tungsten-logo
Sign In
animagine-xl
animagine-xl

animagine-xl

53 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/b43a615fbb92480c93827485161aaeb0/00000-2418283981.webp
https://files.tungsten.run/uploads/d1246aad86b74a3ea7b5e5243f65b1a3/00001-2418283982.webp
https://files.tungsten.run/uploads/874a8ef26ffd4063b0508a230d4c02f7/00002-2418283983.webp
This example was created by evevalentine2017
Finished in 99.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1 girl, twintails, curvy, pantyhose, hands in pockets, pleated skirt, hoodie, school uniform, hood down, blue skirt, cowboy shot, long sleeves, sailor collar, outdoor, ultra-resolution image, masterpiece, best quality. Full negative prompt: monochrome,male,abs,ribs,unaestheticXL2v10,, worst quality,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, signature 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:36, 1.37s/it] 7%|▋ | 2/28 [00:02<00:35, 1.37s/it] 11%|█ | 3/28 [00:04<00:34, 1.37s/it] 14%|█▍ | 4/28 [00:05<00:33, 1.38s/it] 18%|█▊ | 5/28 [00:06<00:31, 1.37s/it] 21%|██▏ | 6/28 [00:08<00:30, 1.37s/it] 25%|██▌ | 7/28 [00:09<00:28, 1.37s/it] 29%|██▊ | 8/28 [00:10<00:27, 1.37s/it] 32%|███▏ | 9/28 [00:12<00:26, 1.38s/it] 36%|███▌ | 10/28 [00:13<00:24, 1.38s/it] 39%|███▉ | 11/28 [00:15<00:23, 1.38s/it] 43%|████▎ | 12/28 [00:16<00:22, 1.38s/it] 46%|████▋ | 13/28 [00:17<00:20, 1.38s/it] 50%|█████ | 14/28 [00:19<00:19, 1.38s/it] 54%|█████▎ | 15/28 [00:20<00:17, 1.38s/it] 57%|█████▋ | 16/28 [00:22<00:16, 1.38s/it] 61%|██████ | 17/28 [00:23<00:15, 1.38s/it] 64%|██████▍ | 18/28 [00:24<00:13, 1.38s/it] 68%|██████▊ | 19/28 [00:26<00:12, 1.38s/it] 71%|███████▏ | 20/28 [00:27<00:11, 1.38s/it] 75%|███████▌ | 21/28 [00:28<00:09, 1.38s/it] 79%|███████▊ | 22/28 [00:30<00:08, 1.37s/it] 82%|████████▏ | 23/28 [00:31<00:06, 1.37s/it] 86%|████████▌ | 24/28 [00:33<00:05, 1.37s/it] 89%|████████▉ | 25/28 [00:34<00:04, 1.37s/it] 93%|█████████▎| 26/28 [00:35<00:02, 1.36s/it] 96%|█████████▋| 27/28 [00:37<00:01, 1.36s/it] 100%|██████████| 28/28 [00:38<00:00, 1.36s/it] 100%|██████████| 28/28 [00:38<00:00, 1.37s/it] Decoding latents in cuda:0... done in 2.39s Move latents to cpu... done in 0.03s 0: 640x640 5 faces, 7.8ms Speed: 3.2ms preprocess, 7.8ms inference, 30.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.23it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.41it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.38it/s] 31%|███ | 4/13 [00:01<00:04, 2.18it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.11it/s] 46%|████▌ | 6/13 [00:02<00:03, 2.07it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.05it/s] 62%|██████▏ | 8/13 [00:03<00:02, 1.95it/s] 69%|██████▉ | 9/13 [00:04<00:02, 1.89it/s] 77%|███████▋ | 10/13 [00:04<00:01, 1.87it/s] 85%|████████▍ | 11/13 [00:05<00:01, 1.91it/s] 92%|█████████▏| 12/13 [00:05<00:00, 1.91it/s] 100%|██████████| 13/13 [00:06<00:00, 1.89it/s] 100%|██████████| 13/13 [00:06<00:00, 1.99it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:06, 1.95it/s] 15%|█▌ | 2/13 [00:01<00:05, 1.97it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.11it/s] 31%|███ | 4/13 [00:01<00:04, 2.21it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.31it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.34it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.38it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.40it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.41it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.43it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.43it/s] 92%|█████████▏| 12/13 [00:05<00:00, 2.44it/s] 100%|██████████| 13/13 [00:05<00:00, 2.44it/s] 100%|██████████| 13/13 [00:05<00:00, 2.35it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.50it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.47it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.46it/s] 31%|███ | 4/13 [00:01<00:03, 2.44it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.44it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.44it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.44it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.44it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.44it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.45it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.45it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.45it/s] 100%|██████████| 13/13 [00:05<00:00, 2.44it/s] 100%|██████████| 13/13 [00:05<00:00, 2.45it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.51it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.49it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.45it/s] 31%|███ | 4/13 [00:01<00:03, 2.45it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.44it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.44it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.44it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.44it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.44it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.43it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.44it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.43it/s] 100%|██████████| 13/13 [00:05<00:00, 2.44it/s] 100%|██████████| 13/13 [00:05<00:00, 2.44it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.49it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.47it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.44it/s] 31%|███ | 4/13 [00:01<00:03, 2.45it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.42it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.43it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.43it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.43it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.43it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.43it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.43it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.43it/s] 100%|██████████| 13/13 [00:05<00:00, 2.43it/s] 100%|██████████| 13/13 [00:05<00:00, 2.43it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.2ms preprocess, 7.5ms inference, 2.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.56it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.53it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.43it/s] 31%|███ | 4/13 [00:01<00:03, 2.45it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.43it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.43it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.43it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.41it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.43it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.41it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.42it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.42it/s] 100%|██████████| 13/13 [00:05<00:00, 2.39it/s] 100%|██████████| 13/13 [00:05<00:00, 2.42it/s] Decoding latents in cuda:0... done in 0.81s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.55it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.52it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.42it/s] 31%|███ | 4/13 [00:01<00:03, 2.44it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.42it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.40it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.41it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.40it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.42it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.41it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.42it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.42it/s] 100%|██████████| 13/13 [00:05<00:00, 2.41it/s] 100%|██████████| 13/13 [00:05<00:00, 2.42it/s] Decoding latents in cuda:0... done in 0.8s 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/b43a615fbb92480c93827485161aaeb0/00000-2418283981.webp
https://files.tungsten.run/uploads/d1246aad86b74a3ea7b5e5243f65b1a3/00001-2418283982.webp
https://files.tungsten.run/uploads/874a8ef26ffd4063b0508a230d4c02f7/00002-2418283983.webp
This example was created by evevalentine2017
Finished in 99.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1 girl, twintails, curvy, pantyhose, hands in pockets, pleated skirt, hoodie, school uniform, hood down, blue skirt, cowboy shot, long sleeves, sailor collar, outdoor, ultra-resolution image, masterpiece, best quality. Full negative prompt: monochrome,male,abs,ribs,unaestheticXL2v10,, worst quality,lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, signature 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:36, 1.37s/it] 7%|▋ | 2/28 [00:02<00:35, 1.37s/it] 11%|█ | 3/28 [00:04<00:34, 1.37s/it] 14%|█▍ | 4/28 [00:05<00:33, 1.38s/it] 18%|█▊ | 5/28 [00:06<00:31, 1.37s/it] 21%|██▏ | 6/28 [00:08<00:30, 1.37s/it] 25%|██▌ | 7/28 [00:09<00:28, 1.37s/it] 29%|██▊ | 8/28 [00:10<00:27, 1.37s/it] 32%|███▏ | 9/28 [00:12<00:26, 1.38s/it] 36%|███▌ | 10/28 [00:13<00:24, 1.38s/it] 39%|███▉ | 11/28 [00:15<00:23, 1.38s/it] 43%|████▎ | 12/28 [00:16<00:22, 1.38s/it] 46%|████▋ | 13/28 [00:17<00:20, 1.38s/it] 50%|█████ | 14/28 [00:19<00:19, 1.38s/it] 54%|█████▎ | 15/28 [00:20<00:17, 1.38s/it] 57%|█████▋ | 16/28 [00:22<00:16, 1.38s/it] 61%|██████ | 17/28 [00:23<00:15, 1.38s/it] 64%|██████▍ | 18/28 [00:24<00:13, 1.38s/it] 68%|██████▊ | 19/28 [00:26<00:12, 1.38s/it] 71%|███████▏ | 20/28 [00:27<00:11, 1.38s/it] 75%|███████▌ | 21/28 [00:28<00:09, 1.38s/it] 79%|███████▊ | 22/28 [00:30<00:08, 1.37s/it] 82%|████████▏ | 23/28 [00:31<00:06, 1.37s/it] 86%|████████▌ | 24/28 [00:33<00:05, 1.37s/it] 89%|████████▉ | 25/28 [00:34<00:04, 1.37s/it] 93%|█████████▎| 26/28 [00:35<00:02, 1.36s/it] 96%|█████████▋| 27/28 [00:37<00:01, 1.36s/it] 100%|██████████| 28/28 [00:38<00:00, 1.36s/it] 100%|██████████| 28/28 [00:38<00:00, 1.37s/it] Decoding latents in cuda:0... done in 2.39s Move latents to cpu... done in 0.03s 0: 640x640 5 faces, 7.8ms Speed: 3.2ms preprocess, 7.8ms inference, 30.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.23it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.41it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.38it/s] 31%|███ | 4/13 [00:01<00:04, 2.18it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.11it/s] 46%|████▌ | 6/13 [00:02<00:03, 2.07it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.05it/s] 62%|██████▏ | 8/13 [00:03<00:02, 1.95it/s] 69%|██████▉ | 9/13 [00:04<00:02, 1.89it/s] 77%|███████▋ | 10/13 [00:04<00:01, 1.87it/s] 85%|████████▍ | 11/13 [00:05<00:01, 1.91it/s] 92%|█████████▏| 12/13 [00:05<00:00, 1.91it/s] 100%|██████████| 13/13 [00:06<00:00, 1.89it/s] 100%|██████████| 13/13 [00:06<00:00, 1.99it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:06, 1.95it/s] 15%|█▌ | 2/13 [00:01<00:05, 1.97it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.11it/s] 31%|███ | 4/13 [00:01<00:04, 2.21it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.31it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.34it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.38it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.40it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.41it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.43it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.43it/s] 92%|█████████▏| 12/13 [00:05<00:00, 2.44it/s] 100%|██████████| 13/13 [00:05<00:00, 2.44it/s] 100%|██████████| 13/13 [00:05<00:00, 2.35it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.50it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.47it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.46it/s] 31%|███ | 4/13 [00:01<00:03, 2.44it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.44it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.44it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.44it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.44it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.44it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.45it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.45it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.45it/s] 100%|██████████| 13/13 [00:05<00:00, 2.44it/s] 100%|██████████| 13/13 [00:05<00:00, 2.45it/s] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.51it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.49it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.45it/s] 31%|███ | 4/13 [00:01<00:03, 2.45it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.44it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.44it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.44it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.44it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.44it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.43it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.44it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.43it/s] 100%|██████████| 13/13 [00:05<00:00, 2.44it/s] 100%|██████████| 13/13 [00:05<00:00, 2.44it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.49it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.47it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.44it/s] 31%|███ | 4/13 [00:01<00:03, 2.45it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.42it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.43it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.43it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.43it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.43it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.43it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.43it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.43it/s] 100%|██████████| 13/13 [00:05<00:00, 2.43it/s] 100%|██████████| 13/13 [00:05<00:00, 2.43it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.2ms preprocess, 7.5ms inference, 2.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.56it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.53it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.43it/s] 31%|███ | 4/13 [00:01<00:03, 2.45it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.43it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.43it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.43it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.41it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.43it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.41it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.42it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.42it/s] 100%|██████████| 13/13 [00:05<00:00, 2.39it/s] 100%|██████████| 13/13 [00:05<00:00, 2.42it/s] Decoding latents in cuda:0... done in 0.81s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.1ms preprocess, 7.5ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:04, 2.55it/s] 15%|█▌ | 2/13 [00:00<00:04, 2.52it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.42it/s] 31%|███ | 4/13 [00:01<00:03, 2.44it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.42it/s] 46%|████▌ | 6/13 [00:02<00:02, 2.40it/s] 54%|█████▍ | 7/13 [00:02<00:02, 2.41it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.40it/s] 69%|██████▉ | 9/13 [00:03<00:01, 2.42it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.41it/s] 85%|████████▍ | 11/13 [00:04<00:00, 2.42it/s] 92%|█████████▏| 12/13 [00:04<00:00, 2.42it/s] 100%|██████████| 13/13 [00:05<00:00, 2.41it/s] 100%|██████████| 13/13 [00:05<00:00, 2.42it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s Uploading outputs... Finished.