tungsten-logo
Sign In
Ephemeral with CarDos XL
cardos-xl:v1.0
sparks
sparks
·
Feb 20
371
Input
prompt
Specify things to see in the output
ephemeral
negative_prompt
Specify things to not see in the output
worst quality, low quality
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1280
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
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.
3854938525
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
Restart
samping_steps
Number of denoising steps
26
cfg_scale
Scale for classifier-free guidance
7
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/811910cb67c0424eabac754e09fe29d2/00000-3854938525.webp
https://files.tungsten.run/uploads/85a71136d5b4413ca9a9ddc79cda4db2/00001-3854938526.webp
https://files.tungsten.run/uploads/34bacc5498f741b981bcd2df9eb7bbe1/00002-3854938527.webp
Finished in 97.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: ephemeral, <lora:add-detail-xl:1.0> Full negative prompt: worst quality, low quality 0%| | 0/26 [00:00<?, ?it/s] 4%|▍ | 1/26 [00:04<01:52, 4.50s/it] 8%|▊ | 2/26 [00:07<01:32, 3.86s/it] 12%|█▏ | 3/26 [00:11<01:24, 3.66s/it] 15%|█▌ | 4/26 [00:14<01:18, 3.57s/it] 19%|█▉ | 5/26 [00:18<01:13, 3.52s/it] 23%|██▎ | 6/26 [00:21<01:09, 3.50s/it] 27%|██▋ | 7/26 [00:25<01:06, 3.48s/it] 31%|███ | 8/26 [00:28<01:02, 3.47s/it] 35%|███▍ | 9/26 [00:32<00:58, 3.47s/it] 38%|███▊ | 10/26 [00:35<00:55, 3.47s/it] 42%|████▏ | 11/26 [00:38<00:52, 3.47s/it] 46%|████▌ | 12/26 [00:42<00:48, 3.47s/it] 50%|█████ | 13/26 [00:45<00:45, 3.48s/it] 54%|█████▍ | 14/26 [00:49<00:41, 3.48s/it] 58%|█████▊ | 15/26 [00:52<00:38, 3.49s/it] 62%|██████▏ | 16/26 [00:56<00:34, 3.49s/it] 65%|██████▌ | 17/26 [00:59<00:31, 3.50s/it] 69%|██████▉ | 18/26 [01:03<00:28, 3.50s/it] 73%|███████▎ | 19/26 [01:06<00:24, 3.51s/it] 77%|███████▋ | 20/26 [01:10<00:21, 3.52s/it] 81%|████████ | 21/26 [01:14<00:17, 3.53s/it] 85%|████████▍ | 22/26 [01:17<00:14, 3.54s/it] 88%|████████▊ | 23/26 [01:21<00:10, 3.55s/it] 92%|█████████▏| 24/26 [01:24<00:07, 3.55s/it] 96%|█████████▌| 25/26 [01:28<00:03, 3.55s/it] 100%|██████████| 26/26 [01:30<00:00, 3.02s/it] 100%|██████████| 26/26 [01:30<00:00, 3.46s/it] Decoding latents in cuda:0... done in 3.16s Move latents to cpu... done in 0.04s Uploading outputs... Finished.
prompt
Specify things to see in the output
ephemeral
negative_prompt
Specify things to not see in the output
worst quality, low quality
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1280
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
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.
3854938525
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
Restart
samping_steps
Number of denoising steps
26
cfg_scale
Scale for classifier-free guidance
7
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/811910cb67c0424eabac754e09fe29d2/00000-3854938525.webp
https://files.tungsten.run/uploads/85a71136d5b4413ca9a9ddc79cda4db2/00001-3854938526.webp
https://files.tungsten.run/uploads/34bacc5498f741b981bcd2df9eb7bbe1/00002-3854938527.webp
Finished in 97.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: ephemeral, <lora:add-detail-xl:1.0> Full negative prompt: worst quality, low quality 0%| | 0/26 [00:00<?, ?it/s] 4%|▍ | 1/26 [00:04<01:52, 4.50s/it] 8%|▊ | 2/26 [00:07<01:32, 3.86s/it] 12%|█▏ | 3/26 [00:11<01:24, 3.66s/it] 15%|█▌ | 4/26 [00:14<01:18, 3.57s/it] 19%|█▉ | 5/26 [00:18<01:13, 3.52s/it] 23%|██▎ | 6/26 [00:21<01:09, 3.50s/it] 27%|██▋ | 7/26 [00:25<01:06, 3.48s/it] 31%|███ | 8/26 [00:28<01:02, 3.47s/it] 35%|███▍ | 9/26 [00:32<00:58, 3.47s/it] 38%|███▊ | 10/26 [00:35<00:55, 3.47s/it] 42%|████▏ | 11/26 [00:38<00:52, 3.47s/it] 46%|████▌ | 12/26 [00:42<00:48, 3.47s/it] 50%|█████ | 13/26 [00:45<00:45, 3.48s/it] 54%|█████▍ | 14/26 [00:49<00:41, 3.48s/it] 58%|█████▊ | 15/26 [00:52<00:38, 3.49s/it] 62%|██████▏ | 16/26 [00:56<00:34, 3.49s/it] 65%|██████▌ | 17/26 [00:59<00:31, 3.50s/it] 69%|██████▉ | 18/26 [01:03<00:28, 3.50s/it] 73%|███████▎ | 19/26 [01:06<00:24, 3.51s/it] 77%|███████▋ | 20/26 [01:10<00:21, 3.52s/it] 81%|████████ | 21/26 [01:14<00:17, 3.53s/it] 85%|████████▍ | 22/26 [01:17<00:14, 3.54s/it] 88%|████████▊ | 23/26 [01:21<00:10, 3.55s/it] 92%|█████████▏| 24/26 [01:24<00:07, 3.55s/it] 96%|█████████▌| 25/26 [01:28<00:03, 3.55s/it] 100%|██████████| 26/26 [01:30<00:00, 3.02s/it] 100%|██████████| 26/26 [01:30<00:00, 3.46s/it] Decoding latents in cuda:0... done in 3.16s Move latents to cpu... done in 0.04s Uploading outputs... Finished.