tungsten-logo
Sign In
realistic-art
realistic-art

realistic-art

6 stars
Version: v1.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
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
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
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.
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.
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/0fb7317e65fb4c71b84a8dc1536f3b1e/00000-4013745597.webp
https://files.tungsten.run/uploads/e3b43f2a03314ab7a4d0f1e41cbe52f2/00001-4013745598.webp
https://files.tungsten.run/uploads/e707fc1782cb4436a7454955d6aaa45c/00002-4013745599.webp
https://files.tungsten.run/uploads/8bbdb3b547d4451b854af02b09e67132/00003-4013745600.webp
This example was created by evevalentine2017
Finished in 91.2 seconds
Setting up the model... Processing... Full prompt: hyper detailed masterpiece, dynamic realistic digital art, awesome quality, interstellar province, spurting caldera, challenging terrain crevice distortion, aurora, transparent, pesticidal, streetwise, twinkling, cool, socratic, navigational, ethnic cuisine, <lora:epiCRealismHelper:1>, Full negative prompt: mirrored, cloned, duplicate, ugly, deformed, signature, watermark, realisticvision-negative-embedding 0%| | 0/46 [00:00<?, ?it/s] 2%|▏ | 1/46 [00:02<01:30, 2.01s/it] 4%|▍ | 2/46 [00:03<01:22, 1.88s/it] 7%|▋ | 3/46 [00:05<01:21, 1.91s/it] 9%|▊ | 4/46 [00:07<01:22, 1.96s/it] 11%|█ | 5/46 [00:09<01:17, 1.89s/it] 13%|█▎ | 6/46 [00:11<01:15, 1.88s/it] 15%|█▌ | 7/46 [00:13<01:14, 1.91s/it] 17%|█▋ | 8/46 [00:15<01:12, 1.91s/it] 20%|█▉ | 9/46 [00:17<01:10, 1.90s/it] 22%|██▏ | 10/46 [00:18<01:07, 1.88s/it] 24%|██▍ | 11/46 [00:20<01:04, 1.85s/it] 26%|██▌ | 12/46 [00:22<01:02, 1.83s/it] 28%|██▊ | 13/46 [00:24<01:01, 1.85s/it] 30%|███ | 14/46 [00:26<00:58, 1.83s/it] 33%|███▎ | 15/46 [00:27<00:55, 1.79s/it] 35%|███▍ | 16/46 [00:29<00:53, 1.78s/it] 37%|███▋ | 17/46 [00:31<00:53, 1.84s/it] 39%|███▉ | 18/46 [00:33<00:50, 1.80s/it] 41%|████▏ | 19/46 [00:35<00:47, 1.77s/it] 43%|████▎ | 20/46 [00:36<00:46, 1.79s/it] 46%|████▌ | 21/46 [00:38<00:45, 1.81s/it] 48%|████▊ | 22/46 [00:40<00:43, 1.79s/it] 50%|█████ | 23/46 [00:42<00:40, 1.77s/it] 52%|█████▏ | 24/46 [00:44<00:39, 1.78s/it] 54%|█████▍ | 25/46 [00:45<00:37, 1.81s/it] 57%|█████▋ | 26/46 [00:47<00:35, 1.78s/it] 59%|█████▊ | 27/46 [00:49<00:33, 1.77s/it] 61%|██████ | 28/46 [00:51<00:31, 1.77s/it] 63%|██████▎ | 29/46 [00:52<00:29, 1.75s/it] 65%|██████▌ | 30/46 [00:54<00:28, 1.77s/it] 67%|██████▋ | 31/46 [00:56<00:25, 1.67s/it] 70%|██████▉ | 32/46 [00:57<00:22, 1.60s/it] 72%|███████▏ | 33/46 [00:59<00:20, 1.58s/it] 74%|███████▍ | 34/46 [01:00<00:19, 1.61s/it] 76%|███████▌ | 35/46 [01:02<00:17, 1.60s/it] 78%|███████▊ | 36/46 [01:04<00:16, 1.65s/it] 80%|████████ | 37/46 [01:05<00:14, 1.60s/it] 83%|████████▎ | 38/46 [01:07<00:12, 1.61s/it] 85%|████████▍ | 39/46 [01:08<00:11, 1.59s/it] 87%|████████▋ | 40/46 [01:10<00:09, 1.60s/it] 89%|████████▉ | 41/46 [01:11<00:07, 1.57s/it] 91%|█████████▏| 42/46 [01:13<00:06, 1.57s/it] 93%|█████████▎| 43/46 [01:14<00:04, 1.50s/it] 96%|█████████▌| 44/46 [01:16<00:03, 1.53s/it] 98%|█████████▊| 45/46 [01:17<00:01, 1.31s/it] 100%|██████████| 46/46 [01:17<00:00, 1.11s/it] 100%|██████████| 46/46 [01:17<00:00, 1.69s/it] Decoding latents in cuda:0... done in 0.99s Move latents to cpu... done in 0.02s 0: 640x640 (no detections), 8.3ms Speed: 3.6ms preprocess, 8.3ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 8.4ms Speed: 2.9ms preprocess, 8.4ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 (no detections), 8.2ms Speed: 3.0ms preprocess, 8.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x640 (no detections), 8.1ms Speed: 2.9ms preprocess, 8.1ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 4 with 1st settings. Uploading outputs... Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
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
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
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.
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.
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/0fb7317e65fb4c71b84a8dc1536f3b1e/00000-4013745597.webp
https://files.tungsten.run/uploads/e3b43f2a03314ab7a4d0f1e41cbe52f2/00001-4013745598.webp
https://files.tungsten.run/uploads/e707fc1782cb4436a7454955d6aaa45c/00002-4013745599.webp
https://files.tungsten.run/uploads/8bbdb3b547d4451b854af02b09e67132/00003-4013745600.webp
This example was created by evevalentine2017
Finished in 91.2 seconds
Setting up the model... Processing... Full prompt: hyper detailed masterpiece, dynamic realistic digital art, awesome quality, interstellar province, spurting caldera, challenging terrain crevice distortion, aurora, transparent, pesticidal, streetwise, twinkling, cool, socratic, navigational, ethnic cuisine, <lora:epiCRealismHelper:1>, Full negative prompt: mirrored, cloned, duplicate, ugly, deformed, signature, watermark, realisticvision-negative-embedding 0%| | 0/46 [00:00<?, ?it/s] 2%|▏ | 1/46 [00:02<01:30, 2.01s/it] 4%|▍ | 2/46 [00:03<01:22, 1.88s/it] 7%|▋ | 3/46 [00:05<01:21, 1.91s/it] 9%|▊ | 4/46 [00:07<01:22, 1.96s/it] 11%|█ | 5/46 [00:09<01:17, 1.89s/it] 13%|█▎ | 6/46 [00:11<01:15, 1.88s/it] 15%|█▌ | 7/46 [00:13<01:14, 1.91s/it] 17%|█▋ | 8/46 [00:15<01:12, 1.91s/it] 20%|█▉ | 9/46 [00:17<01:10, 1.90s/it] 22%|██▏ | 10/46 [00:18<01:07, 1.88s/it] 24%|██▍ | 11/46 [00:20<01:04, 1.85s/it] 26%|██▌ | 12/46 [00:22<01:02, 1.83s/it] 28%|██▊ | 13/46 [00:24<01:01, 1.85s/it] 30%|███ | 14/46 [00:26<00:58, 1.83s/it] 33%|███▎ | 15/46 [00:27<00:55, 1.79s/it] 35%|███▍ | 16/46 [00:29<00:53, 1.78s/it] 37%|███▋ | 17/46 [00:31<00:53, 1.84s/it] 39%|███▉ | 18/46 [00:33<00:50, 1.80s/it] 41%|████▏ | 19/46 [00:35<00:47, 1.77s/it] 43%|████▎ | 20/46 [00:36<00:46, 1.79s/it] 46%|████▌ | 21/46 [00:38<00:45, 1.81s/it] 48%|████▊ | 22/46 [00:40<00:43, 1.79s/it] 50%|█████ | 23/46 [00:42<00:40, 1.77s/it] 52%|█████▏ | 24/46 [00:44<00:39, 1.78s/it] 54%|█████▍ | 25/46 [00:45<00:37, 1.81s/it] 57%|█████▋ | 26/46 [00:47<00:35, 1.78s/it] 59%|█████▊ | 27/46 [00:49<00:33, 1.77s/it] 61%|██████ | 28/46 [00:51<00:31, 1.77s/it] 63%|██████▎ | 29/46 [00:52<00:29, 1.75s/it] 65%|██████▌ | 30/46 [00:54<00:28, 1.77s/it] 67%|██████▋ | 31/46 [00:56<00:25, 1.67s/it] 70%|██████▉ | 32/46 [00:57<00:22, 1.60s/it] 72%|███████▏ | 33/46 [00:59<00:20, 1.58s/it] 74%|███████▍ | 34/46 [01:00<00:19, 1.61s/it] 76%|███████▌ | 35/46 [01:02<00:17, 1.60s/it] 78%|███████▊ | 36/46 [01:04<00:16, 1.65s/it] 80%|████████ | 37/46 [01:05<00:14, 1.60s/it] 83%|████████▎ | 38/46 [01:07<00:12, 1.61s/it] 85%|████████▍ | 39/46 [01:08<00:11, 1.59s/it] 87%|████████▋ | 40/46 [01:10<00:09, 1.60s/it] 89%|████████▉ | 41/46 [01:11<00:07, 1.57s/it] 91%|█████████▏| 42/46 [01:13<00:06, 1.57s/it] 93%|█████████▎| 43/46 [01:14<00:04, 1.50s/it] 96%|█████████▌| 44/46 [01:16<00:03, 1.53s/it] 98%|█████████▊| 45/46 [01:17<00:01, 1.31s/it] 100%|██████████| 46/46 [01:17<00:00, 1.11s/it] 100%|██████████| 46/46 [01:17<00:00, 1.69s/it] Decoding latents in cuda:0... done in 0.99s Move latents to cpu... done in 0.02s 0: 640x640 (no detections), 8.3ms Speed: 3.6ms preprocess, 8.3ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 8.4ms Speed: 2.9ms preprocess, 8.4ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 (no detections), 8.2ms Speed: 3.0ms preprocess, 8.2ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x640 (no detections), 8.1ms Speed: 2.9ms preprocess, 8.1ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 4 with 1st settings. Uploading outputs... Finished.