tungsten-logo
Sign In
Golden Knights with Hephaistos SD XL
hephaistos-sd-xl:v3.3
evevalentine2017
evevalentine2017
·
Jan 20
362
Input
prompt
Specify things to see in the output
(8K, masterpiece, award winning photo:1.3), (ultra highres, absurdres, ultradetailed, sharp focus, realistic colors:1.1), (hyperdetailed art of a paladin in black holy armor with cape, broadsword on back, visored medieval helmet), (perfect lighting, detailed shadows), Holy symbols
negative_prompt
Specify things to not see in the output
(worst quality, low quality, 2d, painting, cartoons, sketch:1.1), tooth, open mouth, dull, blurry, watermark, low quality, black and white, dull skin, lack of details, airbrushed skin, bad hands, mutated, grotesque, ugly hands, weird hands
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
true
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.
1679285659
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
70
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/85e44ecd078241699e2d15367ec1d1d5/00000-1679285659.webp
https://files.tungsten.run/uploads/7eb4d69a3f3b4a0792d50a771985b79f/00001-1679285660.webp
https://files.tungsten.run/uploads/3f61669d6fdc4e9293bbc1bd90dff334/00002-1679285661.webp
Finished in 216.3 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: (8K, masterpiece, award winning photo:1.3), (ultra highres, absurdres, ultradetailed, sharp focus, realistic colors:1.1), (hyperdetailed art of a paladin in black holy armor with cape, broadsword on back, visored medieval helmet), (perfect lighting, detailed shadows), Holy symbols Full negative prompt: (worst quality, low quality, 2d, painting, cartoons, sketch:1.1), tooth, open mouth, dull, blurry, watermark, low quality, black and white, dull skin, lack of details, airbrushed skin, bad hands, mutated, grotesque, ugly hands, weird hands 0%| | 0/70 [00:00<?, ?it/s] 1%|▏ | 1/70 [00:02<02:28, 2.15s/it] 3%|▎ | 2/70 [00:04<02:46, 2.45s/it] 4%|▍ | 3/70 [00:07<02:57, 2.64s/it] 6%|▌ | 4/70 [00:10<02:57, 2.68s/it] 7%|▋ | 5/70 [00:13<02:57, 2.73s/it] 9%|▊ | 6/70 [00:16<02:56, 2.76s/it] 10%|█ | 7/70 [00:19<02:57, 2.83s/it] 11%|█▏ | 8/70 [00:21<02:54, 2.81s/it] 13%|█▎ | 9/70 [00:24<02:51, 2.81s/it] 14%|█▍ | 10/70 [00:27<02:45, 2.76s/it] 16%|█▌ | 11/70 [00:30<02:42, 2.76s/it] 17%|█▋ | 12/70 [00:32<02:40, 2.77s/it] 19%|█▊ | 13/70 [00:35<02:37, 2.76s/it] 20%|██ | 14/70 [00:38<02:35, 2.77s/it] 21%|██▏ | 15/70 [00:41<02:30, 2.74s/it] 23%|██▎ | 16/70 [00:43<02:30, 2.79s/it] 24%|██▍ | 17/70 [00:46<02:21, 2.67s/it] 26%|██▌ | 18/70 [00:48<02:14, 2.59s/it] 27%|██▋ | 19/70 [00:51<02:13, 2.62s/it] 29%|██▊ | 20/70 [00:54<02:13, 2.66s/it] 30%|███ | 21/70 [00:56<02:12, 2.71s/it] 31%|███▏ | 22/70 [00:59<02:10, 2.71s/it] 33%|███▎ | 23/70 [01:02<02:09, 2.76s/it] 34%|███▍ | 24/70 [01:05<02:05, 2.72s/it] 36%|███▌ | 25/70 [01:08<02:03, 2.75s/it] 37%|███▋ | 26/70 [01:10<01:57, 2.67s/it] 39%|███▊ | 27/70 [01:13<01:53, 2.65s/it] 40%|████ | 28/70 [01:15<01:50, 2.64s/it] 41%|████▏ | 29/70 [01:18<01:49, 2.66s/it] 43%|████▎ | 30/70 [01:21<01:47, 2.68s/it] 44%|████▍ | 31/70 [01:23<01:45, 2.71s/it] 46%|████▌ | 32/70 [01:26<01:43, 2.73s/it] 47%|████▋ | 33/70 [01:29<01:38, 2.66s/it] 49%|████▊ | 34/70 [01:31<01:36, 2.68s/it] 50%|█████ | 35/70 [01:34<01:31, 2.62s/it] 51%|█████▏ | 36/70 [01:37<01:29, 2.64s/it] 53%|█████▎ | 37/70 [01:39<01:25, 2.58s/it] 54%|█████▍ | 38/70 [01:42<01:21, 2.55s/it] 56%|█████▌ | 39/70 [01:44<01:20, 2.59s/it] 57%|█████▋ | 40/70 [01:47<01:17, 2.57s/it] 59%|█████▊ | 41/70 [01:49<01:14, 2.55s/it] 60%|██████ | 42/70 [01:52<01:12, 2.57s/it] 61%|██████▏ | 43/70 [01:54<01:08, 2.54s/it] 63%|██████▎ | 44/70 [01:57<01:05, 2.53s/it] 64%|██████▍ | 45/70 [01:59<01:03, 2.55s/it] 66%|██████▌ | 46/70 [02:02<01:02, 2.61s/it] 67%|██████▋ | 47/70 [02:05<00:59, 2.59s/it] 69%|██████▊ | 48/70 [02:07<00:56, 2.58s/it] 70%|███████ | 49/70 [02:10<00:52, 2.48s/it] 71%|███████▏ | 50/70 [02:12<00:50, 2.51s/it] 73%|███████▎ | 51/70 [02:15<00:48, 2.55s/it] 74%|███████▍ | 52/70 [02:17<00:46, 2.59s/it] 76%|███████▌ | 53/70 [02:20<00:43, 2.56s/it] 77%|███████▋ | 54/70 [02:23<00:41, 2.57s/it] 79%|███████▊ | 55/70 [02:25<00:38, 2.54s/it] 80%|████████ | 56/70 [02:27<00:35, 2.53s/it] 81%|████████▏ | 57/70 [02:30<00:32, 2.53s/it] 83%|████████▎ | 58/70 [02:32<00:29, 2.48s/it] 84%|████████▍ | 59/70 [02:35<00:26, 2.40s/it] 86%|████████▌ | 60/70 [02:37<00:23, 2.37s/it] 87%|████████▋ | 61/70 [02:39<00:21, 2.44s/it] 89%|████████▊ | 62/70 [02:42<00:18, 2.35s/it] 90%|█████████ | 63/70 [02:44<00:16, 2.38s/it] 91%|█████████▏| 64/70 [02:46<00:14, 2.36s/it] 93%|█████████▎| 65/70 [02:49<00:12, 2.43s/it] 94%|█████████▍| 66/70 [02:51<00:09, 2.30s/it] 96%|█████████▌| 67/70 [02:54<00:07, 2.36s/it] 97%|█████████▋| 68/70 [02:56<00:04, 2.31s/it] 99%|█████████▊| 69/70 [02:57<00:02, 2.06s/it] 100%|██████████| 70/70 [02:59<00:00, 1.84s/it] 100%|██████████| 70/70 [02:59<00:00, 2.56s/it] Decoding latents in cuda:0... done in 2.4s Move latents to cpu... done in 0.03s 0: 640x640 (no detections), 7.6ms Speed: 3.2ms preprocess, 7.6ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 7.2ms Speed: 3.1ms preprocess, 7.2ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 (no detections), 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 (no detections), 7.1ms Speed: 2.9ms preprocess, 7.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 (no detections), 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x640 1 hand, 7.1ms Speed: 3.0ms preprocess, 7.1ms inference, 10.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:00<00:28, 1.11it/s] 6%|▋ | 2/32 [00:01<00:25, 1.19it/s] 9%|▉ | 3/32 [00:02<00:23, 1.22it/s] 12%|█▎ | 4/32 [00:03<00:22, 1.22it/s] 16%|█▌ | 5/32 [00:04<00:21, 1.24it/s] 19%|█▉ | 6/32 [00:04<00:20, 1.25it/s] 22%|██▏ | 7/32 [00:05<00:20, 1.24it/s] 25%|██▌ | 8/32 [00:06<00:19, 1.21it/s] 28%|██▊ | 9/32 [00:07<00:18, 1.23it/s] 31%|███▏ | 10/32 [00:08<00:17, 1.24it/s] 34%|███▍ | 11/32 [00:08<00:16, 1.30it/s] 38%|███▊ | 12/32 [00:09<00:15, 1.28it/s] 41%|████ | 13/32 [00:10<00:15, 1.26it/s] 44%|████▍ | 14/32 [00:11<00:14, 1.24it/s] 47%|████▋ | 15/32 [00:12<00:13, 1.26it/s] 50%|█████ | 16/32 [00:12<00:12, 1.25it/s] 53%|█████▎ | 17/32 [00:13<00:11, 1.26it/s] 56%|█████▋ | 18/32 [00:14<00:11, 1.27it/s] 59%|█████▉ | 19/32 [00:15<00:10, 1.28it/s] 62%|██████▎ | 20/32 [00:15<00:09, 1.29it/s] 66%|██████▌ | 21/32 [00:16<00:08, 1.33it/s] 69%|██████▉ | 22/32 [00:17<00:07, 1.34it/s] 72%|███████▏ | 23/32 [00:18<00:06, 1.29it/s] 75%|███████▌ | 24/32 [00:18<00:05, 1.34it/s] 78%|███████▊ | 25/32 [00:19<00:05, 1.32it/s] 81%|████████▏ | 26/32 [00:20<00:04, 1.35it/s] 84%|████████▍ | 27/32 [00:21<00:03, 1.32it/s] 88%|████████▊ | 28/32 [00:21<00:02, 1.40it/s] 91%|█████████ | 29/32 [00:22<00:02, 1.39it/s] 94%|█████████▍| 30/32 [00:23<00:01, 1.42it/s] 97%|█████████▋| 31/32 [00:23<00:00, 1.59it/s] 100%|██████████| 32/32 [00:24<00:00, 1.79it/s] 100%|██████████| 32/32 [00:24<00:00, 1.33it/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
(8K, masterpiece, award winning photo:1.3), (ultra highres, absurdres, ultradetailed, sharp focus, realistic colors:1.1), (hyperdetailed art of a paladin in black holy armor with cape, broadsword on back, visored medieval helmet), (perfect lighting, detailed shadows), Holy symbols
negative_prompt
Specify things to not see in the output
(worst quality, low quality, 2d, painting, cartoons, sketch:1.1), tooth, open mouth, dull, blurry, watermark, low quality, black and white, dull skin, lack of details, airbrushed skin, bad hands, mutated, grotesque, ugly hands, weird hands
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
true
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.
1679285659
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
70
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/85e44ecd078241699e2d15367ec1d1d5/00000-1679285659.webp
https://files.tungsten.run/uploads/7eb4d69a3f3b4a0792d50a771985b79f/00001-1679285660.webp
https://files.tungsten.run/uploads/3f61669d6fdc4e9293bbc1bd90dff334/00002-1679285661.webp
Finished in 216.3 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: (8K, masterpiece, award winning photo:1.3), (ultra highres, absurdres, ultradetailed, sharp focus, realistic colors:1.1), (hyperdetailed art of a paladin in black holy armor with cape, broadsword on back, visored medieval helmet), (perfect lighting, detailed shadows), Holy symbols Full negative prompt: (worst quality, low quality, 2d, painting, cartoons, sketch:1.1), tooth, open mouth, dull, blurry, watermark, low quality, black and white, dull skin, lack of details, airbrushed skin, bad hands, mutated, grotesque, ugly hands, weird hands 0%| | 0/70 [00:00<?, ?it/s] 1%|▏ | 1/70 [00:02<02:28, 2.15s/it] 3%|▎ | 2/70 [00:04<02:46, 2.45s/it] 4%|▍ | 3/70 [00:07<02:57, 2.64s/it] 6%|▌ | 4/70 [00:10<02:57, 2.68s/it] 7%|▋ | 5/70 [00:13<02:57, 2.73s/it] 9%|▊ | 6/70 [00:16<02:56, 2.76s/it] 10%|█ | 7/70 [00:19<02:57, 2.83s/it] 11%|█▏ | 8/70 [00:21<02:54, 2.81s/it] 13%|█▎ | 9/70 [00:24<02:51, 2.81s/it] 14%|█▍ | 10/70 [00:27<02:45, 2.76s/it] 16%|█▌ | 11/70 [00:30<02:42, 2.76s/it] 17%|█▋ | 12/70 [00:32<02:40, 2.77s/it] 19%|█▊ | 13/70 [00:35<02:37, 2.76s/it] 20%|██ | 14/70 [00:38<02:35, 2.77s/it] 21%|██▏ | 15/70 [00:41<02:30, 2.74s/it] 23%|██▎ | 16/70 [00:43<02:30, 2.79s/it] 24%|██▍ | 17/70 [00:46<02:21, 2.67s/it] 26%|██▌ | 18/70 [00:48<02:14, 2.59s/it] 27%|██▋ | 19/70 [00:51<02:13, 2.62s/it] 29%|██▊ | 20/70 [00:54<02:13, 2.66s/it] 30%|███ | 21/70 [00:56<02:12, 2.71s/it] 31%|███▏ | 22/70 [00:59<02:10, 2.71s/it] 33%|███▎ | 23/70 [01:02<02:09, 2.76s/it] 34%|███▍ | 24/70 [01:05<02:05, 2.72s/it] 36%|███▌ | 25/70 [01:08<02:03, 2.75s/it] 37%|███▋ | 26/70 [01:10<01:57, 2.67s/it] 39%|███▊ | 27/70 [01:13<01:53, 2.65s/it] 40%|████ | 28/70 [01:15<01:50, 2.64s/it] 41%|████▏ | 29/70 [01:18<01:49, 2.66s/it] 43%|████▎ | 30/70 [01:21<01:47, 2.68s/it] 44%|████▍ | 31/70 [01:23<01:45, 2.71s/it] 46%|████▌ | 32/70 [01:26<01:43, 2.73s/it] 47%|████▋ | 33/70 [01:29<01:38, 2.66s/it] 49%|████▊ | 34/70 [01:31<01:36, 2.68s/it] 50%|█████ | 35/70 [01:34<01:31, 2.62s/it] 51%|█████▏ | 36/70 [01:37<01:29, 2.64s/it] 53%|█████▎ | 37/70 [01:39<01:25, 2.58s/it] 54%|█████▍ | 38/70 [01:42<01:21, 2.55s/it] 56%|█████▌ | 39/70 [01:44<01:20, 2.59s/it] 57%|█████▋ | 40/70 [01:47<01:17, 2.57s/it] 59%|█████▊ | 41/70 [01:49<01:14, 2.55s/it] 60%|██████ | 42/70 [01:52<01:12, 2.57s/it] 61%|██████▏ | 43/70 [01:54<01:08, 2.54s/it] 63%|██████▎ | 44/70 [01:57<01:05, 2.53s/it] 64%|██████▍ | 45/70 [01:59<01:03, 2.55s/it] 66%|██████▌ | 46/70 [02:02<01:02, 2.61s/it] 67%|██████▋ | 47/70 [02:05<00:59, 2.59s/it] 69%|██████▊ | 48/70 [02:07<00:56, 2.58s/it] 70%|███████ | 49/70 [02:10<00:52, 2.48s/it] 71%|███████▏ | 50/70 [02:12<00:50, 2.51s/it] 73%|███████▎ | 51/70 [02:15<00:48, 2.55s/it] 74%|███████▍ | 52/70 [02:17<00:46, 2.59s/it] 76%|███████▌ | 53/70 [02:20<00:43, 2.56s/it] 77%|███████▋ | 54/70 [02:23<00:41, 2.57s/it] 79%|███████▊ | 55/70 [02:25<00:38, 2.54s/it] 80%|████████ | 56/70 [02:27<00:35, 2.53s/it] 81%|████████▏ | 57/70 [02:30<00:32, 2.53s/it] 83%|████████▎ | 58/70 [02:32<00:29, 2.48s/it] 84%|████████▍ | 59/70 [02:35<00:26, 2.40s/it] 86%|████████▌ | 60/70 [02:37<00:23, 2.37s/it] 87%|████████▋ | 61/70 [02:39<00:21, 2.44s/it] 89%|████████▊ | 62/70 [02:42<00:18, 2.35s/it] 90%|█████████ | 63/70 [02:44<00:16, 2.38s/it] 91%|█████████▏| 64/70 [02:46<00:14, 2.36s/it] 93%|█████████▎| 65/70 [02:49<00:12, 2.43s/it] 94%|█████████▍| 66/70 [02:51<00:09, 2.30s/it] 96%|█████████▌| 67/70 [02:54<00:07, 2.36s/it] 97%|█████████▋| 68/70 [02:56<00:04, 2.31s/it] 99%|█████████▊| 69/70 [02:57<00:02, 2.06s/it] 100%|██████████| 70/70 [02:59<00:00, 1.84s/it] 100%|██████████| 70/70 [02:59<00:00, 2.56s/it] Decoding latents in cuda:0... done in 2.4s Move latents to cpu... done in 0.03s 0: 640x640 (no detections), 7.6ms Speed: 3.2ms preprocess, 7.6ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 7.2ms Speed: 3.1ms preprocess, 7.2ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 (no detections), 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 (no detections), 7.1ms Speed: 2.9ms preprocess, 7.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 (no detections), 7.4ms Speed: 2.9ms preprocess, 7.4ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x640 1 hand, 7.1ms Speed: 3.0ms preprocess, 7.1ms inference, 10.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:00<00:28, 1.11it/s] 6%|▋ | 2/32 [00:01<00:25, 1.19it/s] 9%|▉ | 3/32 [00:02<00:23, 1.22it/s] 12%|█▎ | 4/32 [00:03<00:22, 1.22it/s] 16%|█▌ | 5/32 [00:04<00:21, 1.24it/s] 19%|█▉ | 6/32 [00:04<00:20, 1.25it/s] 22%|██▏ | 7/32 [00:05<00:20, 1.24it/s] 25%|██▌ | 8/32 [00:06<00:19, 1.21it/s] 28%|██▊ | 9/32 [00:07<00:18, 1.23it/s] 31%|███▏ | 10/32 [00:08<00:17, 1.24it/s] 34%|███▍ | 11/32 [00:08<00:16, 1.30it/s] 38%|███▊ | 12/32 [00:09<00:15, 1.28it/s] 41%|████ | 13/32 [00:10<00:15, 1.26it/s] 44%|████▍ | 14/32 [00:11<00:14, 1.24it/s] 47%|████▋ | 15/32 [00:12<00:13, 1.26it/s] 50%|█████ | 16/32 [00:12<00:12, 1.25it/s] 53%|█████▎ | 17/32 [00:13<00:11, 1.26it/s] 56%|█████▋ | 18/32 [00:14<00:11, 1.27it/s] 59%|█████▉ | 19/32 [00:15<00:10, 1.28it/s] 62%|██████▎ | 20/32 [00:15<00:09, 1.29it/s] 66%|██████▌ | 21/32 [00:16<00:08, 1.33it/s] 69%|██████▉ | 22/32 [00:17<00:07, 1.34it/s] 72%|███████▏ | 23/32 [00:18<00:06, 1.29it/s] 75%|███████▌ | 24/32 [00:18<00:05, 1.34it/s] 78%|███████▊ | 25/32 [00:19<00:05, 1.32it/s] 81%|████████▏ | 26/32 [00:20<00:04, 1.35it/s] 84%|████████▍ | 27/32 [00:21<00:03, 1.32it/s] 88%|████████▊ | 28/32 [00:21<00:02, 1.40it/s] 91%|█████████ | 29/32 [00:22<00:02, 1.39it/s] 94%|█████████▍| 30/32 [00:23<00:01, 1.42it/s] 97%|█████████▋| 31/32 [00:23<00:00, 1.59it/s] 100%|██████████| 32/32 [00:24<00:00, 1.79it/s] 100%|██████████| 32/32 [00:24<00:00, 1.33it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s Uploading outputs... Finished.