tungsten-logo
Sign In
Sand Castle with Ultraspice (XLTURBO)
ultraspicexl-turbo:v1.0
sparks
sparks
·
Feb 3
372
Input
prompt
Specify things to see in the output
a castle of sand in a house of glass, high quality, 4K
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
3
width
Output image width
1200
height
Output image height
1200
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
1.5
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.
1854530925
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++ SDE Karras
samping_steps
Number of denoising steps
11
cfg_scale
Scale for classifier-free guidance
1.5
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/90d80c1764244bf2a04be87ddac5838d/00000-1854530925.webp
https://files.tungsten.run/uploads/a1923f745ff94c29b7588c88abc83395/00001-1854530926.webp
https://files.tungsten.run/uploads/3ef1e557a8124ce68926fa2c4b257dc2/00002-1854530927.webp
Finished in 86.5 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: a castle of sand in a house of glass, high quality, 4K, <lora:add-detail-xl:1.5> Full negative prompt: 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:07<01:13, 7.38s/it] 18%|█▊ | 2/11 [00:15<01:10, 7.80s/it] 27%|██▋ | 3/11 [00:23<01:03, 7.96s/it] 36%|███▋ | 4/11 [00:32<00:57, 8.17s/it] 45%|████▌ | 5/11 [00:40<00:48, 8.16s/it] 55%|█████▍ | 6/11 [00:48<00:40, 8.09s/it] 64%|██████▎ | 7/11 [00:55<00:31, 7.93s/it] 73%|███████▎ | 8/11 [01:03<00:23, 7.84s/it] 82%|████████▏ | 9/11 [01:11<00:15, 7.76s/it] 91%|█████████ | 10/11 [01:16<00:07, 7.07s/it] 100%|██████████| 11/11 [01:18<00:00, 5.53s/it] 100%|██████████| 11/11 [01:18<00:00, 7.15s/it] Decoding latents in cuda:0... done in 3.34s Move latents to cpu... done in 0.04s Uploading outputs... Finished.
prompt
Specify things to see in the output
a castle of sand in a house of glass, high quality, 4K
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
3
width
Output image width
1200
height
Output image height
1200
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
1.5
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.
1854530925
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++ SDE Karras
samping_steps
Number of denoising steps
11
cfg_scale
Scale for classifier-free guidance
1.5
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/90d80c1764244bf2a04be87ddac5838d/00000-1854530925.webp
https://files.tungsten.run/uploads/a1923f745ff94c29b7588c88abc83395/00001-1854530926.webp
https://files.tungsten.run/uploads/3ef1e557a8124ce68926fa2c4b257dc2/00002-1854530927.webp
Finished in 86.5 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: a castle of sand in a house of glass, high quality, 4K, <lora:add-detail-xl:1.5> Full negative prompt: 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:07<01:13, 7.38s/it] 18%|█▊ | 2/11 [00:15<01:10, 7.80s/it] 27%|██▋ | 3/11 [00:23<01:03, 7.96s/it] 36%|███▋ | 4/11 [00:32<00:57, 8.17s/it] 45%|████▌ | 5/11 [00:40<00:48, 8.16s/it] 55%|█████▍ | 6/11 [00:48<00:40, 8.09s/it] 64%|██████▎ | 7/11 [00:55<00:31, 7.93s/it] 73%|███████▎ | 8/11 [01:03<00:23, 7.84s/it] 82%|████████▏ | 9/11 [01:11<00:15, 7.76s/it] 91%|█████████ | 10/11 [01:16<00:07, 7.07s/it] 100%|██████████| 11/11 [01:18<00:00, 5.53s/it] 100%|██████████| 11/11 [01:18<00:00, 7.15s/it] Decoding latents in cuda:0... done in 3.34s Move latents to cpu... done in 0.04s Uploading outputs... Finished.