tungsten-logo
Sign In
Cyberpunk Streets with Realism Engine SDXL
realism-engine-sdxl:v3.0
evevalentine2017
evevalentine2017
·
Feb 1
328
Input
prompt
Specify things to see in the output
A bustling cyberpunk cityscape at night, with neon lights reflected in the rain-soaked streets, and towering skyscrapers looming in the background.
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2139477933
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M SDE Karras
samping_steps
Number of denoising steps
24
cfg_scale
Scale for classifier-free guidance
3.1
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
None
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.
false
Output
https://files.tungsten.run/uploads/85e7bb0f8f08400485952481462442a7/00000-2139477933.webp
https://files.tungsten.run/uploads/69bc628e43c84313888288db0ce92788/00001-2139477934.webp
https://files.tungsten.run/uploads/9934f375d0f349c08ac78b144581ad6a/00002-2139477935.webp
Finished in 46.2 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: A bustling cyberpunk cityscape at night, with neon lights reflected in the rain-soaked streets, and towering skyscrapers looming in the background. Full negative prompt: 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:01<00:35, 1.54s/it] 8%|▊ | 2/24 [00:03<00:41, 1.88s/it] 12%|█▎ | 3/24 [00:05<00:40, 1.94s/it] 17%|█▋ | 4/24 [00:07<00:38, 1.94s/it] 21%|██ | 5/24 [00:09<00:37, 1.98s/it] 25%|██▌ | 6/24 [00:11<00:36, 2.00s/it] 29%|██▉ | 7/24 [00:13<00:33, 2.00s/it] 33%|███▎ | 8/24 [00:15<00:32, 2.03s/it] 38%|███▊ | 9/24 [00:17<00:30, 2.07s/it] 42%|████▏ | 10/24 [00:19<00:28, 2.05s/it] 46%|████▌ | 11/24 [00:21<00:26, 2.03s/it] 50%|█████ | 12/24 [00:23<00:23, 2.00s/it] 54%|█████▍ | 13/24 [00:25<00:21, 1.97s/it] 58%|█████▊ | 14/24 [00:27<00:19, 1.94s/it] 62%|██████▎ | 15/24 [00:29<00:17, 1.92s/it] 67%|██████▋ | 16/24 [00:31<00:15, 1.89s/it] 71%|███████ | 17/24 [00:32<00:12, 1.82s/it] 75%|███████▌ | 18/24 [00:35<00:11, 1.88s/it] 79%|███████▉ | 19/24 [00:36<00:09, 1.88s/it] 83%|████████▎ | 20/24 [00:38<00:07, 1.85s/it] 88%|████████▊ | 21/24 [00:40<00:05, 1.85s/it] 92%|█████████▏| 22/24 [00:42<00:03, 1.76s/it] 96%|█████████▌| 23/24 [00:43<00:01, 1.52s/it] 100%|██████████| 24/24 [00:43<00:00, 1.33s/it] 100%|██████████| 24/24 [00:43<00:00, 1.83s/it] Decoding latents in cuda:0... done in 1.66s Move latents to cpu... done in 0.02s Uploading outputs... Finished.
prompt
Specify things to see in the output
A bustling cyberpunk cityscape at night, with neon lights reflected in the rain-soaked streets, and towering skyscrapers looming in the background.
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2139477933
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M SDE Karras
samping_steps
Number of denoising steps
24
cfg_scale
Scale for classifier-free guidance
3.1
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
None
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.
false
https://files.tungsten.run/uploads/85e7bb0f8f08400485952481462442a7/00000-2139477933.webp
https://files.tungsten.run/uploads/69bc628e43c84313888288db0ce92788/00001-2139477934.webp
https://files.tungsten.run/uploads/9934f375d0f349c08ac78b144581ad6a/00002-2139477935.webp
Finished in 46.2 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: A bustling cyberpunk cityscape at night, with neon lights reflected in the rain-soaked streets, and towering skyscrapers looming in the background. Full negative prompt: 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:01<00:35, 1.54s/it] 8%|▊ | 2/24 [00:03<00:41, 1.88s/it] 12%|█▎ | 3/24 [00:05<00:40, 1.94s/it] 17%|█▋ | 4/24 [00:07<00:38, 1.94s/it] 21%|██ | 5/24 [00:09<00:37, 1.98s/it] 25%|██▌ | 6/24 [00:11<00:36, 2.00s/it] 29%|██▉ | 7/24 [00:13<00:33, 2.00s/it] 33%|███▎ | 8/24 [00:15<00:32, 2.03s/it] 38%|███▊ | 9/24 [00:17<00:30, 2.07s/it] 42%|████▏ | 10/24 [00:19<00:28, 2.05s/it] 46%|████▌ | 11/24 [00:21<00:26, 2.03s/it] 50%|█████ | 12/24 [00:23<00:23, 2.00s/it] 54%|█████▍ | 13/24 [00:25<00:21, 1.97s/it] 58%|█████▊ | 14/24 [00:27<00:19, 1.94s/it] 62%|██████▎ | 15/24 [00:29<00:17, 1.92s/it] 67%|██████▋ | 16/24 [00:31<00:15, 1.89s/it] 71%|███████ | 17/24 [00:32<00:12, 1.82s/it] 75%|███████▌ | 18/24 [00:35<00:11, 1.88s/it] 79%|███████▉ | 19/24 [00:36<00:09, 1.88s/it] 83%|████████▎ | 20/24 [00:38<00:07, 1.85s/it] 88%|████████▊ | 21/24 [00:40<00:05, 1.85s/it] 92%|█████████▏| 22/24 [00:42<00:03, 1.76s/it] 96%|█████████▌| 23/24 [00:43<00:01, 1.52s/it] 100%|██████████| 24/24 [00:43<00:00, 1.33s/it] 100%|██████████| 24/24 [00:43<00:00, 1.83s/it] Decoding latents in cuda:0... done in 1.66s Move latents to cpu... done in 0.02s Uploading outputs... Finished.