tungsten-logo
Sign In
FULLY_REAL_XL
FULLY_REAL_XL

FULLY_REAL_XL

15 stars
Version: v10Perfect10n
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
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
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/256e8a933a4e45188ac0db30484c566a/00000-2133542551.webp
https://files.tungsten.run/uploads/738a59bf0e4747d8bb59b450a077868d/00001-2133542552.webp
https://files.tungsten.run/uploads/f1341ac37b424e8087ca772994c0c14d/00002-2133542553.webp
This example was created by sparks
Finished in 206.7 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: cinematic film still leaning toward the viewer, fisheye-lense-photo, 23 year old redhead, "Streetpunk Sexy" - Visualize a portrait of a young woman on a city street. rainy night, The shot, taken from a distance, captures her (wet body: 1.6) and indifferent expression in the midst of the urban night, with body sweat and wetness hinting at the city's humid atmosphere. white-dress, black-crop-top, messy hair, pigtails, candid pose, head tilt, The photo, taken with a Canon EOS 5D Mark III, showcases her natural skin texture, including subtle acne (0.3), in hyperrealistic detail under soft, sharp lighting. The depth of field focuses on her, against a backdrop of soothing, muted colors and high contrast, creating a dark, yet gorgeous (1.2) and immersive night scene, approaching perfection, dynamic, highly detailed, smooth, sharp focus, art by Carne Griffiths and Wadim Kashin, trending on artstation, sharp focus, intricate details, highly detailed, by Greg Rutkowski, mysterious, epic, cinematic, create a photorealistic image that the viewer has never envisioned before, the image should demonstrate extreme creativity, imaginative, bold, inspiring, original in subject, original in style, amazing composition, intricately detailed, absurdly complex, . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy., <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: ((nudity, nsfw:1.5)), bad anatomy, bad hands, text, watermark, low-quality, signature, moiré pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, bad-contrast, 0%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:03<03:46, 3.84s/it] 3%|▎ | 2/60 [00:07<03:24, 3.52s/it] 5%|▌ | 3/60 [00:10<03:21, 3.53s/it] 7%|▋ | 4/60 [00:13<03:09, 3.38s/it] 8%|▊ | 5/60 [00:17<03:05, 3.38s/it] 10%|█ | 6/60 [00:20<03:04, 3.41s/it] 12%|█▏ | 7/60 [00:23<02:54, 3.29s/it] 13%|█▎ | 8/60 [00:27<02:52, 3.32s/it] 15%|█▌ | 9/60 [00:30<02:47, 3.29s/it] 17%|█▋ | 10/60 [00:33<02:44, 3.28s/it] 18%|█▊ | 11/60 [00:36<02:42, 3.31s/it] 20%|██ | 12/60 [00:40<02:44, 3.42s/it] 22%|██▏ | 13/60 [00:44<02:44, 3.49s/it] 23%|██▎ | 14/60 [00:48<02:43, 3.56s/it] 25%|██▌ | 15/60 [00:51<02:37, 3.51s/it] 27%|██▋ | 16/60 [00:54<02:32, 3.47s/it] 28%|██▊ | 17/60 [00:58<02:30, 3.51s/it] 30%|███ | 18/60 [01:02<02:37, 3.76s/it] 32%|███▏ | 19/60 [01:06<02:37, 3.85s/it] 33%|███▎ | 20/60 [01:10<02:28, 3.71s/it] 35%|███▌ | 21/60 [01:13<02:18, 3.55s/it] 37%|███▋ | 22/60 [01:16<02:11, 3.46s/it] 38%|███▊ | 23/60 [01:19<02:02, 3.31s/it] 40%|████ | 24/60 [01:23<02:01, 3.38s/it] 42%|████▏ | 25/60 [01:26<02:00, 3.44s/it] 43%|████▎ | 26/60 [01:30<02:01, 3.57s/it] 45%|████▌ | 27/60 [01:34<01:56, 3.54s/it] 47%|████▋ | 28/60 [01:37<01:54, 3.57s/it] 48%|████▊ | 29/60 [01:41<01:51, 3.60s/it] 50%|█████ | 30/60 [01:45<01:50, 3.67s/it] 52%|█████▏ | 31/60 [01:48<01:46, 3.66s/it] 53%|█████▎ | 32/60 [01:52<01:39, 3.54s/it] 55%|█████▌ | 33/60 [01:55<01:34, 3.51s/it] 57%|█████▋ | 34/60 [01:59<01:31, 3.52s/it] 58%|█████▊ | 35/60 [02:02<01:27, 3.50s/it] 60%|██████ | 36/60 [02:05<01:23, 3.46s/it] 62%|██████▏ | 37/60 [02:09<01:18, 3.39s/it] 63%|██████▎ | 38/60 [02:12<01:14, 3.37s/it] 65%|██████▌ | 39/60 [02:15<01:09, 3.32s/it] 67%|██████▋ | 40/60 [02:19<01:07, 3.36s/it] 68%|██████▊ | 41/60 [02:22<01:03, 3.35s/it] 70%|███████ | 42/60 [02:25<01:00, 3.36s/it] 72%|███████▏ | 43/60 [02:29<00:56, 3.35s/it] 73%|███████▎ | 44/60 [02:32<00:53, 3.34s/it] 75%|███████▌ | 45/60 [02:35<00:47, 3.16s/it] 77%|███████▋ | 46/60 [02:37<00:42, 3.06s/it] 78%|███████▊ | 47/60 [02:41<00:40, 3.10s/it] 80%|████████ | 48/60 [02:44<00:36, 3.05s/it] 82%|████████▏ | 49/60 [02:47<00:33, 3.03s/it] 83%|████████▎ | 50/60 [02:50<00:30, 3.07s/it] 85%|████████▌ | 51/60 [02:53<00:27, 3.01s/it] 87%|████████▋ | 52/60 [02:56<00:23, 2.96s/it] 88%|████████▊ | 53/60 [02:59<00:21, 3.01s/it] 90%|█████████ | 54/60 [03:02<00:17, 2.97s/it] 92%|█████████▏| 55/60 [03:04<00:14, 2.92s/it] 93%|█████████▎| 56/60 [03:07<00:11, 2.95s/it] 95%|█████████▌| 57/60 [03:10<00:08, 2.93s/it] 97%|█████████▋| 58/60 [03:13<00:06, 3.01s/it] 98%|█████████▊| 59/60 [03:16<00:02, 2.76s/it] 100%|██████████| 60/60 [03:17<00:00, 2.39s/it] 100%|██████████| 60/60 [03:17<00:00, 3.29s/it] Decoding latents in cuda:0... done in 2.85s Move latents to cpu... done in 0.04s
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
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
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/256e8a933a4e45188ac0db30484c566a/00000-2133542551.webp
https://files.tungsten.run/uploads/738a59bf0e4747d8bb59b450a077868d/00001-2133542552.webp
https://files.tungsten.run/uploads/f1341ac37b424e8087ca772994c0c14d/00002-2133542553.webp
This example was created by sparks
Finished in 206.7 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: cinematic film still leaning toward the viewer, fisheye-lense-photo, 23 year old redhead, "Streetpunk Sexy" - Visualize a portrait of a young woman on a city street. rainy night, The shot, taken from a distance, captures her (wet body: 1.6) and indifferent expression in the midst of the urban night, with body sweat and wetness hinting at the city's humid atmosphere. white-dress, black-crop-top, messy hair, pigtails, candid pose, head tilt, The photo, taken with a Canon EOS 5D Mark III, showcases her natural skin texture, including subtle acne (0.3), in hyperrealistic detail under soft, sharp lighting. The depth of field focuses on her, against a backdrop of soothing, muted colors and high contrast, creating a dark, yet gorgeous (1.2) and immersive night scene, approaching perfection, dynamic, highly detailed, smooth, sharp focus, art by Carne Griffiths and Wadim Kashin, trending on artstation, sharp focus, intricate details, highly detailed, by Greg Rutkowski, mysterious, epic, cinematic, create a photorealistic image that the viewer has never envisioned before, the image should demonstrate extreme creativity, imaginative, bold, inspiring, original in subject, original in style, amazing composition, intricately detailed, absurdly complex, . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy., <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: ((nudity, nsfw:1.5)), bad anatomy, bad hands, text, watermark, low-quality, signature, moiré pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, bad-contrast, 0%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:03<03:46, 3.84s/it] 3%|▎ | 2/60 [00:07<03:24, 3.52s/it] 5%|▌ | 3/60 [00:10<03:21, 3.53s/it] 7%|▋ | 4/60 [00:13<03:09, 3.38s/it] 8%|▊ | 5/60 [00:17<03:05, 3.38s/it] 10%|█ | 6/60 [00:20<03:04, 3.41s/it] 12%|█▏ | 7/60 [00:23<02:54, 3.29s/it] 13%|█▎ | 8/60 [00:27<02:52, 3.32s/it] 15%|█▌ | 9/60 [00:30<02:47, 3.29s/it] 17%|█▋ | 10/60 [00:33<02:44, 3.28s/it] 18%|█▊ | 11/60 [00:36<02:42, 3.31s/it] 20%|██ | 12/60 [00:40<02:44, 3.42s/it] 22%|██▏ | 13/60 [00:44<02:44, 3.49s/it] 23%|██▎ | 14/60 [00:48<02:43, 3.56s/it] 25%|██▌ | 15/60 [00:51<02:37, 3.51s/it] 27%|██▋ | 16/60 [00:54<02:32, 3.47s/it] 28%|██▊ | 17/60 [00:58<02:30, 3.51s/it] 30%|███ | 18/60 [01:02<02:37, 3.76s/it] 32%|███▏ | 19/60 [01:06<02:37, 3.85s/it] 33%|███▎ | 20/60 [01:10<02:28, 3.71s/it] 35%|███▌ | 21/60 [01:13<02:18, 3.55s/it] 37%|███▋ | 22/60 [01:16<02:11, 3.46s/it] 38%|███▊ | 23/60 [01:19<02:02, 3.31s/it] 40%|████ | 24/60 [01:23<02:01, 3.38s/it] 42%|████▏ | 25/60 [01:26<02:00, 3.44s/it] 43%|████▎ | 26/60 [01:30<02:01, 3.57s/it] 45%|████▌ | 27/60 [01:34<01:56, 3.54s/it] 47%|████▋ | 28/60 [01:37<01:54, 3.57s/it] 48%|████▊ | 29/60 [01:41<01:51, 3.60s/it] 50%|█████ | 30/60 [01:45<01:50, 3.67s/it] 52%|█████▏ | 31/60 [01:48<01:46, 3.66s/it] 53%|█████▎ | 32/60 [01:52<01:39, 3.54s/it] 55%|█████▌ | 33/60 [01:55<01:34, 3.51s/it] 57%|█████▋ | 34/60 [01:59<01:31, 3.52s/it] 58%|█████▊ | 35/60 [02:02<01:27, 3.50s/it] 60%|██████ | 36/60 [02:05<01:23, 3.46s/it] 62%|██████▏ | 37/60 [02:09<01:18, 3.39s/it] 63%|██████▎ | 38/60 [02:12<01:14, 3.37s/it] 65%|██████▌ | 39/60 [02:15<01:09, 3.32s/it] 67%|██████▋ | 40/60 [02:19<01:07, 3.36s/it] 68%|██████▊ | 41/60 [02:22<01:03, 3.35s/it] 70%|███████ | 42/60 [02:25<01:00, 3.36s/it] 72%|███████▏ | 43/60 [02:29<00:56, 3.35s/it] 73%|███████▎ | 44/60 [02:32<00:53, 3.34s/it] 75%|███████▌ | 45/60 [02:35<00:47, 3.16s/it] 77%|███████▋ | 46/60 [02:37<00:42, 3.06s/it] 78%|███████▊ | 47/60 [02:41<00:40, 3.10s/it] 80%|████████ | 48/60 [02:44<00:36, 3.05s/it] 82%|████████▏ | 49/60 [02:47<00:33, 3.03s/it] 83%|████████▎ | 50/60 [02:50<00:30, 3.07s/it] 85%|████████▌ | 51/60 [02:53<00:27, 3.01s/it] 87%|████████▋ | 52/60 [02:56<00:23, 2.96s/it] 88%|████████▊ | 53/60 [02:59<00:21, 3.01s/it] 90%|█████████ | 54/60 [03:02<00:17, 2.97s/it] 92%|█████████▏| 55/60 [03:04<00:14, 2.92s/it] 93%|█████████▎| 56/60 [03:07<00:11, 2.95s/it] 95%|█████████▌| 57/60 [03:10<00:08, 2.93s/it] 97%|█████████▋| 58/60 [03:13<00:06, 3.01s/it] 98%|█████████▊| 59/60 [03:16<00:02, 2.76s/it] 100%|██████████| 60/60 [03:17<00:00, 2.39s/it] 100%|██████████| 60/60 [03:17<00:00, 3.29s/it] Decoding latents in cuda:0... done in 2.85s Move latents to cpu... done in 0.04s