tungsten-logo
Sign In
(Mexican) Girl with Socamerge AniMix XL
socamerge-animix-xl:v1.0
sparks
sparks
·
Feb 19
359
Input
prompt
Specify things to see in the output
(Cyberpunk:1.5), (3d anime style:1.5), (close shot, zoomed in upper body portrait:1.3). A thinking, (closed mouth:1.5) shy sexy strong young 23 year old (Mexican:1.3) woman with long straight bohemian black hair, amber eyes, (medium breasts:1.3), big ass, (perfect hands:1.3), She is wearing royal purple synthetic bodysuit, platform heels, She is slutty sitting, legs crossed facing diagonal to camera, in a orchard with (tall trees:1.5) with debris and buildings, arid landscape with (feathery gray leaves:1.5), (feathery blue flowers:1.5) and (ocean blue sky:1.5) with (galaxy overhead:1.5). noon, raining, cinematic lighting, vibrant colors, detailed skin texture, detailed cloth texture, beautiful detailed perfect face, intricate sharp details, ultra high res, <lora:EnvyBetterHiresFixXL01:1>
negative_prompt
Specify things to not see in the output
(watermark:1.5), (long torso:1.3), (tall torso:1.3), (hair accessory:1.1), (hair decoration:1.1), (cleft chin:1.1), (nasolabial crease:1.1), gloss, facial asymmetry, ring, eye bags, dark circles under eyes, bad hands, distorted fingers, unnatural hands, extra fingers, ugly, tiling, blurry, blurred, grainy, signature, draft, worst quality, low quality, leopard, tiger, zebra, cheetah, multiple planets, multiple moons
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1280
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.3
detail
Enhance/diminish detail while keeping the overall style/character
1
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2536348410
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 3M SDE Exponential
samping_steps
Number of denoising steps
40
cfg_scale
Scale for classifier-free guidance
6
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
EnvyBetterHiresFixXL01.safetensors
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.
false
Output
https://files.tungsten.run/uploads/ca26901c177043a0a61d491ae86636b1/00000-2536348410.webp
https://files.tungsten.run/uploads/d3ceeee785864672a3677798a475e600/00001-2536348411.webp
https://files.tungsten.run/uploads/b7f3fcd9cfd24d02871db00451a3395c/00002-2536348412.webp
Finished in 189.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: (Cyberpunk:1.5), (3d anime style:1.5), (close shot, zoomed in upper body portrait:1.3). A thinking, (closed mouth:1.5) shy sexy strong young 23 year old (Mexican:1.3) woman with long straight bohemian black hair, amber eyes, (medium breasts:1.3), big ass, (perfect hands:1.3), She is wearing royal purple synthetic bodysuit, platform heels, She is slutty sitting, legs crossed facing diagonal to camera, in a orchard with (tall trees:1.5) with debris and buildings, arid landscape with (feathery gray leaves:1.5), (feathery blue flowers:1.5) and (ocean blue sky:1.5) with (galaxy overhead:1.5). noon, raining, cinematic lighting, vibrant colors, detailed skin texture, detailed cloth texture, beautiful detailed perfect face, intricate sharp details, ultra high res, <lora:EnvyBetterHiresFixXL01:1>, <lora:add-detail-xl:1.0> Full negative prompt: (watermark:1.5), (long torso:1.3), (tall torso:1.3), (hair accessory:1.1), (hair decoration:1.1), (cleft chin:1.1), (nasolabial crease:1.1), gloss, facial asymmetry, ring, eye bags, dark circles under eyes, bad hands, distorted fingers, unnatural hands, extra fingers, ugly, tiling, blurry, blurred, grainy, signature, draft, worst quality, low quality, leopard, tiger, zebra, cheetah, multiple planets, multiple moons 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:04<02:36, 4.00s/it] 5%|▌ | 2/40 [00:07<02:18, 3.65s/it] 8%|▊ | 3/40 [00:11<02:15, 3.67s/it] 10%|█ | 4/40 [00:14<02:08, 3.58s/it] 12%|█▎ | 5/40 [00:18<02:04, 3.56s/it] 15%|█▌ | 6/40 [00:21<02:02, 3.61s/it] 18%|█▊ | 7/40 [00:25<01:58, 3.58s/it] 20%|██ | 8/40 [00:28<01:55, 3.60s/it] 22%|██▎ | 9/40 [00:32<01:50, 3.56s/it] 25%|██▌ | 10/40 [00:35<01:44, 3.49s/it] 28%|██▊ | 11/40 [00:39<01:40, 3.47s/it] 30%|███ | 12/40 [00:42<01:36, 3.46s/it] 32%|███▎ | 13/40 [00:45<01:32, 3.43s/it] 35%|███▌ | 14/40 [00:49<01:29, 3.44s/it] 38%|███▊ | 15/40 [00:52<01:25, 3.40s/it] 40%|████ | 16/40 [00:55<01:20, 3.36s/it] 42%|████▎ | 17/40 [00:59<01:16, 3.33s/it] 45%|████▌ | 18/40 [01:02<01:13, 3.34s/it] 48%|████▊ | 19/40 [01:05<01:08, 3.26s/it] 50%|█████ | 20/40 [01:08<01:04, 3.23s/it] 52%|█████▎ | 21/40 [01:12<01:02, 3.31s/it] 55%|█████▌ | 22/40 [01:15<00:59, 3.33s/it] 57%|█████▊ | 23/40 [01:18<00:54, 3.23s/it] 60%|██████ | 24/40 [01:21<00:50, 3.15s/it] 62%|██████▎ | 25/40 [01:24<00:47, 3.18s/it] 65%|██████▌ | 26/40 [01:28<00:44, 3.20s/it] 68%|██████▊ | 27/40 [01:31<00:41, 3.20s/it] 70%|███████ | 28/40 [01:34<00:38, 3.21s/it] 72%|███████▎ | 29/40 [01:37<00:34, 3.16s/it] 75%|███████▌ | 30/40 [01:41<00:33, 3.36s/it] 78%|███████▊ | 31/40 [01:44<00:29, 3.25s/it] 80%|████████ | 32/40 [01:47<00:25, 3.15s/it] 82%|████████▎ | 33/40 [01:50<00:22, 3.15s/it] 85%|████████▌ | 34/40 [01:53<00:18, 3.02s/it] 88%|████████▊ | 35/40 [01:56<00:14, 2.99s/it] 90%|█████████ | 36/40 [01:59<00:12, 3.04s/it] 92%|█████████▎| 37/40 [02:02<00:08, 2.97s/it] 95%|█████████▌| 38/40 [02:04<00:05, 2.83s/it] 98%|█████████▊| 39/40 [02:06<00:02, 2.53s/it] 100%|██████████| 40/40 [02:08<00:00, 2.28s/it] 100%|██████████| 40/40 [02:08<00:00, 3.20s/it] Decoding latents in cuda:0... done in 3.05s Move latents to cpu... done in 0.04s 0: 640x512 1 face, 164.9ms Speed: 3.2ms preprocess, 164.9ms inference, 16.1ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:01<00:13, 1.12s/it] 15%|█▌ | 2/13 [00:02<00:11, 1.05s/it] 23%|██▎ | 3/13 [00:03<00:10, 1.06s/it] 31%|███ | 4/13 [00:04<00:09, 1.02s/it] 38%|███▊ | 5/13 [00:05<00:07, 1.01it/s] 46%|████▌ | 6/13 [00:06<00:06, 1.01it/s] 54%|█████▍ | 7/13 [00:06<00:05, 1.06it/s] 62%|██████▏ | 8/13 [00:07<00:04, 1.07it/s] 69%|██████▉ | 9/13 [00:08<00:03, 1.05it/s] 77%|███████▋ | 10/13 [00:09<00:02, 1.07it/s] 85%|████████▍ | 11/13 [00:10<00:01, 1.13it/s] 92%|█████████▏| 12/13 [00:11<00:00, 1.27it/s] 100%|██████████| 13/13 [00:11<00:00, 1.43it/s] 100%|██████████| 13/13 [00:11<00:00, 1.12it/s] Decoding latents in cuda:0... done in 1.02s Move latents to cpu... done in 0.0s 0: 640x512 1 face, 8.3ms Speed: 2.2ms preprocess, 8.3ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:01<00:12, 1.05s/it] 15%|█▌ | 2/13 [00:02<00:11, 1.00s/it] 23%|██▎ | 3/13 [00:03<00:10, 1.03s/it] 31%|███ | 4/13 [00:04<00:08, 1.01it/s] 38%|███▊ | 5/13 [00:05<00:08, 1.08s/it] 46%|████▌ | 6/13 [00:06<00:08, 1.27s/it] 54%|█████▍ | 7/13 [00:08<00:07, 1.29s/it] 62%|██████▏ | 8/13 [00:09<00:05, 1.17s/it] 69%|██████▉ | 9/13 [00:10<00:04, 1.12s/it] 77%|███████▋ | 10/13 [00:10<00:03, 1.04s/it] 85%|████████▍ | 11/13 [00:11<00:01, 1.03it/s] 92%|█████████▏| 12/13 [00:12<00:00, 1.19it/s] 100%|██████████| 13/13 [00:12<00:00, 1.36it/s] 100%|██████████| 13/13 [00:12<00:00, 1.01it/s] Decoding latents in cuda:0... done in 1.02s Move latents to cpu... done in 0.0s 0: 640x512 1 face, 8.2ms Speed: 2.1ms preprocess, 8.2ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:01<00:12, 1.04s/it] 15%|█▌ | 2/13 [00:01<00:10, 1.01it/s] 23%|██▎ | 3/13 [00:03<00:10, 1.02s/it] 31%|███ | 4/13 [00:04<00:08, 1.00it/s] 38%|███▊ | 5/13 [00:04<00:07, 1.03it/s] 46%|████▌ | 6/13 [00:05<00:06, 1.03it/s] 54%|█████▍ | 7/13 [00:06<00:05, 1.07it/s] 62%|██████▏ | 8/13 [00:07<00:04, 1.07it/s] 69%|██████▉ | 9/13 [00:08<00:03, 1.05it/s] 77%|███████▋ | 10/13 [00:09<00:02, 1.07it/s] 85%|████████▍ | 11/13 [00:10<00:01, 1.12it/s] 92%|█████████▏| 12/13 [00:10<00:00, 1.27it/s] 100%|██████████| 13/13 [00:11<00:00, 1.43it/s] 100%|██████████| 13/13 [00:11<00:00, 1.14it/s] Decoding latents in cuda:0... done in 1.03s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt
Specify things to see in the output
(Cyberpunk:1.5), (3d anime style:1.5), (close shot, zoomed in upper body portrait:1.3). A thinking, (closed mouth:1.5) shy sexy strong young 23 year old (Mexican:1.3) woman with long straight bohemian black hair, amber eyes, (medium breasts:1.3), big ass, (perfect hands:1.3), She is wearing royal purple synthetic bodysuit, platform heels, She is slutty sitting, legs crossed facing diagonal to camera, in a orchard with (tall trees:1.5) with debris and buildings, arid landscape with (feathery gray leaves:1.5), (feathery blue flowers:1.5) and (ocean blue sky:1.5) with (galaxy overhead:1.5). noon, raining, cinematic lighting, vibrant colors, detailed skin texture, detailed cloth texture, beautiful detailed perfect face, intricate sharp details, ultra high res, <lora:EnvyBetterHiresFixXL01:1>
negative_prompt
Specify things to not see in the output
(watermark:1.5), (long torso:1.3), (tall torso:1.3), (hair accessory:1.1), (hair decoration:1.1), (cleft chin:1.1), (nasolabial crease:1.1), gloss, facial asymmetry, ring, eye bags, dark circles under eyes, bad hands, distorted fingers, unnatural hands, extra fingers, ugly, tiling, blurry, blurred, grainy, signature, draft, worst quality, low quality, leopard, tiger, zebra, cheetah, multiple planets, multiple moons
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1280
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.3
detail
Enhance/diminish detail while keeping the overall style/character
1
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2536348410
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 3M SDE Exponential
samping_steps
Number of denoising steps
40
cfg_scale
Scale for classifier-free guidance
6
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
EnvyBetterHiresFixXL01.safetensors
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.
false
https://files.tungsten.run/uploads/ca26901c177043a0a61d491ae86636b1/00000-2536348410.webp
https://files.tungsten.run/uploads/d3ceeee785864672a3677798a475e600/00001-2536348411.webp
https://files.tungsten.run/uploads/b7f3fcd9cfd24d02871db00451a3395c/00002-2536348412.webp
Finished in 189.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: (Cyberpunk:1.5), (3d anime style:1.5), (close shot, zoomed in upper body portrait:1.3). A thinking, (closed mouth:1.5) shy sexy strong young 23 year old (Mexican:1.3) woman with long straight bohemian black hair, amber eyes, (medium breasts:1.3), big ass, (perfect hands:1.3), She is wearing royal purple synthetic bodysuit, platform heels, She is slutty sitting, legs crossed facing diagonal to camera, in a orchard with (tall trees:1.5) with debris and buildings, arid landscape with (feathery gray leaves:1.5), (feathery blue flowers:1.5) and (ocean blue sky:1.5) with (galaxy overhead:1.5). noon, raining, cinematic lighting, vibrant colors, detailed skin texture, detailed cloth texture, beautiful detailed perfect face, intricate sharp details, ultra high res, <lora:EnvyBetterHiresFixXL01:1>, <lora:add-detail-xl:1.0> Full negative prompt: (watermark:1.5), (long torso:1.3), (tall torso:1.3), (hair accessory:1.1), (hair decoration:1.1), (cleft chin:1.1), (nasolabial crease:1.1), gloss, facial asymmetry, ring, eye bags, dark circles under eyes, bad hands, distorted fingers, unnatural hands, extra fingers, ugly, tiling, blurry, blurred, grainy, signature, draft, worst quality, low quality, leopard, tiger, zebra, cheetah, multiple planets, multiple moons 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:04<02:36, 4.00s/it] 5%|▌ | 2/40 [00:07<02:18, 3.65s/it] 8%|▊ | 3/40 [00:11<02:15, 3.67s/it] 10%|█ | 4/40 [00:14<02:08, 3.58s/it] 12%|█▎ | 5/40 [00:18<02:04, 3.56s/it] 15%|█▌ | 6/40 [00:21<02:02, 3.61s/it] 18%|█▊ | 7/40 [00:25<01:58, 3.58s/it] 20%|██ | 8/40 [00:28<01:55, 3.60s/it] 22%|██▎ | 9/40 [00:32<01:50, 3.56s/it] 25%|██▌ | 10/40 [00:35<01:44, 3.49s/it] 28%|██▊ | 11/40 [00:39<01:40, 3.47s/it] 30%|███ | 12/40 [00:42<01:36, 3.46s/it] 32%|███▎ | 13/40 [00:45<01:32, 3.43s/it] 35%|███▌ | 14/40 [00:49<01:29, 3.44s/it] 38%|███▊ | 15/40 [00:52<01:25, 3.40s/it] 40%|████ | 16/40 [00:55<01:20, 3.36s/it] 42%|████▎ | 17/40 [00:59<01:16, 3.33s/it] 45%|████▌ | 18/40 [01:02<01:13, 3.34s/it] 48%|████▊ | 19/40 [01:05<01:08, 3.26s/it] 50%|█████ | 20/40 [01:08<01:04, 3.23s/it] 52%|█████▎ | 21/40 [01:12<01:02, 3.31s/it] 55%|█████▌ | 22/40 [01:15<00:59, 3.33s/it] 57%|█████▊ | 23/40 [01:18<00:54, 3.23s/it] 60%|██████ | 24/40 [01:21<00:50, 3.15s/it] 62%|██████▎ | 25/40 [01:24<00:47, 3.18s/it] 65%|██████▌ | 26/40 [01:28<00:44, 3.20s/it] 68%|██████▊ | 27/40 [01:31<00:41, 3.20s/it] 70%|███████ | 28/40 [01:34<00:38, 3.21s/it] 72%|███████▎ | 29/40 [01:37<00:34, 3.16s/it] 75%|███████▌ | 30/40 [01:41<00:33, 3.36s/it] 78%|███████▊ | 31/40 [01:44<00:29, 3.25s/it] 80%|████████ | 32/40 [01:47<00:25, 3.15s/it] 82%|████████▎ | 33/40 [01:50<00:22, 3.15s/it] 85%|████████▌ | 34/40 [01:53<00:18, 3.02s/it] 88%|████████▊ | 35/40 [01:56<00:14, 2.99s/it] 90%|█████████ | 36/40 [01:59<00:12, 3.04s/it] 92%|█████████▎| 37/40 [02:02<00:08, 2.97s/it] 95%|█████████▌| 38/40 [02:04<00:05, 2.83s/it] 98%|█████████▊| 39/40 [02:06<00:02, 2.53s/it] 100%|██████████| 40/40 [02:08<00:00, 2.28s/it] 100%|██████████| 40/40 [02:08<00:00, 3.20s/it] Decoding latents in cuda:0... done in 3.05s Move latents to cpu... done in 0.04s 0: 640x512 1 face, 164.9ms Speed: 3.2ms preprocess, 164.9ms inference, 16.1ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:01<00:13, 1.12s/it] 15%|█▌ | 2/13 [00:02<00:11, 1.05s/it] 23%|██▎ | 3/13 [00:03<00:10, 1.06s/it] 31%|███ | 4/13 [00:04<00:09, 1.02s/it] 38%|███▊ | 5/13 [00:05<00:07, 1.01it/s] 46%|████▌ | 6/13 [00:06<00:06, 1.01it/s] 54%|█████▍ | 7/13 [00:06<00:05, 1.06it/s] 62%|██████▏ | 8/13 [00:07<00:04, 1.07it/s] 69%|██████▉ | 9/13 [00:08<00:03, 1.05it/s] 77%|███████▋ | 10/13 [00:09<00:02, 1.07it/s] 85%|████████▍ | 11/13 [00:10<00:01, 1.13it/s] 92%|█████████▏| 12/13 [00:11<00:00, 1.27it/s] 100%|██████████| 13/13 [00:11<00:00, 1.43it/s] 100%|██████████| 13/13 [00:11<00:00, 1.12it/s] Decoding latents in cuda:0... done in 1.02s Move latents to cpu... done in 0.0s 0: 640x512 1 face, 8.3ms Speed: 2.2ms preprocess, 8.3ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:01<00:12, 1.05s/it] 15%|█▌ | 2/13 [00:02<00:11, 1.00s/it] 23%|██▎ | 3/13 [00:03<00:10, 1.03s/it] 31%|███ | 4/13 [00:04<00:08, 1.01it/s] 38%|███▊ | 5/13 [00:05<00:08, 1.08s/it] 46%|████▌ | 6/13 [00:06<00:08, 1.27s/it] 54%|█████▍ | 7/13 [00:08<00:07, 1.29s/it] 62%|██████▏ | 8/13 [00:09<00:05, 1.17s/it] 69%|██████▉ | 9/13 [00:10<00:04, 1.12s/it] 77%|███████▋ | 10/13 [00:10<00:03, 1.04s/it] 85%|████████▍ | 11/13 [00:11<00:01, 1.03it/s] 92%|█████████▏| 12/13 [00:12<00:00, 1.19it/s] 100%|██████████| 13/13 [00:12<00:00, 1.36it/s] 100%|██████████| 13/13 [00:12<00:00, 1.01it/s] Decoding latents in cuda:0... done in 1.02s Move latents to cpu... done in 0.0s 0: 640x512 1 face, 8.2ms Speed: 2.1ms preprocess, 8.2ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:01<00:12, 1.04s/it] 15%|█▌ | 2/13 [00:01<00:10, 1.01it/s] 23%|██▎ | 3/13 [00:03<00:10, 1.02s/it] 31%|███ | 4/13 [00:04<00:08, 1.00it/s] 38%|███▊ | 5/13 [00:04<00:07, 1.03it/s] 46%|████▌ | 6/13 [00:05<00:06, 1.03it/s] 54%|█████▍ | 7/13 [00:06<00:05, 1.07it/s] 62%|██████▏ | 8/13 [00:07<00:04, 1.07it/s] 69%|██████▉ | 9/13 [00:08<00:03, 1.05it/s] 77%|███████▋ | 10/13 [00:09<00:02, 1.07it/s] 85%|████████▍ | 11/13 [00:10<00:01, 1.12it/s] 92%|█████████▏| 12/13 [00:10<00:00, 1.27it/s] 100%|██████████| 13/13 [00:11<00:00, 1.43it/s] 100%|██████████| 13/13 [00:11<00:00, 1.14it/s] Decoding latents in cuda:0... done in 1.03s Move latents to cpu... done in 0.0s Uploading outputs... Finished.