tungsten-logo
Sign In
photorealxl
photorealxl

photorealxl

4 stars
Version: photoRealSlimA
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/612b1b39f5df4da39976a1902c1f8657/00000-281714072.webp
https://files.tungsten.run/uploads/8ed095ce95f84be4b59d81a8561f74ae/00001-281714073.webp
https://files.tungsten.run/uploads/86ab79dd3302405e95eb9fb03521eac0/00002-281714074.webp
This example was created by sparks
Finished in 107.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: photo, 8k portrait 1girl, glitter, high resolution, detailed, portrait, shiny skin, multicolor,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: Clear, high quality, absence of JPEG artifacts, well-framed, devoid of watermarks, signatures, distortions, or mutations, correct proportions, clear background, focused, free from painting, framing, drawing, sketching, camera-rendering, and cropping elements, no watermarks, logos, barcodes, UI elements, signatures, text, labels, errors, titles, stickers, markings, speech bubbles, lines, low resolution, low quality, amateurish, low-rated, phone photography, wedding-related, framed, painted, Tumblr-style, and HDR or Terragen effects, without high contrast, Chinese characters, NSFW content, yellow tint, pubic hair, sketch duplications, oversized eyes, text, logos, or monochromatic tones 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:03<02:23, 3.68s/it] 5%|▌ | 2/40 [00:06<01:56, 3.06s/it] 8%|▊ | 3/40 [00:09<01:49, 2.97s/it] 10%|█ | 4/40 [00:11<01:42, 2.84s/it] 12%|█▎ | 5/40 [00:14<01:37, 2.80s/it] 15%|█▌ | 6/40 [00:17<01:35, 2.80s/it] 18%|█▊ | 7/40 [00:20<01:31, 2.76s/it] 20%|██ | 8/40 [00:22<01:29, 2.78s/it] 22%|██▎ | 9/40 [00:25<01:25, 2.75s/it] 25%|██▌ | 10/40 [00:28<01:20, 2.67s/it] 28%|██▊ | 11/40 [00:30<01:17, 2.68s/it] 30%|███ | 12/40 [00:33<01:14, 2.66s/it] 32%|███▎ | 13/40 [00:35<01:11, 2.64s/it] 35%|███▌ | 14/40 [00:38<01:08, 2.65s/it] 38%|███▊ | 15/40 [00:41<01:05, 2.61s/it] 40%|████ | 16/40 [00:43<01:01, 2.57s/it] 42%|████▎ | 17/40 [00:46<00:58, 2.54s/it] 45%|████▌ | 18/40 [00:48<00:55, 2.54s/it] 48%|████▊ | 19/40 [00:50<00:51, 2.48s/it] 50%|█████ | 20/40 [00:53<00:48, 2.45s/it] 52%|█████▎ | 21/40 [00:55<00:47, 2.51s/it] 55%|█████▌ | 22/40 [00:58<00:45, 2.53s/it] 57%|█████▊ | 23/40 [01:00<00:41, 2.45s/it] 60%|██████ | 24/40 [01:03<00:38, 2.39s/it] 62%|██████▎ | 25/40 [01:05<00:36, 2.45s/it] 65%|██████▌ | 26/40 [01:08<00:34, 2.45s/it] 68%|██████▊ | 27/40 [01:10<00:31, 2.43s/it] 70%|███████ | 28/40 [01:13<00:29, 2.47s/it] 72%|███████▎ | 29/40 [01:15<00:26, 2.44s/it] 75%|███████▌ | 30/40 [01:18<00:24, 2.49s/it] 78%|███████▊ | 31/40 [01:20<00:21, 2.44s/it] 80%|████████ | 32/40 [01:22<00:19, 2.40s/it] 82%|████████▎ | 33/40 [01:25<00:17, 2.45s/it] 85%|████████▌ | 34/40 [01:27<00:14, 2.36s/it] 88%|████████▊ | 35/40 [01:29<00:11, 2.33s/it] 90%|█████████ | 36/40 [01:31<00:09, 2.34s/it] 92%|█████████▎| 37/40 [01:34<00:06, 2.27s/it] 95%|█████████▌| 38/40 [01:35<00:04, 2.15s/it] 98%|█████████▊| 39/40 [01:37<00:01, 1.91s/it] 100%|██████████| 40/40 [01:38<00:00, 1.70s/it] 100%|██████████| 40/40 [01:38<00:00, 2.46s/it] Decoding latents in cuda:0... done in 2.34s Move latents to cpu... done in 0.03s Uploading outputs... Finished.
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/612b1b39f5df4da39976a1902c1f8657/00000-281714072.webp
https://files.tungsten.run/uploads/8ed095ce95f84be4b59d81a8561f74ae/00001-281714073.webp
https://files.tungsten.run/uploads/86ab79dd3302405e95eb9fb03521eac0/00002-281714074.webp
This example was created by sparks
Finished in 107.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: photo, 8k portrait 1girl, glitter, high resolution, detailed, portrait, shiny skin, multicolor,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: Clear, high quality, absence of JPEG artifacts, well-framed, devoid of watermarks, signatures, distortions, or mutations, correct proportions, clear background, focused, free from painting, framing, drawing, sketching, camera-rendering, and cropping elements, no watermarks, logos, barcodes, UI elements, signatures, text, labels, errors, titles, stickers, markings, speech bubbles, lines, low resolution, low quality, amateurish, low-rated, phone photography, wedding-related, framed, painted, Tumblr-style, and HDR or Terragen effects, without high contrast, Chinese characters, NSFW content, yellow tint, pubic hair, sketch duplications, oversized eyes, text, logos, or monochromatic tones 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:03<02:23, 3.68s/it] 5%|▌ | 2/40 [00:06<01:56, 3.06s/it] 8%|▊ | 3/40 [00:09<01:49, 2.97s/it] 10%|█ | 4/40 [00:11<01:42, 2.84s/it] 12%|█▎ | 5/40 [00:14<01:37, 2.80s/it] 15%|█▌ | 6/40 [00:17<01:35, 2.80s/it] 18%|█▊ | 7/40 [00:20<01:31, 2.76s/it] 20%|██ | 8/40 [00:22<01:29, 2.78s/it] 22%|██▎ | 9/40 [00:25<01:25, 2.75s/it] 25%|██▌ | 10/40 [00:28<01:20, 2.67s/it] 28%|██▊ | 11/40 [00:30<01:17, 2.68s/it] 30%|███ | 12/40 [00:33<01:14, 2.66s/it] 32%|███▎ | 13/40 [00:35<01:11, 2.64s/it] 35%|███▌ | 14/40 [00:38<01:08, 2.65s/it] 38%|███▊ | 15/40 [00:41<01:05, 2.61s/it] 40%|████ | 16/40 [00:43<01:01, 2.57s/it] 42%|████▎ | 17/40 [00:46<00:58, 2.54s/it] 45%|████▌ | 18/40 [00:48<00:55, 2.54s/it] 48%|████▊ | 19/40 [00:50<00:51, 2.48s/it] 50%|█████ | 20/40 [00:53<00:48, 2.45s/it] 52%|█████▎ | 21/40 [00:55<00:47, 2.51s/it] 55%|█████▌ | 22/40 [00:58<00:45, 2.53s/it] 57%|█████▊ | 23/40 [01:00<00:41, 2.45s/it] 60%|██████ | 24/40 [01:03<00:38, 2.39s/it] 62%|██████▎ | 25/40 [01:05<00:36, 2.45s/it] 65%|██████▌ | 26/40 [01:08<00:34, 2.45s/it] 68%|██████▊ | 27/40 [01:10<00:31, 2.43s/it] 70%|███████ | 28/40 [01:13<00:29, 2.47s/it] 72%|███████▎ | 29/40 [01:15<00:26, 2.44s/it] 75%|███████▌ | 30/40 [01:18<00:24, 2.49s/it] 78%|███████▊ | 31/40 [01:20<00:21, 2.44s/it] 80%|████████ | 32/40 [01:22<00:19, 2.40s/it] 82%|████████▎ | 33/40 [01:25<00:17, 2.45s/it] 85%|████████▌ | 34/40 [01:27<00:14, 2.36s/it] 88%|████████▊ | 35/40 [01:29<00:11, 2.33s/it] 90%|█████████ | 36/40 [01:31<00:09, 2.34s/it] 92%|█████████▎| 37/40 [01:34<00:06, 2.27s/it] 95%|█████████▌| 38/40 [01:35<00:04, 2.15s/it] 98%|█████████▊| 39/40 [01:37<00:01, 1.91s/it] 100%|██████████| 40/40 [01:38<00:00, 1.70s/it] 100%|██████████| 40/40 [01:38<00:00, 2.46s/it] Decoding latents in cuda:0... done in 2.34s Move latents to cpu... done in 0.03s Uploading outputs... Finished.