animerge
animerge
17 stars
Version: v25
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
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
saturation
Adjust saturation
num_outputs
Number of output images
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
width
Output image width
height
Output image height
reference_image
Image that the output should be similar to
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/11d4d83dcd004161bfa1757a7d9b327d/00000-1756907654.png
https://files.tungsten.run/uploads/fd5cb9c2635e4f0f8fe9a8242da4eceb/00001-1756907655.png
https://files.tungsten.run/uploads/8be741267c3b49ed9436634d7c889a2f/00002-1756907656.png
https://files.tungsten.run/uploads/22fa9feb14244fb2b1203b0aadf685c2/00003-1756907657.png
This example was created by evevalentine2017
Finished in 69.9 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (best quality, masterpiece, colorful, dynamic angle, highest detailed)upper body photo, full body photo, fashion photography of cute mechangel, glowing 4 wings, solo, glowing armor, glowing halo, building, glowing mechanical 4 wings (intricate details, hyperdetailed:1.15), detailed, light passing through hair, (official art, extreme detailed, highest detailed), HDR+, <lora:FaceBeauty_qinglong_V3:1>, (ultra detailed:1.5), (masterpiece:1.5), (ultra realistic:1.5) Full negative prompt: bad-hands-5, By bad artist -neg 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:58, 1.20s/it] 4%|▍ | 2/50 [00:01<00:41, 1.16it/s] 6%|▌ | 3/50 [00:02<00:35, 1.34it/s] 8%|▊ | 4/50 [00:03<00:32, 1.43it/s] 10%|█ | 5/50 [00:03<00:30, 1.49it/s] 12%|█▏ | 6/50 [00:04<00:28, 1.53it/s] 14%|█▍ | 7/50 [00:04<00:27, 1.56it/s] 16%|█▌ | 8/50 [00:05<00:26, 1.58it/s] 18%|█▊ | 9/50 [00:06<00:25, 1.59it/s] 20%|██ | 10/50 [00:06<00:25, 1.59it/s] 22%|██▏ | 11/50 [00:07<00:24, 1.60it/s] 24%|██▍ | 12/50 [00:08<00:23, 1.60it/s] 26%|██▌ | 13/50 [00:08<00:23, 1.61it/s] 28%|██▊ | 14/50 [00:09<00:22, 1.61it/s] 30%|███ | 15/50 [00:09<00:21, 1.61it/s] 32%|███▏ | 16/50 [00:10<00:21, 1.60it/s] 34%|███▍ | 17/50 [00:11<00:20, 1.61it/s] 36%|███▌ | 18/50 [00:11<00:19, 1.61it/s] 38%|███▊ | 19/50 [00:12<00:19, 1.61it/s] 40%|████ | 20/50 [00:12<00:18, 1.61it/s] 42%|████▏ | 21/50 [00:13<00:17, 1.61it/s] 44%|████▍ | 22/50 [00:14<00:17, 1.61it/s] 46%|████▌ | 23/50 [00:14<00:16, 1.61it/s] 48%|████▊ | 24/50 [00:15<00:16, 1.61it/s] 50%|█████ | 25/50 [00:16<00:15, 1.61it/s] 52%|█████▏ | 26/50 [00:16<00:14, 1.61it/s] 54%|█████▍ | 27/50 [00:17<00:14, 1.61it/s] 56%|█████▌ | 28/50 [00:17<00:13, 1.60it/s] 58%|█████▊ | 29/50 [00:18<00:13, 1.60it/s] 60%|██████ | 30/50 [00:19<00:12, 1.61it/s] 62%|██████▏ | 31/50 [00:19<00:11, 1.60it/s] 64%|██████▍ | 32/50 [00:20<00:11, 1.60it/s] 66%|██████▌ | 33/50 [00:21<00:10, 1.60it/s] 68%|██████▊ | 34/50 [00:21<00:09, 1.60it/s] 70%|███████ | 35/50 [00:22<00:09, 1.60it/s] 72%|███████▏ | 36/50 [00:22<00:08, 1.60it/s] 74%|███████▍ | 37/50 [00:23<00:08, 1.60it/s] 76%|███████▌ | 38/50 [00:24<00:07, 1.60it/s] 78%|███████▊ | 39/50 [00:24<00:06, 1.60it/s] 80%|████████ | 40/50 [00:25<00:06, 1.60it/s] 82%|████████▏ | 41/50 [00:26<00:05, 1.60it/s] 84%|████████▍ | 42/50 [00:26<00:05, 1.60it/s] 86%|████████▌ | 43/50 [00:27<00:04, 1.60it/s] 88%|████████▊ | 44/50 [00:27<00:03, 1.60it/s] 90%|█████████ | 45/50 [00:28<00:03, 1.60it/s] 92%|█████████▏| 46/50 [00:29<00:02, 1.60it/s] 94%|█████████▍| 47/50 [00:29<00:01, 1.59it/s] 96%|█████████▌| 48/50 [00:30<00:01, 1.59it/s] 98%|█████████▊| 49/50 [00:31<00:00, 1.59it/s] 100%|██████████| 50/50 [00:31<00:00, 1.59it/s] 100%|██████████| 50/50 [00:31<00:00, 1.57it/s] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.7ms preprocess, 7.8ms inference, 34.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:10, 2.56it/s] 7%|▋ | 2/28 [00:00<00:07, 3.57it/s] 11%|█ | 3/28 [00:00<00:06, 4.14it/s] 14%|█▍ | 4/28 [00:01<00:05, 4.34it/s] 18%|█▊ | 5/28 [00:01<00:05, 4.54it/s] 21%|██▏ | 6/28 [00:01<00:04, 4.73it/s] 25%|██▌ | 7/28 [00:01<00:04, 4.85it/s] 29%|██▊ | 8/28 [00:01<00:04, 4.94it/s] 32%|███▏ | 9/28 [00:01<00:03, 4.94it/s] 36%|███▌ | 10/28 [00:02<00:03, 4.99it/s] 39%|███▉ | 11/28 [00:02<00:03, 5.02it/s] 43%|████▎ | 12/28 [00:02<00:03, 5.03it/s] 46%|████▋ | 13/28 [00:02<00:02, 5.07it/s] 50%|█████ | 14/28 [00:02<00:02, 4.98it/s] 54%|█████▎ | 15/28 [00:03<00:02, 5.01it/s] 57%|█████▋ | 16/28 [00:03<00:02, 5.01it/s] 61%|██████ | 17/28 [00:03<00:02, 5.02it/s] 64%|██████▍ | 18/28 [00:03<00:02, 4.94it/s] 68%|██████▊ | 19/28 [00:04<00:01, 4.81it/s] 71%|███████▏ | 20/28 [00:04<00:01, 4.89it/s] 75%|███████▌ | 21/28 [00:04<00:01, 4.94it/s] 79%|███████▊ | 22/28 [00:04<00:01, 4.98it/s] 82%|████████▏ | 23/28 [00:04<00:01, 4.92it/s] 86%|████████▌ | 24/28 [00:05<00:00, 4.85it/s] 89%|████████▉ | 25/28 [00:05<00:00, 4.89it/s] 93%|█████████▎| 26/28 [00:05<00:00, 4.88it/s] 96%|█████████▋| 27/28 [00:05<00:00, 4.93it/s] 100%|██████████| 28/28 [00:05<00:00, 4.93it/s] 100%|██████████| 28/28 [00:05<00:00, 4.80it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.1ms Speed: 3.2ms preprocess, 7.1ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.5ms Speed: 2.8ms preprocess, 7.5ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:05, 5.11it/s] 7%|▋ | 2/28 [00:00<00:05, 5.12it/s] 11%|█ | 3/28 [00:00<00:04, 5.09it/s] 14%|█▍ | 4/28 [00:00<00:04, 5.11it/s] 18%|█▊ | 5/28 [00:00<00:04, 4.97it/s] 21%|██▏ | 6/28 [00:01<00:04, 5.01it/s] 25%|██▌ | 7/28 [00:01<00:04, 5.00it/s] 29%|██▊ | 8/28 [00:01<00:03, 5.05it/s] 32%|███▏ | 9/28 [00:01<00:03, 5.07it/s] 36%|███▌ | 10/28 [00:01<00:03, 4.97it/s] 39%|███▉ | 11/28 [00:02<00:03, 5.02it/s] 43%|████▎ | 12/28 [00:02<00:03, 5.05it/s] 46%|████▋ | 13/28 [00:02<00:02, 5.07it/s] 50%|█████ | 14/28 [00:02<00:02, 4.91it/s] 54%|█████▎ | 15/28 [00:03<00:02, 4.76it/s] 57%|█████▋ | 16/28 [00:03<00:02, 4.84it/s] 61%|██████ | 17/28 [00:03<00:02, 4.90it/s] 64%|██████▍ | 18/28 [00:03<00:02, 4.96it/s] 68%|██████▊ | 19/28 [00:03<00:01, 4.99it/s] 71%|███████▏ | 20/28 [00:04<00:01, 4.83it/s] 75%|███████▌ | 21/28 [00:04<00:01, 4.90it/s] 79%|███████▊ | 22/28 [00:04<00:01, 4.96it/s] 82%|████████▏ | 23/28 [00:04<00:00, 5.00it/s] 86%|████████▌ | 24/28 [00:04<00:00, 5.03it/s] 89%|████████▉ | 25/28 [00:05<00:00, 4.89it/s] 93%|█████████▎| 26/28 [00:05<00:00, 4.95it/s] 96%|█████████▋| 27/28 [00:05<00:00, 4.99it/s] 100%|██████████| 28/28 [00:05<00:00, 5.01it/s] 100%|██████████| 28/28 [00:05<00:00, 4.98it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.2ms Speed: 2.7ms preprocess, 7.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:05, 5.07it/s] 7%|▋ | 2/28 [00:00<00:05, 4.89it/s] 11%|█ | 3/28 [00:00<00:05, 4.98it/s] 14%|█▍ | 4/28 [00:00<00:04, 5.03it/s] 18%|█▊ | 5/28 [00:00<00:04, 5.05it/s] 21%|██▏ | 6/28 [00:01<00:04, 5.08it/s] 25%|██▌ | 7/28 [00:01<00:04, 5.01it/s] 29%|██▊ | 8/28 [00:01<00:04, 5.00it/s] 32%|███▏ | 9/28 [00:01<00:03, 5.03it/s] 36%|███▌ | 10/28 [00:01<00:03, 5.05it/s] 39%|███▉ | 11/28 [00:02<00:03, 5.05it/s] 43%|████▎ | 12/28 [00:02<00:03, 5.06it/s] 46%|████▋ | 13/28 [00:02<00:02, 5.05it/s] 50%|█████ | 14/28 [00:02<00:02, 5.05it/s] 54%|█████▎ | 15/28 [00:02<00:02, 5.04it/s] 57%|█████▋ | 16/28 [00:03<00:02, 5.04it/s] 61%|██████ | 17/28 [00:03<00:02, 5.04it/s] 64%|██████▍ | 18/28 [00:03<00:01, 5.05it/s] 68%|██████▊ | 19/28 [00:03<00:01, 5.05it/s] 71%|███████▏ | 20/28 [00:03<00:01, 5.07it/s] 75%|███████▌ | 21/28 [00:04<00:01, 5.06it/s] 79%|███████▊ | 22/28 [00:04<00:01, 5.07it/s] 82%|████████▏ | 23/28 [00:04<00:00, 5.01it/s] 86%|████████▌ | 24/28 [00:04<00:00, 5.00it/s] 89%|████████▉ | 25/28 [00:04<00:00, 5.01it/s] 93%|█████████▎| 26/28 [00:05<00:00, 5.01it/s] 96%|█████████▋| 27/28 [00:05<00:00, 4.99it/s] 100%|██████████| 28/28 [00:05<00:00, 4.97it/s] 100%|██████████| 28/28 [00:05<00:00, 5.02it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 2.9ms preprocess, 7.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. 0: 640x640 1 face, 7.6ms Speed: 2.8ms preprocess, 7.6ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:05, 5.14it/s] 7%|▋ | 2/28 [00:00<00:05, 5.06it/s] 11%|█ | 3/28 [00:00<00:04, 5.09it/s] 14%|█▍ | 4/28 [00:00<00:04, 4.97it/s] 18%|█▊ | 5/28 [00:00<00:04, 5.01it/s] 21%|██▏ | 6/28 [00:01<00:04, 5.05it/s] 25%|██▌ | 7/28 [00:01<00:04, 5.07it/s] 29%|██▊ | 8/28 [00:01<00:03, 5.07it/s] 32%|███▏ | 9/28 [00:01<00:03, 5.00it/s] 36%|███▌ | 10/28 [00:01<00:03, 5.02it/s] 39%|███▉ | 11/28 [00:02<00:03, 5.04it/s] 43%|████▎ | 12/28 [00:02<00:03, 5.05it/s] 46%|████▋ | 13/28 [00:02<00:02, 5.05it/s] 50%|█████ | 14/28 [00:02<00:02, 5.05it/s] 54%|█████▎ | 15/28 [00:02<00:02, 5.06it/s] 57%|█████▋ | 16/28 [00:03<00:02, 5.05it/s] 61%|██████ | 17/28 [00:03<00:02, 5.07it/s] 64%|██████▍ | 18/28 [00:03<00:01, 5.07it/s] 68%|██████▊ | 19/28 [00:03<00:01, 5.04it/s] 71%|███████▏ | 20/28 [00:03<00:01, 5.04it/s] 75%|███████▌ | 21/28 [00:04<00:01, 5.07it/s] 79%|███████▊ | 22/28 [00:04<00:01, 5.08it/s] 82%|████████▏ | 23/28 [00:04<00:00, 5.09it/s] 86%|████████▌ | 24/28 [00:04<00:00, 5.06it/s] 89%|████████▉ | 25/28 [00:04<00:00, 5.02it/s] 93%|█████████▎| 26/28 [00:05<00:00, 5.01it/s] 96%|█████████▋| 27/28 [00:05<00:00, 5.00it/s] 100%|██████████| 28/28 [00:05<00:00, 5.01it/s] 100%|██████████| 28/28 [00:05<00:00, 5.04it/s] Decoding latents in cuda:0... =========================================== A tensor with all NaNs was produced in VAE. Converted VAE into 32-bit float and retry. =========================================== done in 0.45s Move latents to cpu... done in 0.22s 0: 640x640 (no detections), 9.8ms Speed: 2.8ms preprocess, 9.8ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 4 with 2nd settings. Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
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
saturation
Adjust saturation
num_outputs
Number of output images
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
width
Output image width
height
Output image height
reference_image
Image that the output should be similar to
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/11d4d83dcd004161bfa1757a7d9b327d/00000-1756907654.png
https://files.tungsten.run/uploads/fd5cb9c2635e4f0f8fe9a8242da4eceb/00001-1756907655.png
https://files.tungsten.run/uploads/8be741267c3b49ed9436634d7c889a2f/00002-1756907656.png
https://files.tungsten.run/uploads/22fa9feb14244fb2b1203b0aadf685c2/00003-1756907657.png
This example was created by evevalentine2017
Finished in 69.9 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (best quality, masterpiece, colorful, dynamic angle, highest detailed)upper body photo, full body photo, fashion photography of cute mechangel, glowing 4 wings, solo, glowing armor, glowing halo, building, glowing mechanical 4 wings (intricate details, hyperdetailed:1.15), detailed, light passing through hair, (official art, extreme detailed, highest detailed), HDR+, <lora:FaceBeauty_qinglong_V3:1>, (ultra detailed:1.5), (masterpiece:1.5), (ultra realistic:1.5) Full negative prompt: bad-hands-5, By bad artist -neg 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:58, 1.20s/it] 4%|▍ | 2/50 [00:01<00:41, 1.16it/s] 6%|▌ | 3/50 [00:02<00:35, 1.34it/s] 8%|▊ | 4/50 [00:03<00:32, 1.43it/s] 10%|█ | 5/50 [00:03<00:30, 1.49it/s] 12%|█▏ | 6/50 [00:04<00:28, 1.53it/s] 14%|█▍ | 7/50 [00:04<00:27, 1.56it/s] 16%|█▌ | 8/50 [00:05<00:26, 1.58it/s] 18%|█▊ | 9/50 [00:06<00:25, 1.59it/s] 20%|██ | 10/50 [00:06<00:25, 1.59it/s] 22%|██▏ | 11/50 [00:07<00:24, 1.60it/s] 24%|██▍ | 12/50 [00:08<00:23, 1.60it/s] 26%|██▌ | 13/50 [00:08<00:23, 1.61it/s] 28%|██▊ | 14/50 [00:09<00:22, 1.61it/s] 30%|███ | 15/50 [00:09<00:21, 1.61it/s] 32%|███▏ | 16/50 [00:10<00:21, 1.60it/s] 34%|███▍ | 17/50 [00:11<00:20, 1.61it/s] 36%|███▌ | 18/50 [00:11<00:19, 1.61it/s] 38%|███▊ | 19/50 [00:12<00:19, 1.61it/s] 40%|████ | 20/50 [00:12<00:18, 1.61it/s] 42%|████▏ | 21/50 [00:13<00:17, 1.61it/s] 44%|████▍ | 22/50 [00:14<00:17, 1.61it/s] 46%|████▌ | 23/50 [00:14<00:16, 1.61it/s] 48%|████▊ | 24/50 [00:15<00:16, 1.61it/s] 50%|█████ | 25/50 [00:16<00:15, 1.61it/s] 52%|█████▏ | 26/50 [00:16<00:14, 1.61it/s] 54%|█████▍ | 27/50 [00:17<00:14, 1.61it/s] 56%|█████▌ | 28/50 [00:17<00:13, 1.60it/s] 58%|█████▊ | 29/50 [00:18<00:13, 1.60it/s] 60%|██████ | 30/50 [00:19<00:12, 1.61it/s] 62%|██████▏ | 31/50 [00:19<00:11, 1.60it/s] 64%|██████▍ | 32/50 [00:20<00:11, 1.60it/s] 66%|██████▌ | 33/50 [00:21<00:10, 1.60it/s] 68%|██████▊ | 34/50 [00:21<00:09, 1.60it/s] 70%|███████ | 35/50 [00:22<00:09, 1.60it/s] 72%|███████▏ | 36/50 [00:22<00:08, 1.60it/s] 74%|███████▍ | 37/50 [00:23<00:08, 1.60it/s] 76%|███████▌ | 38/50 [00:24<00:07, 1.60it/s] 78%|███████▊ | 39/50 [00:24<00:06, 1.60it/s] 80%|████████ | 40/50 [00:25<00:06, 1.60it/s] 82%|████████▏ | 41/50 [00:26<00:05, 1.60it/s] 84%|████████▍ | 42/50 [00:26<00:05, 1.60it/s] 86%|████████▌ | 43/50 [00:27<00:04, 1.60it/s] 88%|████████▊ | 44/50 [00:27<00:03, 1.60it/s] 90%|█████████ | 45/50 [00:28<00:03, 1.60it/s] 92%|█████████▏| 46/50 [00:29<00:02, 1.60it/s] 94%|█████████▍| 47/50 [00:29<00:01, 1.59it/s] 96%|█████████▌| 48/50 [00:30<00:01, 1.59it/s] 98%|█████████▊| 49/50 [00:31<00:00, 1.59it/s] 100%|██████████| 50/50 [00:31<00:00, 1.59it/s] 100%|██████████| 50/50 [00:31<00:00, 1.57it/s] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.7ms preprocess, 7.8ms inference, 34.2ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:10, 2.56it/s] 7%|▋ | 2/28 [00:00<00:07, 3.57it/s] 11%|█ | 3/28 [00:00<00:06, 4.14it/s] 14%|█▍ | 4/28 [00:01<00:05, 4.34it/s] 18%|█▊ | 5/28 [00:01<00:05, 4.54it/s] 21%|██▏ | 6/28 [00:01<00:04, 4.73it/s] 25%|██▌ | 7/28 [00:01<00:04, 4.85it/s] 29%|██▊ | 8/28 [00:01<00:04, 4.94it/s] 32%|███▏ | 9/28 [00:01<00:03, 4.94it/s] 36%|███▌ | 10/28 [00:02<00:03, 4.99it/s] 39%|███▉ | 11/28 [00:02<00:03, 5.02it/s] 43%|████▎ | 12/28 [00:02<00:03, 5.03it/s] 46%|████▋ | 13/28 [00:02<00:02, 5.07it/s] 50%|█████ | 14/28 [00:02<00:02, 4.98it/s] 54%|█████▎ | 15/28 [00:03<00:02, 5.01it/s] 57%|█████▋ | 16/28 [00:03<00:02, 5.01it/s] 61%|██████ | 17/28 [00:03<00:02, 5.02it/s] 64%|██████▍ | 18/28 [00:03<00:02, 4.94it/s] 68%|██████▊ | 19/28 [00:04<00:01, 4.81it/s] 71%|███████▏ | 20/28 [00:04<00:01, 4.89it/s] 75%|███████▌ | 21/28 [00:04<00:01, 4.94it/s] 79%|███████▊ | 22/28 [00:04<00:01, 4.98it/s] 82%|████████▏ | 23/28 [00:04<00:01, 4.92it/s] 86%|████████▌ | 24/28 [00:05<00:00, 4.85it/s] 89%|████████▉ | 25/28 [00:05<00:00, 4.89it/s] 93%|█████████▎| 26/28 [00:05<00:00, 4.88it/s] 96%|█████████▋| 27/28 [00:05<00:00, 4.93it/s] 100%|██████████| 28/28 [00:05<00:00, 4.93it/s] 100%|██████████| 28/28 [00:05<00:00, 4.80it/s] Decoding latents in cuda:0... done in 0.23s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.1ms Speed: 3.2ms preprocess, 7.1ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.5ms Speed: 2.8ms preprocess, 7.5ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:05, 5.11it/s] 7%|▋ | 2/28 [00:00<00:05, 5.12it/s] 11%|█ | 3/28 [00:00<00:04, 5.09it/s] 14%|█▍ | 4/28 [00:00<00:04, 5.11it/s] 18%|█▊ | 5/28 [00:00<00:04, 4.97it/s] 21%|██▏ | 6/28 [00:01<00:04, 5.01it/s] 25%|██▌ | 7/28 [00:01<00:04, 5.00it/s] 29%|██▊ | 8/28 [00:01<00:03, 5.05it/s] 32%|███▏ | 9/28 [00:01<00:03, 5.07it/s] 36%|███▌ | 10/28 [00:01<00:03, 4.97it/s] 39%|███▉ | 11/28 [00:02<00:03, 5.02it/s] 43%|████▎ | 12/28 [00:02<00:03, 5.05it/s] 46%|████▋ | 13/28 [00:02<00:02, 5.07it/s] 50%|█████ | 14/28 [00:02<00:02, 4.91it/s] 54%|█████▎ | 15/28 [00:03<00:02, 4.76it/s] 57%|█████▋ | 16/28 [00:03<00:02, 4.84it/s] 61%|██████ | 17/28 [00:03<00:02, 4.90it/s] 64%|██████▍ | 18/28 [00:03<00:02, 4.96it/s] 68%|██████▊ | 19/28 [00:03<00:01, 4.99it/s] 71%|███████▏ | 20/28 [00:04<00:01, 4.83it/s] 75%|███████▌ | 21/28 [00:04<00:01, 4.90it/s] 79%|███████▊ | 22/28 [00:04<00:01, 4.96it/s] 82%|████████▏ | 23/28 [00:04<00:00, 5.00it/s] 86%|████████▌ | 24/28 [00:04<00:00, 5.03it/s] 89%|████████▉ | 25/28 [00:05<00:00, 4.89it/s] 93%|█████████▎| 26/28 [00:05<00:00, 4.95it/s] 96%|█████████▋| 27/28 [00:05<00:00, 4.99it/s] 100%|██████████| 28/28 [00:05<00:00, 5.01it/s] 100%|██████████| 28/28 [00:05<00:00, 4.98it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.2ms Speed: 2.7ms preprocess, 7.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:05, 5.07it/s] 7%|▋ | 2/28 [00:00<00:05, 4.89it/s] 11%|█ | 3/28 [00:00<00:05, 4.98it/s] 14%|█▍ | 4/28 [00:00<00:04, 5.03it/s] 18%|█▊ | 5/28 [00:00<00:04, 5.05it/s] 21%|██▏ | 6/28 [00:01<00:04, 5.08it/s] 25%|██▌ | 7/28 [00:01<00:04, 5.01it/s] 29%|██▊ | 8/28 [00:01<00:04, 5.00it/s] 32%|███▏ | 9/28 [00:01<00:03, 5.03it/s] 36%|███▌ | 10/28 [00:01<00:03, 5.05it/s] 39%|███▉ | 11/28 [00:02<00:03, 5.05it/s] 43%|████▎ | 12/28 [00:02<00:03, 5.06it/s] 46%|████▋ | 13/28 [00:02<00:02, 5.05it/s] 50%|█████ | 14/28 [00:02<00:02, 5.05it/s] 54%|█████▎ | 15/28 [00:02<00:02, 5.04it/s] 57%|█████▋ | 16/28 [00:03<00:02, 5.04it/s] 61%|██████ | 17/28 [00:03<00:02, 5.04it/s] 64%|██████▍ | 18/28 [00:03<00:01, 5.05it/s] 68%|██████▊ | 19/28 [00:03<00:01, 5.05it/s] 71%|███████▏ | 20/28 [00:03<00:01, 5.07it/s] 75%|███████▌ | 21/28 [00:04<00:01, 5.06it/s] 79%|███████▊ | 22/28 [00:04<00:01, 5.07it/s] 82%|████████▏ | 23/28 [00:04<00:00, 5.01it/s] 86%|████████▌ | 24/28 [00:04<00:00, 5.00it/s] 89%|████████▉ | 25/28 [00:04<00:00, 5.01it/s] 93%|█████████▎| 26/28 [00:05<00:00, 5.01it/s] 96%|█████████▋| 27/28 [00:05<00:00, 4.99it/s] 100%|██████████| 28/28 [00:05<00:00, 4.97it/s] 100%|██████████| 28/28 [00:05<00:00, 5.02it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 2.9ms preprocess, 7.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. 0: 640x640 1 face, 7.6ms Speed: 2.8ms preprocess, 7.6ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:05, 5.14it/s] 7%|▋ | 2/28 [00:00<00:05, 5.06it/s] 11%|█ | 3/28 [00:00<00:04, 5.09it/s] 14%|█▍ | 4/28 [00:00<00:04, 4.97it/s] 18%|█▊ | 5/28 [00:00<00:04, 5.01it/s] 21%|██▏ | 6/28 [00:01<00:04, 5.05it/s] 25%|██▌ | 7/28 [00:01<00:04, 5.07it/s] 29%|██▊ | 8/28 [00:01<00:03, 5.07it/s] 32%|███▏ | 9/28 [00:01<00:03, 5.00it/s] 36%|███▌ | 10/28 [00:01<00:03, 5.02it/s] 39%|███▉ | 11/28 [00:02<00:03, 5.04it/s] 43%|████▎ | 12/28 [00:02<00:03, 5.05it/s] 46%|████▋ | 13/28 [00:02<00:02, 5.05it/s] 50%|█████ | 14/28 [00:02<00:02, 5.05it/s] 54%|█████▎ | 15/28 [00:02<00:02, 5.06it/s] 57%|█████▋ | 16/28 [00:03<00:02, 5.05it/s] 61%|██████ | 17/28 [00:03<00:02, 5.07it/s] 64%|██████▍ | 18/28 [00:03<00:01, 5.07it/s] 68%|██████▊ | 19/28 [00:03<00:01, 5.04it/s] 71%|███████▏ | 20/28 [00:03<00:01, 5.04it/s] 75%|███████▌ | 21/28 [00:04<00:01, 5.07it/s] 79%|███████▊ | 22/28 [00:04<00:01, 5.08it/s] 82%|████████▏ | 23/28 [00:04<00:00, 5.09it/s] 86%|████████▌ | 24/28 [00:04<00:00, 5.06it/s] 89%|████████▉ | 25/28 [00:04<00:00, 5.02it/s] 93%|█████████▎| 26/28 [00:05<00:00, 5.01it/s] 96%|█████████▋| 27/28 [00:05<00:00, 5.00it/s] 100%|██████████| 28/28 [00:05<00:00, 5.01it/s] 100%|██████████| 28/28 [00:05<00:00, 5.04it/s] Decoding latents in cuda:0... =========================================== A tensor with all NaNs was produced in VAE. Converted VAE into 32-bit float and retry. =========================================== done in 0.45s Move latents to cpu... done in 0.22s 0: 640x640 (no detections), 9.8ms Speed: 2.8ms preprocess, 9.8ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 4 with 2nd settings. Finished.