tungsten-logo
Sign In
Dragonlady with lah-mysterious-sdxl
lah-mysterious-sdxl:v4.0
sparks
sparks
·
Jan 21
353
Input
prompt
Specify things to see in the output
masterpiece, best quality ultra-realistic mix fantasy,(1 giant eastern dragon:1.3) behind an asian woman holding a glowing sword,void energy diamond sword, in the style of dark azure and light azure, mixes realistic and fantastical elements, vibrant manga, uhd image, glassy translucence, vibrant illustrations, ultra realistic, long hair, straight hair, light purple hair,head jewelly, jewelly, shawls,light In eyes, red eyes, portrait, firefly, bokeh, mysterious, fantasy, cloud, abstract, colorful background, night sky, flame, very detailed, high resolution, sharp, sharp image, 4k, 8k, masterpiece, best quality, magic effect, (high contrast:1.4), dream art, diamond, skin detail, face detail, eyes detail, mysterious colorful background, dark blue themes
negative_prompt
Specify things to not see in the output
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.
num_outputs
Number of output images
3
width
Output image width
896
height
Output image height
1152
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
0.35
detail
Enhance/diminish detail while keeping the overall style/character
1.5
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.
637001597
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
38
cfg_scale
Scale for classifier-free guidance
6
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/7fa0da2dbdc24d2c947b5a232d52c758/00000-637001597.webp
https://files.tungsten.run/uploads/278ff8a875244bd5bac647d69d3c042e/00001-637001598.webp
https://files.tungsten.run/uploads/4936689feaa942dca953f576e54b80a4/00002-637001599.webp
Finished in 156.6 seconds
Preparing model sparks/lah-mysterious-sdxl:v4.0... v4.0: Pulling from sparks/lah-mysterious-sdxl 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 a62ba808f5e5: Pull complete 8915fc22d7d8: Pull complete 4f7e8419430f: Pull complete 4f4fb700ef54: Pull complete 69c516b0f065: Pull complete 05e851480b1d: Pull complete f61a22f2c3fd: Pull complete db84c34f5c0d: Pull complete Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: masterpiece, best quality ultra-realistic mix fantasy,(1 giant eastern dragon:1.3) behind an asian woman holding a glowing sword,void energy diamond sword, in the style of dark azure and light azure, mixes realistic and fantastical elements, vibrant manga, uhd image, glassy translucence, vibrant illustrations, ultra realistic, long hair, straight hair, light purple hair,head jewelly, jewelly, shawls,light In eyes, red eyes, portrait, firefly, bokeh, mysterious, fantasy, cloud, abstract, colorful background, night sky, flame, very detailed, high resolution, sharp, sharp image, 4k, 8k, masterpiece, best quality, magic effect, (high contrast:1.4), dream art, diamond, skin detail, face detail, eyes detail, mysterious colorful background, dark blue themes, <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%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:03<02:08, 3.48s/it] 5%|▌ | 2/38 [00:05<01:38, 2.73s/it] 8%|▊ | 3/38 [00:08<01:30, 2.58s/it] 11%|█ | 4/38 [00:10<01:27, 2.59s/it] 13%|█▎ | 5/38 [00:13<01:24, 2.57s/it] 16%|█▌ | 6/38 [00:15<01:24, 2.63s/it] 18%|█▊ | 7/38 [00:18<01:21, 2.62s/it] 21%|██ | 8/38 [00:21<01:19, 2.63s/it] 24%|██▎ | 9/38 [00:23<01:15, 2.61s/it] 26%|██▋ | 10/38 [00:26<01:13, 2.61s/it] 29%|██▉ | 11/38 [00:28<01:08, 2.52s/it] 32%|███▏ | 12/38 [00:31<01:05, 2.50s/it] 34%|███▍ | 13/38 [00:33<01:04, 2.58s/it] 37%|███▋ | 14/38 [00:36<01:02, 2.60s/it] 39%|███▉ | 15/38 [00:39<01:04, 2.79s/it] 42%|████▏ | 16/38 [00:42<01:02, 2.83s/it] 45%|████▍ | 17/38 [00:45<00:59, 2.82s/it] 47%|████▋ | 18/38 [00:47<00:53, 2.68s/it] 50%|█████ | 19/38 [00:50<00:48, 2.53s/it] 53%|█████▎ | 20/38 [00:52<00:45, 2.52s/it] 55%|█████▌ | 21/38 [00:55<00:43, 2.54s/it] 58%|█████▊ | 22/38 [00:57<00:40, 2.56s/it] 61%|██████ | 23/38 [01:00<00:38, 2.57s/it] 63%|██████▎ | 24/38 [01:02<00:35, 2.51s/it] 66%|██████▌ | 25/38 [01:05<00:33, 2.55s/it] 68%|██████▊ | 26/38 [01:07<00:30, 2.52s/it] 71%|███████ | 27/38 [01:10<00:27, 2.47s/it] 74%|███████▎ | 28/38 [01:12<00:25, 2.52s/it] 76%|███████▋ | 29/38 [01:15<00:22, 2.47s/it] 79%|███████▉ | 30/38 [01:17<00:19, 2.40s/it] 82%|████████▏ | 31/38 [01:19<00:16, 2.40s/it] 84%|████████▍ | 32/38 [01:22<00:14, 2.37s/it] 87%|████████▋ | 33/38 [01:24<00:11, 2.38s/it] 89%|████████▉ | 34/38 [01:26<00:09, 2.30s/it] 92%|█████████▏| 35/38 [01:28<00:06, 2.31s/it] 95%|█████████▍| 36/38 [01:31<00:04, 2.24s/it] 97%|█████████▋| 37/38 [01:32<00:02, 2.01s/it] 100%|██████████| 38/38 [01:33<00:00, 1.77s/it] 100%|██████████| 38/38 [01:33<00:00, 2.47s/it] Decoding latents in cuda:0... done in 2.33s Move latents to cpu... done in 0.03s 0: 640x512 1 face, 155.4ms Speed: 2.7ms preprocess, 155.4ms inference, 14.3ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:15, 1.21s/it] 14%|█▍ | 2/14 [00:02<00:13, 1.09s/it] 21%|██▏ | 3/14 [00:03<00:11, 1.05s/it] 29%|██▊ | 4/14 [00:04<00:10, 1.06s/it] 36%|███▌ | 5/14 [00:05<00:09, 1.03s/it] 43%|████▎ | 6/14 [00:06<00:07, 1.00it/s] 50%|█████ | 7/14 [00:07<00:06, 1.00it/s] 57%|█████▋ | 8/14 [00:08<00:05, 1.01it/s] 64%|██████▍ | 9/14 [00:09<00:04, 1.01it/s] 71%|███████▏ | 10/14 [00:10<00:03, 1.03it/s] 79%|███████▊ | 11/14 [00:11<00:02, 1.01it/s] 86%|████████▌ | 12/14 [00:12<00:01, 1.04it/s] 93%|█████████▎| 13/14 [00:12<00:00, 1.14it/s] 100%|██████████| 14/14 [00:13<00:00, 1.26it/s] 100%|██████████| 14/14 [00:13<00:00, 1.05it/s] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x512 (no detections), 98.7ms Speed: 2.6ms preprocess, 98.7ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 512) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x512 1 face, 8.2ms Speed: 2.6ms preprocess, 8.2ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:14, 1.09s/it] 14%|█▍ | 2/14 [00:02<00:12, 1.05s/it] 21%|██▏ | 3/14 [00:03<00:11, 1.02s/it] 29%|██▊ | 4/14 [00:04<00:10, 1.05s/it] 36%|███▌ | 5/14 [00:05<00:09, 1.03s/it] 43%|████▎ | 6/14 [00:06<00:08, 1.00s/it] 50%|█████ | 7/14 [00:07<00:07, 1.00s/it] 57%|█████▋ | 8/14 [00:08<00:05, 1.00it/s] 64%|██████▍ | 9/14 [00:09<00:04, 1.01it/s] 71%|███████▏ | 10/14 [00:09<00:03, 1.04it/s] 79%|███████▊ | 11/14 [00:10<00:02, 1.04it/s] 86%|████████▌ | 12/14 [00:11<00:01, 1.06it/s] 93%|█████████▎| 13/14 [00:12<00:00, 1.16it/s] 100%|██████████| 14/14 [00:13<00:00, 1.27it/s] 100%|██████████| 14/14 [00:13<00:00, 1.06it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x512 (no detections), 7.6ms Speed: 2.5ms preprocess, 7.6ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 512) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x512 1 face, 7.8ms Speed: 2.5ms preprocess, 7.8ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:14, 1.09s/it] 14%|█▍ | 2/14 [00:02<00:12, 1.05s/it] 21%|██▏ | 3/14 [00:03<00:11, 1.03s/it] 29%|██▊ | 4/14 [00:04<00:10, 1.05s/it] 36%|███▌ | 5/14 [00:05<00:09, 1.02s/it] 43%|████▎ | 6/14 [00:06<00:08, 1.01s/it] 50%|█████ | 7/14 [00:07<00:07, 1.03s/it] 57%|█████▋ | 8/14 [00:08<00:06, 1.01s/it] 64%|██████▍ | 9/14 [00:09<00:05, 1.01s/it] 71%|███████▏ | 10/14 [00:10<00:03, 1.02it/s] 79%|███████▊ | 11/14 [00:11<00:02, 1.02it/s] 86%|████████▌ | 12/14 [00:12<00:01, 1.05it/s] 93%|█████████▎| 13/14 [00:12<00:00, 1.14it/s] 100%|██████████| 14/14 [00:13<00:00, 1.26it/s] 100%|██████████| 14/14 [00:13<00:00, 1.05it/s] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x512 (no detections), 7.8ms Speed: 2.8ms preprocess, 7.8ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 512) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.
prompt
Specify things to see in the output
masterpiece, best quality ultra-realistic mix fantasy,(1 giant eastern dragon:1.3) behind an asian woman holding a glowing sword,void energy diamond sword, in the style of dark azure and light azure, mixes realistic and fantastical elements, vibrant manga, uhd image, glassy translucence, vibrant illustrations, ultra realistic, long hair, straight hair, light purple hair,head jewelly, jewelly, shawls,light In eyes, red eyes, portrait, firefly, bokeh, mysterious, fantasy, cloud, abstract, colorful background, night sky, flame, very detailed, high resolution, sharp, sharp image, 4k, 8k, masterpiece, best quality, magic effect, (high contrast:1.4), dream art, diamond, skin detail, face detail, eyes detail, mysterious colorful background, dark blue themes
negative_prompt
Specify things to not see in the output
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.
num_outputs
Number of output images
3
width
Output image width
896
height
Output image height
1152
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
0.35
detail
Enhance/diminish detail while keeping the overall style/character
1.5
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.
637001597
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
38
cfg_scale
Scale for classifier-free guidance
6
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/7fa0da2dbdc24d2c947b5a232d52c758/00000-637001597.webp
https://files.tungsten.run/uploads/278ff8a875244bd5bac647d69d3c042e/00001-637001598.webp
https://files.tungsten.run/uploads/4936689feaa942dca953f576e54b80a4/00002-637001599.webp
Finished in 156.6 seconds
Preparing model sparks/lah-mysterious-sdxl:v4.0... v4.0: Pulling from sparks/lah-mysterious-sdxl 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 a62ba808f5e5: Pull complete 8915fc22d7d8: Pull complete 4f7e8419430f: Pull complete 4f4fb700ef54: Pull complete 69c516b0f065: Pull complete 05e851480b1d: Pull complete f61a22f2c3fd: Pull complete db84c34f5c0d: Pull complete Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: masterpiece, best quality ultra-realistic mix fantasy,(1 giant eastern dragon:1.3) behind an asian woman holding a glowing sword,void energy diamond sword, in the style of dark azure and light azure, mixes realistic and fantastical elements, vibrant manga, uhd image, glassy translucence, vibrant illustrations, ultra realistic, long hair, straight hair, light purple hair,head jewelly, jewelly, shawls,light In eyes, red eyes, portrait, firefly, bokeh, mysterious, fantasy, cloud, abstract, colorful background, night sky, flame, very detailed, high resolution, sharp, sharp image, 4k, 8k, masterpiece, best quality, magic effect, (high contrast:1.4), dream art, diamond, skin detail, face detail, eyes detail, mysterious colorful background, dark blue themes, <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%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:03<02:08, 3.48s/it] 5%|▌ | 2/38 [00:05<01:38, 2.73s/it] 8%|▊ | 3/38 [00:08<01:30, 2.58s/it] 11%|█ | 4/38 [00:10<01:27, 2.59s/it] 13%|█▎ | 5/38 [00:13<01:24, 2.57s/it] 16%|█▌ | 6/38 [00:15<01:24, 2.63s/it] 18%|█▊ | 7/38 [00:18<01:21, 2.62s/it] 21%|██ | 8/38 [00:21<01:19, 2.63s/it] 24%|██▎ | 9/38 [00:23<01:15, 2.61s/it] 26%|██▋ | 10/38 [00:26<01:13, 2.61s/it] 29%|██▉ | 11/38 [00:28<01:08, 2.52s/it] 32%|███▏ | 12/38 [00:31<01:05, 2.50s/it] 34%|███▍ | 13/38 [00:33<01:04, 2.58s/it] 37%|███▋ | 14/38 [00:36<01:02, 2.60s/it] 39%|███▉ | 15/38 [00:39<01:04, 2.79s/it] 42%|████▏ | 16/38 [00:42<01:02, 2.83s/it] 45%|████▍ | 17/38 [00:45<00:59, 2.82s/it] 47%|████▋ | 18/38 [00:47<00:53, 2.68s/it] 50%|█████ | 19/38 [00:50<00:48, 2.53s/it] 53%|█████▎ | 20/38 [00:52<00:45, 2.52s/it] 55%|█████▌ | 21/38 [00:55<00:43, 2.54s/it] 58%|█████▊ | 22/38 [00:57<00:40, 2.56s/it] 61%|██████ | 23/38 [01:00<00:38, 2.57s/it] 63%|██████▎ | 24/38 [01:02<00:35, 2.51s/it] 66%|██████▌ | 25/38 [01:05<00:33, 2.55s/it] 68%|██████▊ | 26/38 [01:07<00:30, 2.52s/it] 71%|███████ | 27/38 [01:10<00:27, 2.47s/it] 74%|███████▎ | 28/38 [01:12<00:25, 2.52s/it] 76%|███████▋ | 29/38 [01:15<00:22, 2.47s/it] 79%|███████▉ | 30/38 [01:17<00:19, 2.40s/it] 82%|████████▏ | 31/38 [01:19<00:16, 2.40s/it] 84%|████████▍ | 32/38 [01:22<00:14, 2.37s/it] 87%|████████▋ | 33/38 [01:24<00:11, 2.38s/it] 89%|████████▉ | 34/38 [01:26<00:09, 2.30s/it] 92%|█████████▏| 35/38 [01:28<00:06, 2.31s/it] 95%|█████████▍| 36/38 [01:31<00:04, 2.24s/it] 97%|█████████▋| 37/38 [01:32<00:02, 2.01s/it] 100%|██████████| 38/38 [01:33<00:00, 1.77s/it] 100%|██████████| 38/38 [01:33<00:00, 2.47s/it] Decoding latents in cuda:0... done in 2.33s Move latents to cpu... done in 0.03s 0: 640x512 1 face, 155.4ms Speed: 2.7ms preprocess, 155.4ms inference, 14.3ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:15, 1.21s/it] 14%|█▍ | 2/14 [00:02<00:13, 1.09s/it] 21%|██▏ | 3/14 [00:03<00:11, 1.05s/it] 29%|██▊ | 4/14 [00:04<00:10, 1.06s/it] 36%|███▌ | 5/14 [00:05<00:09, 1.03s/it] 43%|████▎ | 6/14 [00:06<00:07, 1.00it/s] 50%|█████ | 7/14 [00:07<00:06, 1.00it/s] 57%|█████▋ | 8/14 [00:08<00:05, 1.01it/s] 64%|██████▍ | 9/14 [00:09<00:04, 1.01it/s] 71%|███████▏ | 10/14 [00:10<00:03, 1.03it/s] 79%|███████▊ | 11/14 [00:11<00:02, 1.01it/s] 86%|████████▌ | 12/14 [00:12<00:01, 1.04it/s] 93%|█████████▎| 13/14 [00:12<00:00, 1.14it/s] 100%|██████████| 14/14 [00:13<00:00, 1.26it/s] 100%|██████████| 14/14 [00:13<00:00, 1.05it/s] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x512 (no detections), 98.7ms Speed: 2.6ms preprocess, 98.7ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 512) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x512 1 face, 8.2ms Speed: 2.6ms preprocess, 8.2ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:14, 1.09s/it] 14%|█▍ | 2/14 [00:02<00:12, 1.05s/it] 21%|██▏ | 3/14 [00:03<00:11, 1.02s/it] 29%|██▊ | 4/14 [00:04<00:10, 1.05s/it] 36%|███▌ | 5/14 [00:05<00:09, 1.03s/it] 43%|████▎ | 6/14 [00:06<00:08, 1.00s/it] 50%|█████ | 7/14 [00:07<00:07, 1.00s/it] 57%|█████▋ | 8/14 [00:08<00:05, 1.00it/s] 64%|██████▍ | 9/14 [00:09<00:04, 1.01it/s] 71%|███████▏ | 10/14 [00:09<00:03, 1.04it/s] 79%|███████▊ | 11/14 [00:10<00:02, 1.04it/s] 86%|████████▌ | 12/14 [00:11<00:01, 1.06it/s] 93%|█████████▎| 13/14 [00:12<00:00, 1.16it/s] 100%|██████████| 14/14 [00:13<00:00, 1.27it/s] 100%|██████████| 14/14 [00:13<00:00, 1.06it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x512 (no detections), 7.6ms Speed: 2.5ms preprocess, 7.6ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 512) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x512 1 face, 7.8ms Speed: 2.5ms preprocess, 7.8ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 512) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:01<00:14, 1.09s/it] 14%|█▍ | 2/14 [00:02<00:12, 1.05s/it] 21%|██▏ | 3/14 [00:03<00:11, 1.03s/it] 29%|██▊ | 4/14 [00:04<00:10, 1.05s/it] 36%|███▌ | 5/14 [00:05<00:09, 1.02s/it] 43%|████▎ | 6/14 [00:06<00:08, 1.01s/it] 50%|█████ | 7/14 [00:07<00:07, 1.03s/it] 57%|█████▋ | 8/14 [00:08<00:06, 1.01s/it] 64%|██████▍ | 9/14 [00:09<00:05, 1.01s/it] 71%|███████▏ | 10/14 [00:10<00:03, 1.02it/s] 79%|███████▊ | 11/14 [00:11<00:02, 1.02it/s] 86%|████████▌ | 12/14 [00:12<00:01, 1.05it/s] 93%|█████████▎| 13/14 [00:12<00:00, 1.14it/s] 100%|██████████| 14/14 [00:13<00:00, 1.26it/s] 100%|██████████| 14/14 [00:13<00:00, 1.05it/s] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x512 (no detections), 7.8ms Speed: 2.8ms preprocess, 7.8ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 512) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.