|██████▎ | 19/30 [00:25<00:14, 1.32s/it] 67%|██████▋ | 20/30 [00:26<00:13, 1.32s/it] 70%|███████ | 21/30 [00:28<00:11, 1.32s/it] 73%|███████▎ | 22/30 [00:29<00:10, 1.32s/it] 77%|███████▋ | 23/30 [00:30<00:09, 1.32s/it] 80%|████████ | 24/30 [00:32<00:07, 1.32s/it] 83%|████████▎ | 25/30 [00:33<00:06, 1.32s/it] 87%|████████▋ | 26/30 [00:34<00:05, 1.33s/it] 90%|█████████ | 27/30 [00:36<00:03, 1.32s/it] 93%|█████████▎| 28/30 [00:37<00:02, 1.32s/it] 97%|█████████▋| 29/30 [00:38<00:01, 1.32s/it] 100%|██████████| 30/30 [00:39<00:00, 1.13s/it] 100%|██████████| 30/30 [00:39<00:00, 1.31s/it] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.7ms Speed: 3.3ms preprocess, 7.7ms inference, 32.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:07, 2.22it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.74it/s] 18%|█▊ | 3/17 [00:01<00:04, 2.96it/s] 24%|██▎ | 4/17 [00:01<00:04, 3.03it/s] 29%|██▉ | 5/17 [00:01<00:03, 3.12it/s] 35%|███▌ | 6/17 [00:01<00:03, 3.17it/s] 41%|████ | 7/17 [00:02<00:03, 3.18it/s] 47%|████▋ | 8/17 [00:02<00:02, 3.20it/s] 53%|█████▎ | 9/17 [00:02<00:02, 3.22it/s] 59%|█████▉ | 10/17 [00:03<00:02, 3.22it/s] 65%|██████▍ | 11/17 [00:03<00:01, 3.22it/s] 71%|███████ | 12/17 [00:03<00:01, 3.24it/s] 76%|███████▋ | 13/17 [00:04<00:01, 3.24it/s] 82%|████████▏ | 14/17 [00:04<00:00, 3.23it/s] 88%|████████▊ | 15/17 [00:04<00:00, 3.24it/s] 94%|█████████▍| 16/17 [00:05<00:00, 3.23it/s] 100%|██████████| 17/17 [00:05<00:00, 3.79it/s] 100%|██████████| 17/17 [00:05<00:00, 3.25it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 2.9ms preprocess, 7.5ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:04, 3.37it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.33it/s] 18%|█▊ | 3/17 [00:00<00:04, 3.29it/s] 24%|██▎ | 4/17 [00:01<00:04, 3.23it/s] 29%|██▉ | 5/17 [00:01<00:03, 3.25it/s] 35%|███▌ | 6/17 [00:01<00:03, 3.26it/s] 41%|████ | 7/17 [00:02<00:03, 3.23it/s] 47%|████▋ | 8/17 [00:02<00:02, 3.23it/s] 53%|█████▎ | 9/17 [00:02<00:02, 3.24it/s] 59%|█████▉ | 10/17 [00:03<00:02, 3.22it/s] 65%|██████▍ | 11/17 [00:03<00:01, 3.23it/s] 71%|███████ | 12/17 [00:03<00:01, 3.24it/s] 76%|███████▋ | 13/17 [00:04<00:01, 3.23it/s] 82%|████████▏ | 14/17 [00:04<00:00, 3.23it/s] 88%|████████▊ | 15/17 [00:04<00:00, 3.24it/s] 94%|█████████▍| 16/17 [00:04<00:00, 3.24it/s] 100%|██████████| 17/17 [00:05<00:00, 3.81it/s] 100%|██████████| 17/17 [00:05<00:00, 3.34it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:04, 3.37it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.32it/s] 18%|█▊ | 3/17 [00:00<00:04, 3.28it/s] 24%|██▎ | 4/17 [00:01<00:04, 3.22it/s] 29%|██▉ | 5/17 [00:01<00:03, 3.24it/s] 35%|███▌ | 6/17 [00:01<00:03, 3.25it/s] 41%|████ | 7/17 [00:02<00:03, 3.22it/s] 47%|████▋ | 8/17 [00:02<00:02, 3.22it/s] 53%|█████▎ | 9/17 [00:02<00:02, 3.24it/s] 59%|█████▉ | 10/17 [00:03<00:02, 3.22it/s] 65%|██████▍ | 11/17 [00:03<00:01, 3.22it/s] 71%|███████ | 12/17 [00:03<00:01, 3.23it/s] 76%|███████▋ | 13/17 [00:04<00:01, 3.22it/s] 82%|████████▏ | 14/17 [00:04<00:00, 3.21it/s] 88%|████████▊ | 15/17 [00:04<00:00, 3.23it/s] 94%|█████████▍| 16/17 [00:04<00:00, 3.22it/s] 100%|██████████| 17/17 [00:05<00:00, 3.78it/s] 100%|██████████| 17/17 [00:05<00:00, 3.33it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.3ms Speed: 2.7ms preprocess, 7.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:04, 3.38it/s] 12%|█▏ | 2/17 [00:00<00:04, 3.32it/s] 18%|█▊ | 3/17 [00:00<00:04, 3.27it/s] 24%|██▎ | 4/17 [00:01<00:04, 3.23it/s] 29%|██▉ | 5/17 [00:01<00:03, 3.24it/s] 35%|███▌ | 6/17 [00:01<00:03, 3.24it/s] 41%|████ | 7/17 [00:02<00:03, 3.20it/s] 47%|████▋ | 8/17 [00:02<00:02, 3.21it/s] 53%|█████▎ | 9/17 [00:02<00:02, 3.22it/s] 59%|█████▉ | 10/17 [00:03<00:02, 3.21it/s] 65%|██████▍ | 11/17 [00:03<00:01, 3.21it/s] 71%|███████ | 12/17 [00:03<00:01, 3.22it/s] 76%|███████▋ | 13/17 [00:04<00:01, 3.21it/s] 82%|████████▏ | 14/17 [00:04<00:00, 3.20it/s] 88%|████████▊ | 15/17 [00:04<00:00, 3.22it/s] 94%|█████████▍| 16/17 [00:04<00:00, 3.21it/s] 100%|██████████| 17/17 [00:05<00:00, 3.76it/s] 100%|██████████| 17/17 [00:05<00:00, 3.32it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s Finished.