tungsten-logo
Sign In
lah-mysterious-sdxl
lah-mysterious-sdxl

lah-mysterious-sdxl

5 stars
Version: v4.0
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/57c3c4a059454bc2b7729860b2fd8699/00000-3887359567.webp
https://files.tungsten.run/uploads/b65a15371fbf470db48a115049b42693/00001-3887359568.webp
https://files.tungsten.run/uploads/67cd69e6188c425699e3f481f66a9a0d/00002-3887359569.webp
This example was created by sparks
Finished in 168.8 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Create a high-resolution, rendered with a level of precision and detail, photograph capturing an epic scale with vivid colors, sharp focus, and an unparalleled level of detail aesthetic, depicting sexy young athletic woman, slim perfect body shape, drinking beer at nightclub. The entire photograph should be bathed in soft, diffused lighting, RAW photo, full sharp, detailed face (high detailed skin:1.2), soft lighting, high quality, film grain., <lora:add-detail-xl:1.5> Full negative prompt: Focus on depicting quality issues like low quality, worst quality, jpeg artifacts, blurry, soft, and noisy visuals. The art style should encompass elements like comic, cartoon, artwork, western style, drawing, painting, crayon, sketch, graphite, and impressionist. Incorporate monochrome and effects, including monochrome, Bokeh effect, render, 3D, and a Greasy face appearance. The subject should emphasize anatomy and deformities such as zombie features, malformed limbs, extra limbs, cloned face, disfigurement, bad proportions, deformation, distortion, long neck, bad anatomy, bad hands, missing fingers, bad feet, too many fingers, poorly drawn hands, more than 2 thighs, mutated hands and fingers, bad face, extra limbs, three arms, and missing limbs. Avoid any text and signatures like watermark, signature, username, and artist name. Other negative traits to be aware of include a simple background, ugly visuals, duplicates, mutilation, mutations, NFSW content, negative_hand-neg, skin blemishes, errors, extra digits, fewer digits, and bad anatomy. 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:41, 3.50s/it] 7%|▋ | 2/30 [00:06<01:24, 3.00s/it] 10%|█ | 3/30 [00:08<01:18, 2.89s/it] 13%|█▎ | 4/30 [00:11<01:13, 2.84s/it] 17%|█▋ | 5/30 [00:14<01:10, 2.84s/it] 20%|██ | 6/30 [00:17<01:06, 2.78s/it] 23%|██▎ | 7/30 [00:20<01:04, 2.81s/it] 27%|██▋ | 8/30 [00:22<01:01, 2.80s/it] 30%|███ | 9/30 [00:25<00:58, 2.77s/it] 33%|███▎ | 10/30 [00:28<00:55, 2.77s/it] 37%|███▋ | 11/30 [00:31<00:52, 2.76s/it] 40%|████ | 12/30 [00:33<00:50, 2.79s/it] 43%|████▎ | 13/30 [00:36<00:47, 2.79s/it] 47%|████▋ | 14/30 [00:39<00:43, 2.70s/it] 50%|█████ | 15/30 [00:41<00:39, 2.66s/it] 53%|█████▎ | 16/30 [00:44<00:37, 2.65s/it] 57%|█████▋ | 17/30 [00:46<00:34, 2.62s/it] 60%|██████ | 18/30 [00:49<00:31, 2.62s/it] 63%|██████▎ | 19/30 [00:52<00:28, 2.63s/it] 67%|██████▋ | 20/30 [00:54<00:26, 2.65s/it] 70%|███████ | 21/30 [00:57<00:23, 2.62s/it] 73%|███████▎ | 22/30 [01:00<00:21, 2.64s/it] 77%|███████▋ | 23/30 [01:02<00:18, 2.58s/it] 80%|████████ | 24/30 [01:05<00:15, 2.59s/it] 83%|████████▎ | 25/30 [01:07<00:12, 2.53s/it] 87%|████████▋ | 26/30 [01:10<00:10, 2.53s/it] 90%|█████████ | 27/30 [01:12<00:07, 2.43s/it] 93%|█████████▎| 28/30 [01:14<00:04, 2.35s/it] 97%|█████████▋| 29/30 [01:15<00:02, 2.07s/it] 100%|██████████| 30/30 [01:17<00:00, 1.83s/it] 100%|██████████| 30/30 [01:17<00:00, 2.57s/it] Decoding latents in cuda:0... done in 2.39s Move latents to cpu... done in 0.03s 0: 640x512 1 face, 162.2ms Speed: 2.9ms preprocess, 162.2ms inference, 22.9ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:12, 1.26s/it] 18%|█▊ | 2/11 [00:02<00:10, 1.15s/it] 27%|██▋ | 3/11 [00:03<00:09, 1.15s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.09s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.09s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.06s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.05s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.02s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.01it/s] 91%|█████████ | 10/11 [00:10<00:00, 1.12it/s] 100%|██████████| 11/11 [00:10<00:00, 1.23it/s] 100%|██████████| 11/11 [00:10<00:00, 1.02it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x512 (no detections), 114.4ms Speed: 2.6ms preprocess, 114.4ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 512) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x512 1 face, 8.6ms Speed: 2.7ms preprocess, 8.6ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:11, 1.13s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.09s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.10s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.06s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.06s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.03s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.04s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.00s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.02it/s] 91%|█████████ | 10/11 [00:09<00:00, 1.13it/s] 100%|██████████| 11/11 [00:10<00:00, 1.25it/s] 100%|██████████| 11/11 [00:10<00:00, 1.04it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x512 2 hands, 7.6ms Speed: 2.6ms preprocess, 7.6ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:10, 1.10s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.06s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.09s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.08s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.08s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.06s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.05s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.02s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.01it/s] 91%|█████████ | 10/11 [00:09<00:00, 1.12it/s] 100%|██████████| 11/11 [00:10<00:00, 1.24it/s] 100%|██████████| 11/11 [00:10<00:00, 1.04it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:11, 1.12s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.09s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.09s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.07s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.08s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.06s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.06s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.03s/it] 82%|████████▏ | 9/11 [00:09<00:02, 1.00s/it] 91%|█████████ | 10/11 [00:10<00:00, 1.11it/s] 100%|██████████| 11/11 [00:10<00:00, 1.22it/s] 100%|██████████| 11/11 [00:10<00:00, 1.03it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x512 1 face, 8.3ms Speed: 2.7ms preprocess, 8.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:10, 1.09s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.06s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.09s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.06s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.07s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.03s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.04s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.00s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.02it/s] 91%|█████████ | 10/11 [00:09<00:00, 1.12it/s] 100%|██████████| 11/11 [00:10<00:00, 1.23it/s] 100%|██████████| 11/11 [00:10<00:00, 1.04it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x512 1 hand, 7.6ms Speed: 2.6ms preprocess, 7.6ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:11, 1.10s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.07s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.08s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.06s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.07s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.05s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.05s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.02s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.01it/s] 91%|█████████ | 10/11 [00:09<00:00, 1.12it/s] 100%|██████████| 11/11 [00:10<00:00, 1.24it/s] 100%|██████████| 11/11 [00:10<00:00, 1.04it/s] Decoding latents in cuda:0... done in 0.78s 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/57c3c4a059454bc2b7729860b2fd8699/00000-3887359567.webp
https://files.tungsten.run/uploads/b65a15371fbf470db48a115049b42693/00001-3887359568.webp
https://files.tungsten.run/uploads/67cd69e6188c425699e3f481f66a9a0d/00002-3887359569.webp
This example was created by sparks
Finished in 168.8 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Create a high-resolution, rendered with a level of precision and detail, photograph capturing an epic scale with vivid colors, sharp focus, and an unparalleled level of detail aesthetic, depicting sexy young athletic woman, slim perfect body shape, drinking beer at nightclub. The entire photograph should be bathed in soft, diffused lighting, RAW photo, full sharp, detailed face (high detailed skin:1.2), soft lighting, high quality, film grain., <lora:add-detail-xl:1.5> Full negative prompt: Focus on depicting quality issues like low quality, worst quality, jpeg artifacts, blurry, soft, and noisy visuals. The art style should encompass elements like comic, cartoon, artwork, western style, drawing, painting, crayon, sketch, graphite, and impressionist. Incorporate monochrome and effects, including monochrome, Bokeh effect, render, 3D, and a Greasy face appearance. The subject should emphasize anatomy and deformities such as zombie features, malformed limbs, extra limbs, cloned face, disfigurement, bad proportions, deformation, distortion, long neck, bad anatomy, bad hands, missing fingers, bad feet, too many fingers, poorly drawn hands, more than 2 thighs, mutated hands and fingers, bad face, extra limbs, three arms, and missing limbs. Avoid any text and signatures like watermark, signature, username, and artist name. Other negative traits to be aware of include a simple background, ugly visuals, duplicates, mutilation, mutations, NFSW content, negative_hand-neg, skin blemishes, errors, extra digits, fewer digits, and bad anatomy. 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:41, 3.50s/it] 7%|▋ | 2/30 [00:06<01:24, 3.00s/it] 10%|█ | 3/30 [00:08<01:18, 2.89s/it] 13%|█▎ | 4/30 [00:11<01:13, 2.84s/it] 17%|█▋ | 5/30 [00:14<01:10, 2.84s/it] 20%|██ | 6/30 [00:17<01:06, 2.78s/it] 23%|██▎ | 7/30 [00:20<01:04, 2.81s/it] 27%|██▋ | 8/30 [00:22<01:01, 2.80s/it] 30%|███ | 9/30 [00:25<00:58, 2.77s/it] 33%|███▎ | 10/30 [00:28<00:55, 2.77s/it] 37%|███▋ | 11/30 [00:31<00:52, 2.76s/it] 40%|████ | 12/30 [00:33<00:50, 2.79s/it] 43%|████▎ | 13/30 [00:36<00:47, 2.79s/it] 47%|████▋ | 14/30 [00:39<00:43, 2.70s/it] 50%|█████ | 15/30 [00:41<00:39, 2.66s/it] 53%|█████▎ | 16/30 [00:44<00:37, 2.65s/it] 57%|█████▋ | 17/30 [00:46<00:34, 2.62s/it] 60%|██████ | 18/30 [00:49<00:31, 2.62s/it] 63%|██████▎ | 19/30 [00:52<00:28, 2.63s/it] 67%|██████▋ | 20/30 [00:54<00:26, 2.65s/it] 70%|███████ | 21/30 [00:57<00:23, 2.62s/it] 73%|███████▎ | 22/30 [01:00<00:21, 2.64s/it] 77%|███████▋ | 23/30 [01:02<00:18, 2.58s/it] 80%|████████ | 24/30 [01:05<00:15, 2.59s/it] 83%|████████▎ | 25/30 [01:07<00:12, 2.53s/it] 87%|████████▋ | 26/30 [01:10<00:10, 2.53s/it] 90%|█████████ | 27/30 [01:12<00:07, 2.43s/it] 93%|█████████▎| 28/30 [01:14<00:04, 2.35s/it] 97%|█████████▋| 29/30 [01:15<00:02, 2.07s/it] 100%|██████████| 30/30 [01:17<00:00, 1.83s/it] 100%|██████████| 30/30 [01:17<00:00, 2.57s/it] Decoding latents in cuda:0... done in 2.39s Move latents to cpu... done in 0.03s 0: 640x512 1 face, 162.2ms Speed: 2.9ms preprocess, 162.2ms inference, 22.9ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:12, 1.26s/it] 18%|█▊ | 2/11 [00:02<00:10, 1.15s/it] 27%|██▋ | 3/11 [00:03<00:09, 1.15s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.09s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.09s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.06s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.05s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.02s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.01it/s] 91%|█████████ | 10/11 [00:10<00:00, 1.12it/s] 100%|██████████| 11/11 [00:10<00:00, 1.23it/s] 100%|██████████| 11/11 [00:10<00:00, 1.02it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x512 (no detections), 114.4ms Speed: 2.6ms preprocess, 114.4ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 512) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x512 1 face, 8.6ms Speed: 2.7ms preprocess, 8.6ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:11, 1.13s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.09s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.10s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.06s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.06s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.03s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.04s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.00s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.02it/s] 91%|█████████ | 10/11 [00:09<00:00, 1.13it/s] 100%|██████████| 11/11 [00:10<00:00, 1.25it/s] 100%|██████████| 11/11 [00:10<00:00, 1.04it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x512 2 hands, 7.6ms Speed: 2.6ms preprocess, 7.6ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:10, 1.10s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.06s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.09s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.08s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.08s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.06s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.05s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.02s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.01it/s] 91%|█████████ | 10/11 [00:09<00:00, 1.12it/s] 100%|██████████| 11/11 [00:10<00:00, 1.24it/s] 100%|██████████| 11/11 [00:10<00:00, 1.04it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:11, 1.12s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.09s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.09s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.07s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.08s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.06s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.06s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.03s/it] 82%|████████▏ | 9/11 [00:09<00:02, 1.00s/it] 91%|█████████ | 10/11 [00:10<00:00, 1.11it/s] 100%|██████████| 11/11 [00:10<00:00, 1.22it/s] 100%|██████████| 11/11 [00:10<00:00, 1.03it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x512 1 face, 8.3ms Speed: 2.7ms preprocess, 8.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:10, 1.09s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.06s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.09s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.06s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.07s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.03s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.04s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.00s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.02it/s] 91%|█████████ | 10/11 [00:09<00:00, 1.12it/s] 100%|██████████| 11/11 [00:10<00:00, 1.23it/s] 100%|██████████| 11/11 [00:10<00:00, 1.04it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x512 1 hand, 7.6ms Speed: 2.6ms preprocess, 7.6ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:01<00:11, 1.10s/it] 18%|█▊ | 2/11 [00:02<00:09, 1.07s/it] 27%|██▋ | 3/11 [00:03<00:08, 1.08s/it] 36%|███▋ | 4/11 [00:04<00:07, 1.06s/it] 45%|████▌ | 5/11 [00:05<00:06, 1.07s/it] 55%|█████▍ | 6/11 [00:06<00:05, 1.05s/it] 64%|██████▎ | 7/11 [00:07<00:04, 1.05s/it] 73%|███████▎ | 8/11 [00:08<00:03, 1.02s/it] 82%|████████▏ | 9/11 [00:09<00:01, 1.01it/s] 91%|█████████ | 10/11 [00:09<00:00, 1.12it/s] 100%|██████████| 11/11 [00:10<00:00, 1.24it/s] 100%|██████████| 11/11 [00:10<00:00, 1.04it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s Uploading outputs... Finished.