Version: v1.81
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/e5594484d19b49348777b44c75cddfb1/00000-1650465320.png
https://files.tungsten.run/uploads/baa6218cf8694acb8da059b7b6dfe2e2/00001-1650465321.png
https://files.tungsten.run/uploads/2806a1d1953d4931b2073b30dc728fcb/00002-1650465322.png
https://files.tungsten.run/uploads/9eaa37ef4c5244d487be534b8b9c2836/00003-1650465323.png
This example was created by evevalentine2017
Finished in 85.7 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/clearvae_v2.3_fp16.safetensors Full prompt: black humanoid made of rock, upper body, barechested, male, ((masterpiece, best quality)), cracked skin, white electricity coming through cracks, muscular male, (dragonborn:0.6), white hair, outdoors, detailed background <lora:dragonborn_offset:0.6> <lora:r1ge - AnimeRage:1> <lora:Cracked Skin:1.2>, , (top quality:1.5), (masterpiece:1.5), (ultra realistic:1.5), (ultra detailed:1.5), <lora:add_detail:0.3> Full negative prompt: BadDream, (UnrealisticDream:1.3), orange 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:56, 1.95s/it] 7%|▋ | 2/30 [00:03<00:51, 1.82s/it] 10%|█ | 3/30 [00:05<00:48, 1.79s/it] 13%|█▎ | 4/30 [00:07<00:47, 1.81s/it] 17%|█▋ | 5/30 [00:09<00:45, 1.83s/it] 20%|██ | 6/30 [00:10<00:43, 1.82s/it] 23%|██▎ | 7/30 [00:12<00:41, 1.78s/it] 27%|██▋ | 8/30 [00:14<00:39, 1.78s/it] 30%|███ | 9/30 [00:16<00:37, 1.81s/it] 33%|███▎ | 10/30 [00:18<00:36, 1.80s/it] 37%|███▋ | 11/30 [00:19<00:34, 1.80s/it] 40%|████ | 12/30 [00:21<00:32, 1.78s/it] 43%|████▎ | 13/30 [00:23<00:30, 1.78s/it] 47%|████▋ | 14/30 [00:24<00:27, 1.70s/it] 50%|█████ | 15/30 [00:26<00:25, 1.67s/it] 53%|█████▎ | 16/30 [00:28<00:22, 1.62s/it] 57%|█████▋ | 17/30 [00:29<00:21, 1.62s/it] 60%|██████ | 18/30 [00:31<00:19, 1.63s/it] 63%|██████▎ | 19/30 [00:32<00:17, 1.63s/it] 67%|██████▋ | 20/30 [00:34<00:16, 1.66s/it] 70%|███████ | 21/30 [00:36<00:14, 1.64s/it] 73%|███████▎ | 22/30 [00:37<00:13, 1.66s/it] 77%|███████▋ | 23/30 [00:39<00:11, 1.57s/it] 80%|████████ | 24/30 [00:40<00:09, 1.52s/it] 83%|████████▎ | 25/30 [00:42<00:07, 1.53s/it] 87%|████████▋ | 26/30 [00:43<00:06, 1.57s/it] 90%|█████████ | 27/30 [00:45<00:04, 1.58s/it] 93%|█████████▎| 28/30 [00:47<00:03, 1.56s/it] 97%|█████████▋| 29/30 [00:48<00:01, 1.37s/it] 100%|██████████| 30/30 [00:48<00:00, 1.16s/it] 100%|██████████| 30/30 [00:48<00:00, 1.62s/it] Decoding latents in cuda:0... done in 1.0s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.9ms Speed: 9.6ms preprocess, 7.9ms inference, 26.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:08, 1.89it/s] 12%|█▏ | 2/17 [00:00<00:06, 2.26it/s] 18%|█▊ | 3/17 [00:01<00:05, 2.47it/s] 24%|██▎ | 4/17 [00:01<00:05, 2.53it/s] 29%|██▉ | 5/17 [00:02<00:04, 2.53it/s] 35%|███▌ | 6/17 [00:02<00:04, 2.50it/s] 41%|████ | 7/17 [00:02<00:04, 2.48it/s] 47%|████▋ | 8/17 [00:03<00:03, 2.52it/s] 53%|█████▎ | 9/17 [00:03<00:03, 2.49it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.64it/s] 65%|██████▍ | 11/17 [00:04<00:02, 2.73it/s] 71%|███████ | 12/17 [00:04<00:01, 2.71it/s] 76%|███████▋ | 13/17 [00:05<00:01, 2.65it/s] 82%|████████▏ | 14/17 [00:05<00:01, 2.67it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.66it/s] 94%|█████████▍| 16/17 [00:06<00:00, 3.04it/s] 100%|██████████| 17/17 [00:06<00:00, 3.65it/s] 100%|██████████| 17/17 [00:06<00:00, 2.74it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.5ms Speed: 3.2ms preprocess, 7.5ms 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: 2.7ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:05, 2.70it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.66it/s] 18%|█▊ | 3/17 [00:01<00:05, 2.67it/s] 24%|██▎ | 4/17 [00:01<00:04, 2.64it/s] 29%|██▉ | 5/17 [00:01<00:04, 2.54it/s] 35%|███▌ | 6/17 [00:02<00:04, 2.56it/s] 41%|████ | 7/17 [00:02<00:03, 2.51it/s] 47%|████▋ | 8/17 [00:03<00:03, 2.55it/s] 53%|█████▎ | 9/17 [00:03<00:03, 2.52it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.66it/s] 65%|██████▍ | 11/17 [00:04<00:02, 2.75it/s] 71%|███████ | 12/17 [00:04<00:01, 2.74it/s] 76%|███████▋ | 13/17 [00:04<00:01, 2.64it/s] 82%|████████▏ | 14/17 [00:05<00:01, 2.67it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.69it/s] 94%|█████████▍| 16/17 [00:05<00:00, 3.07it/s] 100%|██████████| 17/17 [00:06<00:00, 3.64it/s] 100%|██████████| 17/17 [00:06<00:00, 2.80it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.1ms Speed: 2.8ms preprocess, 7.1ms inference, 0.8ms 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: 2.7ms 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 (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: 2.6ms preprocess, 7.6ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:06, 2.65it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.61it/s] 18%|█▊ | 3/17 [00:01<00:05, 2.67it/s] 24%|██▎ | 4/17 [00:01<00:04, 2.64it/s] 29%|██▉ | 5/17 [00:01<00:04, 2.59it/s] 35%|███▌ | 6/17 [00:02<00:04, 2.57it/s] 41%|████ | 7/17 [00:02<00:03, 2.52it/s] 47%|████▋ | 8/17 [00:03<00:03, 2.55it/s] 53%|█████▎ | 9/17 [00:03<00:03, 2.51it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.65it/s] 65%|██████▍ | 11/17 [00:04<00:02, 2.74it/s] 71%|███████ | 12/17 [00:04<00:01, 2.74it/s] 76%|███████▋ | 13/17 [00:04<00:01, 2.67it/s] 82%|████████▏ | 14/17 [00:05<00:01, 2.67it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.66it/s] 94%|█████████▍| 16/17 [00:05<00:00, 3.04it/s] 100%|██████████| 17/17 [00:06<00:00, 3.65it/s] 100%|██████████| 17/17 [00:06<00:00, 2.80it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.6ms Speed: 3.0ms preprocess, 7.6ms inference, 1.1ms 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/e5594484d19b49348777b44c75cddfb1/00000-1650465320.png
https://files.tungsten.run/uploads/baa6218cf8694acb8da059b7b6dfe2e2/00001-1650465321.png
https://files.tungsten.run/uploads/2806a1d1953d4931b2073b30dc728fcb/00002-1650465322.png
https://files.tungsten.run/uploads/9eaa37ef4c5244d487be534b8b9c2836/00003-1650465323.png
This example was created by evevalentine2017
Finished in 85.7 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/clearvae_v2.3_fp16.safetensors Full prompt: black humanoid made of rock, upper body, barechested, male, ((masterpiece, best quality)), cracked skin, white electricity coming through cracks, muscular male, (dragonborn:0.6), white hair, outdoors, detailed background <lora:dragonborn_offset:0.6> <lora:r1ge - AnimeRage:1> <lora:Cracked Skin:1.2>, , (top quality:1.5), (masterpiece:1.5), (ultra realistic:1.5), (ultra detailed:1.5), <lora:add_detail:0.3> Full negative prompt: BadDream, (UnrealisticDream:1.3), orange 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:56, 1.95s/it] 7%|▋ | 2/30 [00:03<00:51, 1.82s/it] 10%|█ | 3/30 [00:05<00:48, 1.79s/it] 13%|█▎ | 4/30 [00:07<00:47, 1.81s/it] 17%|█▋ | 5/30 [00:09<00:45, 1.83s/it] 20%|██ | 6/30 [00:10<00:43, 1.82s/it] 23%|██▎ | 7/30 [00:12<00:41, 1.78s/it] 27%|██▋ | 8/30 [00:14<00:39, 1.78s/it] 30%|███ | 9/30 [00:16<00:37, 1.81s/it] 33%|███▎ | 10/30 [00:18<00:36, 1.80s/it] 37%|███▋ | 11/30 [00:19<00:34, 1.80s/it] 40%|████ | 12/30 [00:21<00:32, 1.78s/it] 43%|████▎ | 13/30 [00:23<00:30, 1.78s/it] 47%|████▋ | 14/30 [00:24<00:27, 1.70s/it] 50%|█████ | 15/30 [00:26<00:25, 1.67s/it] 53%|█████▎ | 16/30 [00:28<00:22, 1.62s/it] 57%|█████▋ | 17/30 [00:29<00:21, 1.62s/it] 60%|██████ | 18/30 [00:31<00:19, 1.63s/it] 63%|██████▎ | 19/30 [00:32<00:17, 1.63s/it] 67%|██████▋ | 20/30 [00:34<00:16, 1.66s/it] 70%|███████ | 21/30 [00:36<00:14, 1.64s/it] 73%|███████▎ | 22/30 [00:37<00:13, 1.66s/it] 77%|███████▋ | 23/30 [00:39<00:11, 1.57s/it] 80%|████████ | 24/30 [00:40<00:09, 1.52s/it] 83%|████████▎ | 25/30 [00:42<00:07, 1.53s/it] 87%|████████▋ | 26/30 [00:43<00:06, 1.57s/it] 90%|█████████ | 27/30 [00:45<00:04, 1.58s/it] 93%|█████████▎| 28/30 [00:47<00:03, 1.56s/it] 97%|█████████▋| 29/30 [00:48<00:01, 1.37s/it] 100%|██████████| 30/30 [00:48<00:00, 1.16s/it] 100%|██████████| 30/30 [00:48<00:00, 1.62s/it] Decoding latents in cuda:0... done in 1.0s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.9ms Speed: 9.6ms preprocess, 7.9ms inference, 26.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:08, 1.89it/s] 12%|█▏ | 2/17 [00:00<00:06, 2.26it/s] 18%|█▊ | 3/17 [00:01<00:05, 2.47it/s] 24%|██▎ | 4/17 [00:01<00:05, 2.53it/s] 29%|██▉ | 5/17 [00:02<00:04, 2.53it/s] 35%|███▌ | 6/17 [00:02<00:04, 2.50it/s] 41%|████ | 7/17 [00:02<00:04, 2.48it/s] 47%|████▋ | 8/17 [00:03<00:03, 2.52it/s] 53%|█████▎ | 9/17 [00:03<00:03, 2.49it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.64it/s] 65%|██████▍ | 11/17 [00:04<00:02, 2.73it/s] 71%|███████ | 12/17 [00:04<00:01, 2.71it/s] 76%|███████▋ | 13/17 [00:05<00:01, 2.65it/s] 82%|████████▏ | 14/17 [00:05<00:01, 2.67it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.66it/s] 94%|█████████▍| 16/17 [00:06<00:00, 3.04it/s] 100%|██████████| 17/17 [00:06<00:00, 3.65it/s] 100%|██████████| 17/17 [00:06<00:00, 2.74it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.5ms Speed: 3.2ms preprocess, 7.5ms 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: 2.7ms preprocess, 7.5ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:05, 2.70it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.66it/s] 18%|█▊ | 3/17 [00:01<00:05, 2.67it/s] 24%|██▎ | 4/17 [00:01<00:04, 2.64it/s] 29%|██▉ | 5/17 [00:01<00:04, 2.54it/s] 35%|███▌ | 6/17 [00:02<00:04, 2.56it/s] 41%|████ | 7/17 [00:02<00:03, 2.51it/s] 47%|████▋ | 8/17 [00:03<00:03, 2.55it/s] 53%|█████▎ | 9/17 [00:03<00:03, 2.52it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.66it/s] 65%|██████▍ | 11/17 [00:04<00:02, 2.75it/s] 71%|███████ | 12/17 [00:04<00:01, 2.74it/s] 76%|███████▋ | 13/17 [00:04<00:01, 2.64it/s] 82%|████████▏ | 14/17 [00:05<00:01, 2.67it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.69it/s] 94%|█████████▍| 16/17 [00:05<00:00, 3.07it/s] 100%|██████████| 17/17 [00:06<00:00, 3.64it/s] 100%|██████████| 17/17 [00:06<00:00, 2.80it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.1ms Speed: 2.8ms preprocess, 7.1ms inference, 0.8ms 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: 2.7ms 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 (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: 2.6ms preprocess, 7.6ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/17 [00:00<?, ?it/s] 6%|▌ | 1/17 [00:00<00:06, 2.65it/s] 12%|█▏ | 2/17 [00:00<00:05, 2.61it/s] 18%|█▊ | 3/17 [00:01<00:05, 2.67it/s] 24%|██▎ | 4/17 [00:01<00:04, 2.64it/s] 29%|██▉ | 5/17 [00:01<00:04, 2.59it/s] 35%|███▌ | 6/17 [00:02<00:04, 2.57it/s] 41%|████ | 7/17 [00:02<00:03, 2.52it/s] 47%|████▋ | 8/17 [00:03<00:03, 2.55it/s] 53%|█████▎ | 9/17 [00:03<00:03, 2.51it/s] 59%|█████▉ | 10/17 [00:03<00:02, 2.65it/s] 65%|██████▍ | 11/17 [00:04<00:02, 2.74it/s] 71%|███████ | 12/17 [00:04<00:01, 2.74it/s] 76%|███████▋ | 13/17 [00:04<00:01, 2.67it/s] 82%|████████▏ | 14/17 [00:05<00:01, 2.67it/s] 88%|████████▊ | 15/17 [00:05<00:00, 2.66it/s] 94%|█████████▍| 16/17 [00:05<00:00, 3.04it/s] 100%|██████████| 17/17 [00:06<00:00, 3.65it/s] 100%|██████████| 17/17 [00:06<00:00, 2.80it/s] Decoding latents in cuda:0... done in 0.24s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.6ms Speed: 3.0ms preprocess, 7.6ms inference, 1.1ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 4 with 2nd settings. Finished.