tungsten-logo
Sign In
Ninja Chibi with Heart & Soul XL
heart-and-soul-xl:v1.0
evevalentine2017
evevalentine2017
·
Mar 18
336
Input
prompt
Specify things to see in the output
highres,best quality, 1boy, chibi, animal, bird, black eyes, black hair, cat, chibi, cloud, cloudy sky, day, fence, from behind, holding, holding sword, holding weapon, looking at viewer, looking back, lying, male focus, on side, outdoors, profile, short hair, sky, solo, sword, water, weapon
negative_prompt
Specify things to not see in the output
worst quality, kid, loli, child
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1024
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
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
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.
1006478767
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++ 2M SDE Karras
samping_steps
Number of denoising steps
60
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
sdxl_vae.safetensors
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.
false
Output
https://files.tungsten.run/uploads/88ec220ab7924d568312b7366a4dc6ea/00000-1006478767.webp
https://files.tungsten.run/uploads/213c3b1151f748fc9c70934f4a7aec4b/00001-1006478768.webp
https://files.tungsten.run/uploads/3d349162d3d94f33b69c15fd979834f6/00002-1006478769.webp
Finished in 249.2 seconds
Preparing model evevalentine2017/heart-and-soul-xl:v1.0... v1.0: Pulling from evevalentine2017/heart-and-soul-xl 578acb154839: Already exists ac65017cfc56: Already exists 146269b80f9c: Already exists b51bc62cc3ca: Already exists 4ba34dd48a55: Already exists 2c0d7edf2b4f: Already exists bd3aa092d934: Already exists a2a0b079260c: Already exists 48e8a1cea0b1: Already exists 607175607db9: Already exists 44762e60be28: Already exists d1e8a6995bc7: Already exists 8915fc22d7d8: Already exists e186b03af121: Already exists 4f4fb700ef54: Already exists 030de23c0760: Already exists 84e5e3e9ffaa: Pull complete ea4db542c48b: Pull complete fae3c1cdb349: Pull complete Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: highres,best quality, 1boy, chibi, animal, bird, black eyes, black hair, cat, chibi, cloud, cloudy sky, day, fence, from behind, holding, holding sword, holding weapon, looking at viewer, looking back, lying, male focus, on side, outdoors, profile, short hair, sky, solo, sword, water, weapon Full negative prompt: worst quality, kid, loli, child 0%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:02<01:59, 2.02s/it] 3%|▎ | 2/60 [00:04<02:23, 2.47s/it] 5%|▌ | 3/60 [00:07<02:22, 2.50s/it] 7%|▋ | 4/60 [00:10<02:25, 2.60s/it] 8%|▊ | 5/60 [00:13<02:30, 2.73s/it] 10%|█ | 6/60 [00:15<02:30, 2.78s/it] 12%|█▏ | 7/60 [00:18<02:25, 2.75s/it] 13%|█▎ | 8/60 [00:21<02:17, 2.65s/it] 15%|█▌ | 9/60 [00:23<02:13, 2.61s/it] 17%|█▋ | 10/60 [00:26<02:12, 2.64s/it] 18%|█▊ | 11/60 [00:28<02:09, 2.65s/it] 20%|██ | 12/60 [00:31<02:08, 2.68s/it] 22%|██▏ | 13/60 [00:34<02:08, 2.73s/it] 23%|██▎ | 14/60 [00:37<02:05, 2.72s/it] 25%|██▌ | 15/60 [00:39<02:00, 2.68s/it] 27%|██▋ | 16/60 [00:42<01:59, 2.71s/it] 28%|██▊ | 17/60 [00:45<01:55, 2.69s/it] 30%|███ | 18/60 [00:48<01:54, 2.73s/it] 32%|███▏ | 19/60 [00:50<01:50, 2.70s/it] 33%|███▎ | 20/60 [00:53<01:48, 2.72s/it] 35%|███▌ | 21/60 [00:56<01:43, 2.66s/it] 37%|███▋ | 22/60 [00:58<01:42, 2.69s/it] 38%|███▊ | 23/60 [01:01<01:37, 2.64s/it] 40%|████ | 24/60 [01:03<01:35, 2.64s/it] 42%|████▏ | 25/60 [01:06<01:31, 2.61s/it] 43%|████▎ | 26/60 [01:09<01:30, 2.65s/it] 45%|████▌ | 27/60 [01:11<01:27, 2.65s/it] 47%|████▋ | 28/60 [01:14<01:21, 2.54s/it] 48%|████▊ | 29/60 [01:16<01:16, 2.48s/it] 50%|█████ | 30/60 [01:19<01:14, 2.50s/it] 52%|█████▏ | 31/60 [01:21<01:13, 2.54s/it] 53%|█████▎ | 32/60 [01:24<01:09, 2.49s/it] 55%|█████▌ | 33/60 [01:26<01:09, 2.58s/it] 57%|█████▋ | 34/60 [01:29<01:06, 2.54s/it] 58%|█████▊ | 35/60 [01:31<01:03, 2.52s/it] 60%|██████ | 36/60 [01:34<01:02, 2.60s/it] 62%|██████▏ | 37/60 [01:37<00:59, 2.58s/it] 63%|██████▎ | 38/60 [01:39<00:55, 2.50s/it] 65%|██████▌ | 39/60 [01:42<00:54, 2.58s/it] 67%|██████▋ | 40/60 [01:44<00:51, 2.57s/it] 68%|██████▊ | 41/60 [01:47<00:48, 2.55s/it] 70%|███████ | 42/60 [01:49<00:44, 2.49s/it] 72%|███████▏ | 43/60 [01:52<00:41, 2.47s/it] 73%|███████▎ | 44/60 [01:54<00:37, 2.37s/it] 75%|███████▌ | 45/60 [01:56<00:34, 2.29s/it] 77%|███████▋ | 46/60 [01:58<00:33, 2.37s/it] 78%|███████▊ | 47/60 [02:01<00:30, 2.33s/it] 80%|████████ | 48/60 [02:03<00:28, 2.34s/it] 82%|████████▏ | 49/60 [02:05<00:25, 2.32s/it] 83%|████████▎ | 50/60 [02:07<00:23, 2.31s/it] 85%|████████▌ | 51/60 [02:10<00:21, 2.38s/it] 87%|████████▋ | 52/60 [02:12<00:18, 2.25s/it] 88%|████████▊ | 53/60 [02:14<00:16, 2.30s/it] 90%|█████████ | 54/60 [02:16<00:13, 2.24s/it] 92%|█████████▏| 55/60 [02:19<00:11, 2.28s/it] 93%|█████████▎| 56/60 [02:21<00:09, 2.27s/it] 95%|█████████▌| 57/60 [02:24<00:07, 2.35s/it] 97%|█████████▋| 58/60 [02:26<00:04, 2.25s/it] 98%|█████████▊| 59/60 [02:27<00:02, 2.01s/it] 100%|██████████| 60/60 [02:28<00:00, 1.77s/it] 100%|██████████| 60/60 [02:28<00:00, 2.48s/it] Decoding latents in cuda:0... done in 2.34s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.6ms Speed: 3.7ms preprocess, 7.6ms inference, 21.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:34, 1.29s/it] 7%|▋ | 2/28 [00:02<00:30, 1.17s/it] 11%|█ | 3/28 [00:03<00:27, 1.11s/it] 14%|█▍ | 4/28 [00:04<00:28, 1.21s/it] 18%|█▊ | 5/28 [00:05<00:27, 1.19s/it] 21%|██▏ | 6/28 [00:07<00:25, 1.16s/it] 25%|██▌ | 7/28 [00:08<00:25, 1.20s/it] 29%|██▊ | 8/28 [00:09<00:22, 1.15s/it] 32%|███▏ | 9/28 [00:10<00:21, 1.11s/it] 36%|███▌ | 10/28 [00:11<00:19, 1.09s/it] 39%|███▉ | 11/28 [00:12<00:18, 1.08s/it] 43%|████▎ | 12/28 [00:13<00:16, 1.04s/it] 46%|████▋ | 13/28 [00:14<00:14, 1.00it/s] 50%|█████ | 14/28 [00:15<00:14, 1.01s/it] 54%|█████▎ | 15/28 [00:16<00:13, 1.00s/it] 57%|█████▋ | 16/28 [00:17<00:11, 1.00it/s] 61%|██████ | 17/28 [00:18<00:10, 1.01it/s] 64%|██████▍ | 18/28 [00:19<00:09, 1.02it/s] 68%|██████▊ | 19/28 [00:20<00:09, 1.00s/it] 71%|███████▏ | 20/28 [00:21<00:07, 1.04it/s] 75%|███████▌ | 21/28 [00:22<00:06, 1.01it/s] 79%|███████▊ | 22/28 [00:23<00:05, 1.02it/s] 82%|████████▏ | 23/28 [00:24<00:05, 1.00s/it] 86%|████████▌ | 24/28 [00:25<00:03, 1.01it/s] 89%|████████▉ | 25/28 [00:26<00:03, 1.02s/it] 93%|█████████▎| 26/28 [00:27<00:01, 1.00it/s] 96%|█████████▋| 27/28 [00:28<00:00, 1.08it/s] 100%|██████████| 28/28 [00:28<00:00, 1.19it/s] 100%|██████████| 28/28 [00:28<00:00, 1.02s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.9ms Speed: 3.4ms preprocess, 7.9ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:32, 1.19s/it] 7%|▋ | 2/28 [00:02<00:28, 1.09s/it] 11%|█ | 3/28 [00:03<00:27, 1.10s/it] 14%|█▍ | 4/28 [00:04<00:26, 1.12s/it] 18%|█▊ | 5/28 [00:05<00:25, 1.10s/it] 21%|██▏ | 6/28 [00:06<00:23, 1.06s/it] 25%|██▌ | 7/28 [00:07<00:23, 1.10s/it] 29%|██▊ | 8/28 [00:08<00:21, 1.08s/it] 32%|███▏ | 9/28 [00:09<00:20, 1.08s/it] 36%|███▌ | 10/28 [00:10<00:19, 1.06s/it] 39%|███▉ | 11/28 [00:11<00:17, 1.05s/it] 43%|████▎ | 12/28 [00:12<00:16, 1.01s/it] 46%|████▋ | 13/28 [00:13<00:14, 1.02it/s] 50%|█████ | 14/28 [00:14<00:13, 1.00it/s] 54%|█████▎ | 15/28 [00:15<00:12, 1.01it/s] 57%|█████▋ | 16/28 [00:16<00:11, 1.01it/s] 61%|██████ | 17/28 [00:17<00:10, 1.02it/s] 64%|██████▍ | 18/28 [00:18<00:09, 1.02it/s] 68%|██████▊ | 19/28 [00:19<00:09, 1.01s/it] 71%|███████▏ | 20/28 [00:20<00:07, 1.03it/s] 75%|███████▌ | 21/28 [00:21<00:06, 1.02it/s] 79%|███████▊ | 22/28 [00:22<00:05, 1.04it/s] 82%|████████▏ | 23/28 [00:23<00:04, 1.02it/s] 86%|████████▌ | 24/28 [00:24<00:03, 1.03it/s] 89%|████████▉ | 25/28 [00:25<00:02, 1.00it/s] 93%|█████████▎| 26/28 [00:26<00:01, 1.03it/s] 96%|█████████▋| 27/28 [00:27<00:00, 1.12it/s] 100%|██████████| 28/28 [00:27<00:00, 1.23it/s] 100%|██████████| 28/28 [00:27<00:00, 1.01it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.6ms Speed: 3.1ms preprocess, 7.6ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:31, 1.18s/it] 7%|▋ | 2/28 [00:02<00:28, 1.10s/it] 11%|█ | 3/28 [00:03<00:27, 1.09s/it] 14%|█▍ | 4/28 [00:04<00:26, 1.10s/it] 18%|█▊ | 5/28 [00:05<00:24, 1.08s/it] 21%|██▏ | 6/28 [00:06<00:23, 1.05s/it] 25%|██▌ | 7/28 [00:07<00:22, 1.08s/it] 29%|██▊ | 8/28 [00:08<00:21, 1.07s/it] 32%|███▏ | 9/28 [00:09<00:20, 1.06s/it] 36%|███▌ | 10/28 [00:10<00:18, 1.04s/it] 39%|███▉ | 11/28 [00:11<00:17, 1.03s/it] 43%|████▎ | 12/28 [00:12<00:16, 1.00s/it] 46%|████▋ | 13/28 [00:13<00:14, 1.03it/s] 50%|█████ | 14/28 [00:14<00:13, 1.01it/s] 54%|█████▎ | 15/28 [00:15<00:12, 1.02it/s] 57%|█████▋ | 16/28 [00:16<00:11, 1.01it/s] 61%|██████ | 17/28 [00:17<00:10, 1.01it/s] 64%|██████▍ | 18/28 [00:18<00:09, 1.02it/s] 68%|██████▊ | 19/28 [00:19<00:09, 1.00s/it] 71%|███████▏ | 20/28 [00:20<00:07, 1.04it/s] 75%|███████▌ | 21/28 [00:21<00:06, 1.01it/s] 79%|███████▊ | 22/28 [00:22<00:05, 1.03it/s] 82%|████████▏ | 23/28 [00:23<00:04, 1.02it/s] 86%|████████▌ | 24/28 [00:24<00:03, 1.03it/s] 89%|████████▉ | 25/28 [00:25<00:02, 1.01it/s] 93%|█████████▎| 26/28 [00:26<00:01, 1.05it/s] 96%|█████████▋| 27/28 [00:26<00:00, 1.15it/s] 100%|██████████| 28/28 [00:27<00:00, 1.27it/s] 100%|██████████| 28/28 [00:27<00:00, 1.02it/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
highres,best quality, 1boy, chibi, animal, bird, black eyes, black hair, cat, chibi, cloud, cloudy sky, day, fence, from behind, holding, holding sword, holding weapon, looking at viewer, looking back, lying, male focus, on side, outdoors, profile, short hair, sky, solo, sword, water, weapon
negative_prompt
Specify things to not see in the output
worst quality, kid, loli, child
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1024
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
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
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.
1006478767
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++ 2M SDE Karras
samping_steps
Number of denoising steps
60
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
sdxl_vae.safetensors
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.
false
https://files.tungsten.run/uploads/88ec220ab7924d568312b7366a4dc6ea/00000-1006478767.webp
https://files.tungsten.run/uploads/213c3b1151f748fc9c70934f4a7aec4b/00001-1006478768.webp
https://files.tungsten.run/uploads/3d349162d3d94f33b69c15fd979834f6/00002-1006478769.webp
Finished in 249.2 seconds
Preparing model evevalentine2017/heart-and-soul-xl:v1.0... v1.0: Pulling from evevalentine2017/heart-and-soul-xl 578acb154839: Already exists ac65017cfc56: Already exists 146269b80f9c: Already exists b51bc62cc3ca: Already exists 4ba34dd48a55: Already exists 2c0d7edf2b4f: Already exists bd3aa092d934: Already exists a2a0b079260c: Already exists 48e8a1cea0b1: Already exists 607175607db9: Already exists 44762e60be28: Already exists d1e8a6995bc7: Already exists 8915fc22d7d8: Already exists e186b03af121: Already exists 4f4fb700ef54: Already exists 030de23c0760: Already exists 84e5e3e9ffaa: Pull complete ea4db542c48b: Pull complete fae3c1cdb349: Pull complete Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: highres,best quality, 1boy, chibi, animal, bird, black eyes, black hair, cat, chibi, cloud, cloudy sky, day, fence, from behind, holding, holding sword, holding weapon, looking at viewer, looking back, lying, male focus, on side, outdoors, profile, short hair, sky, solo, sword, water, weapon Full negative prompt: worst quality, kid, loli, child 0%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:02<01:59, 2.02s/it] 3%|▎ | 2/60 [00:04<02:23, 2.47s/it] 5%|▌ | 3/60 [00:07<02:22, 2.50s/it] 7%|▋ | 4/60 [00:10<02:25, 2.60s/it] 8%|▊ | 5/60 [00:13<02:30, 2.73s/it] 10%|█ | 6/60 [00:15<02:30, 2.78s/it] 12%|█▏ | 7/60 [00:18<02:25, 2.75s/it] 13%|█▎ | 8/60 [00:21<02:17, 2.65s/it] 15%|█▌ | 9/60 [00:23<02:13, 2.61s/it] 17%|█▋ | 10/60 [00:26<02:12, 2.64s/it] 18%|█▊ | 11/60 [00:28<02:09, 2.65s/it] 20%|██ | 12/60 [00:31<02:08, 2.68s/it] 22%|██▏ | 13/60 [00:34<02:08, 2.73s/it] 23%|██▎ | 14/60 [00:37<02:05, 2.72s/it] 25%|██▌ | 15/60 [00:39<02:00, 2.68s/it] 27%|██▋ | 16/60 [00:42<01:59, 2.71s/it] 28%|██▊ | 17/60 [00:45<01:55, 2.69s/it] 30%|███ | 18/60 [00:48<01:54, 2.73s/it] 32%|███▏ | 19/60 [00:50<01:50, 2.70s/it] 33%|███▎ | 20/60 [00:53<01:48, 2.72s/it] 35%|███▌ | 21/60 [00:56<01:43, 2.66s/it] 37%|███▋ | 22/60 [00:58<01:42, 2.69s/it] 38%|███▊ | 23/60 [01:01<01:37, 2.64s/it] 40%|████ | 24/60 [01:03<01:35, 2.64s/it] 42%|████▏ | 25/60 [01:06<01:31, 2.61s/it] 43%|████▎ | 26/60 [01:09<01:30, 2.65s/it] 45%|████▌ | 27/60 [01:11<01:27, 2.65s/it] 47%|████▋ | 28/60 [01:14<01:21, 2.54s/it] 48%|████▊ | 29/60 [01:16<01:16, 2.48s/it] 50%|█████ | 30/60 [01:19<01:14, 2.50s/it] 52%|█████▏ | 31/60 [01:21<01:13, 2.54s/it] 53%|█████▎ | 32/60 [01:24<01:09, 2.49s/it] 55%|█████▌ | 33/60 [01:26<01:09, 2.58s/it] 57%|█████▋ | 34/60 [01:29<01:06, 2.54s/it] 58%|█████▊ | 35/60 [01:31<01:03, 2.52s/it] 60%|██████ | 36/60 [01:34<01:02, 2.60s/it] 62%|██████▏ | 37/60 [01:37<00:59, 2.58s/it] 63%|██████▎ | 38/60 [01:39<00:55, 2.50s/it] 65%|██████▌ | 39/60 [01:42<00:54, 2.58s/it] 67%|██████▋ | 40/60 [01:44<00:51, 2.57s/it] 68%|██████▊ | 41/60 [01:47<00:48, 2.55s/it] 70%|███████ | 42/60 [01:49<00:44, 2.49s/it] 72%|███████▏ | 43/60 [01:52<00:41, 2.47s/it] 73%|███████▎ | 44/60 [01:54<00:37, 2.37s/it] 75%|███████▌ | 45/60 [01:56<00:34, 2.29s/it] 77%|███████▋ | 46/60 [01:58<00:33, 2.37s/it] 78%|███████▊ | 47/60 [02:01<00:30, 2.33s/it] 80%|████████ | 48/60 [02:03<00:28, 2.34s/it] 82%|████████▏ | 49/60 [02:05<00:25, 2.32s/it] 83%|████████▎ | 50/60 [02:07<00:23, 2.31s/it] 85%|████████▌ | 51/60 [02:10<00:21, 2.38s/it] 87%|████████▋ | 52/60 [02:12<00:18, 2.25s/it] 88%|████████▊ | 53/60 [02:14<00:16, 2.30s/it] 90%|█████████ | 54/60 [02:16<00:13, 2.24s/it] 92%|█████████▏| 55/60 [02:19<00:11, 2.28s/it] 93%|█████████▎| 56/60 [02:21<00:09, 2.27s/it] 95%|█████████▌| 57/60 [02:24<00:07, 2.35s/it] 97%|█████████▋| 58/60 [02:26<00:04, 2.25s/it] 98%|█████████▊| 59/60 [02:27<00:02, 2.01s/it] 100%|██████████| 60/60 [02:28<00:00, 1.77s/it] 100%|██████████| 60/60 [02:28<00:00, 2.48s/it] Decoding latents in cuda:0... done in 2.34s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.6ms Speed: 3.7ms preprocess, 7.6ms inference, 21.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:34, 1.29s/it] 7%|▋ | 2/28 [00:02<00:30, 1.17s/it] 11%|█ | 3/28 [00:03<00:27, 1.11s/it] 14%|█▍ | 4/28 [00:04<00:28, 1.21s/it] 18%|█▊ | 5/28 [00:05<00:27, 1.19s/it] 21%|██▏ | 6/28 [00:07<00:25, 1.16s/it] 25%|██▌ | 7/28 [00:08<00:25, 1.20s/it] 29%|██▊ | 8/28 [00:09<00:22, 1.15s/it] 32%|███▏ | 9/28 [00:10<00:21, 1.11s/it] 36%|███▌ | 10/28 [00:11<00:19, 1.09s/it] 39%|███▉ | 11/28 [00:12<00:18, 1.08s/it] 43%|████▎ | 12/28 [00:13<00:16, 1.04s/it] 46%|████▋ | 13/28 [00:14<00:14, 1.00it/s] 50%|█████ | 14/28 [00:15<00:14, 1.01s/it] 54%|█████▎ | 15/28 [00:16<00:13, 1.00s/it] 57%|█████▋ | 16/28 [00:17<00:11, 1.00it/s] 61%|██████ | 17/28 [00:18<00:10, 1.01it/s] 64%|██████▍ | 18/28 [00:19<00:09, 1.02it/s] 68%|██████▊ | 19/28 [00:20<00:09, 1.00s/it] 71%|███████▏ | 20/28 [00:21<00:07, 1.04it/s] 75%|███████▌ | 21/28 [00:22<00:06, 1.01it/s] 79%|███████▊ | 22/28 [00:23<00:05, 1.02it/s] 82%|████████▏ | 23/28 [00:24<00:05, 1.00s/it] 86%|████████▌ | 24/28 [00:25<00:03, 1.01it/s] 89%|████████▉ | 25/28 [00:26<00:03, 1.02s/it] 93%|█████████▎| 26/28 [00:27<00:01, 1.00it/s] 96%|█████████▋| 27/28 [00:28<00:00, 1.08it/s] 100%|██████████| 28/28 [00:28<00:00, 1.19it/s] 100%|██████████| 28/28 [00:28<00:00, 1.02s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.9ms Speed: 3.4ms preprocess, 7.9ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:32, 1.19s/it] 7%|▋ | 2/28 [00:02<00:28, 1.09s/it] 11%|█ | 3/28 [00:03<00:27, 1.10s/it] 14%|█▍ | 4/28 [00:04<00:26, 1.12s/it] 18%|█▊ | 5/28 [00:05<00:25, 1.10s/it] 21%|██▏ | 6/28 [00:06<00:23, 1.06s/it] 25%|██▌ | 7/28 [00:07<00:23, 1.10s/it] 29%|██▊ | 8/28 [00:08<00:21, 1.08s/it] 32%|███▏ | 9/28 [00:09<00:20, 1.08s/it] 36%|███▌ | 10/28 [00:10<00:19, 1.06s/it] 39%|███▉ | 11/28 [00:11<00:17, 1.05s/it] 43%|████▎ | 12/28 [00:12<00:16, 1.01s/it] 46%|████▋ | 13/28 [00:13<00:14, 1.02it/s] 50%|█████ | 14/28 [00:14<00:13, 1.00it/s] 54%|█████▎ | 15/28 [00:15<00:12, 1.01it/s] 57%|█████▋ | 16/28 [00:16<00:11, 1.01it/s] 61%|██████ | 17/28 [00:17<00:10, 1.02it/s] 64%|██████▍ | 18/28 [00:18<00:09, 1.02it/s] 68%|██████▊ | 19/28 [00:19<00:09, 1.01s/it] 71%|███████▏ | 20/28 [00:20<00:07, 1.03it/s] 75%|███████▌ | 21/28 [00:21<00:06, 1.02it/s] 79%|███████▊ | 22/28 [00:22<00:05, 1.04it/s] 82%|████████▏ | 23/28 [00:23<00:04, 1.02it/s] 86%|████████▌ | 24/28 [00:24<00:03, 1.03it/s] 89%|████████▉ | 25/28 [00:25<00:02, 1.00it/s] 93%|█████████▎| 26/28 [00:26<00:01, 1.03it/s] 96%|█████████▋| 27/28 [00:27<00:00, 1.12it/s] 100%|██████████| 28/28 [00:27<00:00, 1.23it/s] 100%|██████████| 28/28 [00:27<00:00, 1.01it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.6ms Speed: 3.1ms preprocess, 7.6ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:31, 1.18s/it] 7%|▋ | 2/28 [00:02<00:28, 1.10s/it] 11%|█ | 3/28 [00:03<00:27, 1.09s/it] 14%|█▍ | 4/28 [00:04<00:26, 1.10s/it] 18%|█▊ | 5/28 [00:05<00:24, 1.08s/it] 21%|██▏ | 6/28 [00:06<00:23, 1.05s/it] 25%|██▌ | 7/28 [00:07<00:22, 1.08s/it] 29%|██▊ | 8/28 [00:08<00:21, 1.07s/it] 32%|███▏ | 9/28 [00:09<00:20, 1.06s/it] 36%|███▌ | 10/28 [00:10<00:18, 1.04s/it] 39%|███▉ | 11/28 [00:11<00:17, 1.03s/it] 43%|████▎ | 12/28 [00:12<00:16, 1.00s/it] 46%|████▋ | 13/28 [00:13<00:14, 1.03it/s] 50%|█████ | 14/28 [00:14<00:13, 1.01it/s] 54%|█████▎ | 15/28 [00:15<00:12, 1.02it/s] 57%|█████▋ | 16/28 [00:16<00:11, 1.01it/s] 61%|██████ | 17/28 [00:17<00:10, 1.01it/s] 64%|██████▍ | 18/28 [00:18<00:09, 1.02it/s] 68%|██████▊ | 19/28 [00:19<00:09, 1.00s/it] 71%|███████▏ | 20/28 [00:20<00:07, 1.04it/s] 75%|███████▌ | 21/28 [00:21<00:06, 1.01it/s] 79%|███████▊ | 22/28 [00:22<00:05, 1.03it/s] 82%|████████▏ | 23/28 [00:23<00:04, 1.02it/s] 86%|████████▌ | 24/28 [00:24<00:03, 1.03it/s] 89%|████████▉ | 25/28 [00:25<00:02, 1.01it/s] 93%|█████████▎| 26/28 [00:26<00:01, 1.05it/s] 96%|█████████▋| 27/28 [00:26<00:00, 1.15it/s] 100%|██████████| 28/28 [00:27<00:00, 1.27it/s] 100%|██████████| 28/28 [00:27<00:00, 1.02it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s Uploading outputs... Finished.