tungsten-logo
Sign In
realistic-vision
realistic-vision

realistic-vision

92 stars
Version: v5.1-base-v4.3
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/bf8d68b0779747d6b8da2afb061ef224/00000-2238860859.png
https://files.tungsten.run/uploads/6c804cc9d3df43a991fa07445ad721e2/00001-2238860860.png
https://files.tungsten.run/uploads/632cee8c751c4758811a528b0af1eb1c/00002-2238860861.png
https://files.tungsten.run/uploads/72b8cf27eefd4063be593d1cfaf84aff/00003-2238860862.png
This example was created by wwwbookafficionado
Finished in 124.8 seconds
Setting up the model... Processing... Full prompt: photography of (Russian woman1.3), 40 years old, wearing cotton panties and mesh shirt, sexy attire, (looking at viewer:1.2), (in neon tokyo alley:1.2), hyper realistic texture human skin, flat lighting, (soft saturation:1.2), analog style,<lora:add_sharpness:0.7>, <lora:photoblend:0.4>, <lora:epiNoiseoffset_v2-pynoise:0.6> Full negative prompt: nsfwEM, bad-artist, bad-image-v2-39000, bad-picture-chill-75v, bad_prompt, easynegative, FastNegativeV2, fcNeg-neg, kkw-ph1-neg, ng_deepnegative_v1_75t, rmadanegative402_sd15-neg, verybadimagenegative_v1.3, black and white, bnw, b&w, (grey:1.3), (gray:1.3), (greyscale:1.3), (grayscale:1.3), gym, anime, cartoon, painting, girls, women, people, crowd, passer-by, passerby, passers-by, passersby, twisted body, screwed body, gay, gays, shemale, dick, penis, (hat:1.3), (headgear:1.3), (cap:1.3), (beret:1.3), glasses, covering, luggage, (horns:1.5), (evil:1.3), (devil:1.3), angel, (demon:1.3),santa,christmass, goblin, smurf, (monster:1.3), blood, mad, angry, sad, wings, ears, wings, feather, headband, band, maid, mask, flu mask, horror, (closed eyes:1.3), eyes closed, watermark, (text:1.3), logo, earrings, levelry, (teeth:1.3), (teeths:1.3), (open mouth:1.3), (tan lines:1.3), (dark shadows:1.3), (shadows:1.3), strong shadows, shawl, cloth, wrap, clothes, wearing, wears, covering, soup, BadDream, UnrealisticDream, bad-hands-5 Couldn't find network with name add_sharpness Couldn't find network with name photoblend Couldn't find network with name epiNoiseoffset_v2-pynoise 0%| | 0/45 [00:00<?, ?it/s] 2%|▏ | 1/45 [00:02<01:41, 2.30s/it] 4%|▍ | 2/45 [00:05<01:58, 2.76s/it] 7%|▋ | 3/45 [00:08<02:01, 2.89s/it] 9%|▉ | 4/45 [00:11<02:01, 2.97s/it] 11%|█ | 5/45 [00:14<02:00, 3.00s/it] 13%|█▎ | 6/45 [00:17<01:57, 3.02s/it] 16%|█▌ | 7/45 [00:20<01:53, 2.99s/it] 18%|█▊ | 8/45 [00:23<01:51, 3.01s/it] 20%|██ | 9/45 [00:26<01:48, 3.00s/it] 22%|██▏ | 10/45 [00:29<01:45, 3.01s/it] 24%|██▍ | 11/45 [00:32<01:41, 3.00s/it] 27%|██▋ | 12/45 [00:35<01:38, 2.99s/it] 29%|██▉ | 13/45 [00:38<01:34, 2.94s/it] 31%|███ | 14/45 [00:41<01:31, 2.96s/it] 33%|███▎ | 15/45 [00:44<01:28, 2.97s/it] 36%|███▌ | 16/45 [00:47<01:25, 2.94s/it] 38%|███▊ | 17/45 [00:49<01:15, 2.70s/it] 40%|████ | 18/45 [00:52<01:13, 2.70s/it] 42%|████▏ | 19/45 [00:54<01:10, 2.72s/it] 44%|████▍ | 20/45 [00:57<01:09, 2.79s/it] 47%|████▋ | 21/45 [01:00<01:07, 2.79s/it] 49%|████▉ | 22/45 [01:03<01:03, 2.78s/it] 51%|█████ | 23/45 [01:06<01:01, 2.79s/it] 53%|█████▎ | 24/45 [01:09<00:59, 2.82s/it] 56%|█████▌ | 25/45 [01:11<00:56, 2.84s/it] 58%|█████▊ | 26/45 [01:14<00:54, 2.84s/it] 60%|██████ | 27/45 [01:17<00:51, 2.86s/it] 62%|██████▏ | 28/45 [01:20<00:48, 2.85s/it] 64%|██████▍ | 29/45 [01:23<00:44, 2.81s/it] 67%|██████▋ | 30/45 [01:25<00:40, 2.73s/it] 69%|██████▉ | 31/45 [01:28<00:37, 2.68s/it] 71%|███████ | 32/45 [01:30<00:32, 2.52s/it] 73%|███████▎ | 33/45 [01:33<00:30, 2.54s/it] 76%|███████▌ | 34/45 [01:35<00:27, 2.53s/it] 78%|███████▊ | 35/45 [01:37<00:24, 2.42s/it] 80%|████████ | 36/45 [01:40<00:21, 2.38s/it] 82%|████████▏ | 37/45 [01:42<00:18, 2.30s/it] 84%|████████▍ | 38/45 [01:44<00:16, 2.30s/it] 87%|████████▋ | 39/45 [01:46<00:13, 2.20s/it] 89%|████████▉ | 40/45 [01:48<00:10, 2.10s/it] 91%|█████████ | 41/45 [01:50<00:08, 2.04s/it] 93%|█████████▎| 42/45 [01:51<00:05, 1.94s/it] 96%|█████████▌| 43/45 [01:53<00:03, 1.95s/it] 98%|█████████▊| 44/45 [01:55<00:01, 1.87s/it] 100%|██████████| 45/45 [01:56<00:00, 1.48s/it] 100%|██████████| 45/45 [01:56<00:00, 2.58s/it] Decoding latents in cuda:0... done in 0.85s Move latents to cpu... done in 0.02s 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/bf8d68b0779747d6b8da2afb061ef224/00000-2238860859.png
https://files.tungsten.run/uploads/6c804cc9d3df43a991fa07445ad721e2/00001-2238860860.png
https://files.tungsten.run/uploads/632cee8c751c4758811a528b0af1eb1c/00002-2238860861.png
https://files.tungsten.run/uploads/72b8cf27eefd4063be593d1cfaf84aff/00003-2238860862.png
This example was created by wwwbookafficionado
Finished in 124.8 seconds
Setting up the model... Processing... Full prompt: photography of (Russian woman1.3), 40 years old, wearing cotton panties and mesh shirt, sexy attire, (looking at viewer:1.2), (in neon tokyo alley:1.2), hyper realistic texture human skin, flat lighting, (soft saturation:1.2), analog style,<lora:add_sharpness:0.7>, <lora:photoblend:0.4>, <lora:epiNoiseoffset_v2-pynoise:0.6> Full negative prompt: nsfwEM, bad-artist, bad-image-v2-39000, bad-picture-chill-75v, bad_prompt, easynegative, FastNegativeV2, fcNeg-neg, kkw-ph1-neg, ng_deepnegative_v1_75t, rmadanegative402_sd15-neg, verybadimagenegative_v1.3, black and white, bnw, b&w, (grey:1.3), (gray:1.3), (greyscale:1.3), (grayscale:1.3), gym, anime, cartoon, painting, girls, women, people, crowd, passer-by, passerby, passers-by, passersby, twisted body, screwed body, gay, gays, shemale, dick, penis, (hat:1.3), (headgear:1.3), (cap:1.3), (beret:1.3), glasses, covering, luggage, (horns:1.5), (evil:1.3), (devil:1.3), angel, (demon:1.3),santa,christmass, goblin, smurf, (monster:1.3), blood, mad, angry, sad, wings, ears, wings, feather, headband, band, maid, mask, flu mask, horror, (closed eyes:1.3), eyes closed, watermark, (text:1.3), logo, earrings, levelry, (teeth:1.3), (teeths:1.3), (open mouth:1.3), (tan lines:1.3), (dark shadows:1.3), (shadows:1.3), strong shadows, shawl, cloth, wrap, clothes, wearing, wears, covering, soup, BadDream, UnrealisticDream, bad-hands-5 Couldn't find network with name add_sharpness Couldn't find network with name photoblend Couldn't find network with name epiNoiseoffset_v2-pynoise 0%| | 0/45 [00:00<?, ?it/s] 2%|▏ | 1/45 [00:02<01:41, 2.30s/it] 4%|▍ | 2/45 [00:05<01:58, 2.76s/it] 7%|▋ | 3/45 [00:08<02:01, 2.89s/it] 9%|▉ | 4/45 [00:11<02:01, 2.97s/it] 11%|█ | 5/45 [00:14<02:00, 3.00s/it] 13%|█▎ | 6/45 [00:17<01:57, 3.02s/it] 16%|█▌ | 7/45 [00:20<01:53, 2.99s/it] 18%|█▊ | 8/45 [00:23<01:51, 3.01s/it] 20%|██ | 9/45 [00:26<01:48, 3.00s/it] 22%|██▏ | 10/45 [00:29<01:45, 3.01s/it] 24%|██▍ | 11/45 [00:32<01:41, 3.00s/it] 27%|██▋ | 12/45 [00:35<01:38, 2.99s/it] 29%|██▉ | 13/45 [00:38<01:34, 2.94s/it] 31%|███ | 14/45 [00:41<01:31, 2.96s/it] 33%|███▎ | 15/45 [00:44<01:28, 2.97s/it] 36%|███▌ | 16/45 [00:47<01:25, 2.94s/it] 38%|███▊ | 17/45 [00:49<01:15, 2.70s/it] 40%|████ | 18/45 [00:52<01:13, 2.70s/it] 42%|████▏ | 19/45 [00:54<01:10, 2.72s/it] 44%|████▍ | 20/45 [00:57<01:09, 2.79s/it] 47%|████▋ | 21/45 [01:00<01:07, 2.79s/it] 49%|████▉ | 22/45 [01:03<01:03, 2.78s/it] 51%|█████ | 23/45 [01:06<01:01, 2.79s/it] 53%|█████▎ | 24/45 [01:09<00:59, 2.82s/it] 56%|█████▌ | 25/45 [01:11<00:56, 2.84s/it] 58%|█████▊ | 26/45 [01:14<00:54, 2.84s/it] 60%|██████ | 27/45 [01:17<00:51, 2.86s/it] 62%|██████▏ | 28/45 [01:20<00:48, 2.85s/it] 64%|██████▍ | 29/45 [01:23<00:44, 2.81s/it] 67%|██████▋ | 30/45 [01:25<00:40, 2.73s/it] 69%|██████▉ | 31/45 [01:28<00:37, 2.68s/it] 71%|███████ | 32/45 [01:30<00:32, 2.52s/it] 73%|███████▎ | 33/45 [01:33<00:30, 2.54s/it] 76%|███████▌ | 34/45 [01:35<00:27, 2.53s/it] 78%|███████▊ | 35/45 [01:37<00:24, 2.42s/it] 80%|████████ | 36/45 [01:40<00:21, 2.38s/it] 82%|████████▏ | 37/45 [01:42<00:18, 2.30s/it] 84%|████████▍ | 38/45 [01:44<00:16, 2.30s/it] 87%|████████▋ | 39/45 [01:46<00:13, 2.20s/it] 89%|████████▉ | 40/45 [01:48<00:10, 2.10s/it] 91%|█████████ | 41/45 [01:50<00:08, 2.04s/it] 93%|█████████▎| 42/45 [01:51<00:05, 1.94s/it] 96%|█████████▌| 43/45 [01:53<00:03, 1.95s/it] 98%|█████████▊| 44/45 [01:55<00:01, 1.87s/it] 100%|██████████| 45/45 [01:56<00:00, 1.48s/it] 100%|██████████| 45/45 [01:56<00:00, 2.58s/it] Decoding latents in cuda:0... done in 0.85s Move latents to cpu... done in 0.02s Uploading outputs... Finished.