Sunken Ships with Digital Dream XL
Input
prompt
Specify things to see in the output
A deep underwater scene with a sunken pirate ship, surrounded by ais-darkpartz that move like ghostly sea creatures in the dark waters
negative_prompt
Specify things to not see in the output
desaturated, old, baggy eyes, tired, simple background, large breasts, clones, twins, nipples, nsfw
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
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
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.
993554368
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++ 3M SDE Exponential
samping_steps
Number of denoising steps
80
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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/67d4dd5fb23a416ba86b8b46be9cc3bf/00000-993554368.webp
https://files.tungsten.run/uploads/e732d72f44df4438aca40c4d5afe48b4/00001-993554369.webp
https://files.tungsten.run/uploads/70fd0a4671e84b2d93424194e2265582/00002-993554370.webp
Finished in 157.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: A deep underwater scene with a sunken pirate ship, surrounded by ais-darkpartz that move like ghostly sea creatures in the dark waters Full negative prompt: desaturated, old, baggy eyes, tired, simple background, large breasts, clones, twins, nipples, nsfw 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:01<02:06, 1.60s/it] 2%|▎ | 2/80 [00:03<02:25, 1.87s/it] 4%|▍ | 3/80 [00:05<02:30, 1.96s/it] 5%|▌ | 4/80 [00:07<02:34, 2.03s/it] 6%|▋ | 5/80 [00:09<02:34, 2.06s/it] 8%|▊ | 6/80 [00:11<02:29, 2.02s/it] 9%|▉ | 7/80 [00:13<02:24, 1.98s/it] 10%|█ | 8/80 [00:15<02:23, 2.00s/it] 11%|█▏ | 9/80 [00:17<02:25, 2.05s/it] 12%|█▎ | 10/80 [00:20<02:23, 2.05s/it] 14%|█▍ | 11/80 [00:22<02:21, 2.06s/it] 15%|█▌ | 12/80 [00:24<02:17, 2.02s/it] 16%|█▋ | 13/80 [00:26<02:14, 2.00s/it] 18%|█▊ | 14/80 [00:28<02:12, 2.01s/it] 19%|█▉ | 15/80 [00:29<02:09, 1.99s/it] 20%|██ | 16/80 [00:31<02:07, 1.99s/it] 21%|██▏ | 17/80 [00:33<02:05, 1.99s/it] 22%|██▎ | 18/80 [00:36<02:05, 2.03s/it] 24%|██▍ | 19/80 [00:38<02:03, 2.02s/it] 25%|██▌ | 20/80 [00:40<02:01, 2.02s/it] 26%|██▋ | 21/80 [00:42<01:57, 1.99s/it] 28%|██▊ | 22/80 [00:44<01:56, 2.00s/it] 29%|██▉ | 23/80 [00:46<01:55, 2.02s/it] 30%|███ | 24/80 [00:48<01:52, 2.01s/it] 31%|███▏ | 25/80 [00:50<01:49, 1.98s/it] 32%|███▎ | 26/80 [00:52<01:47, 2.00s/it] 34%|███▍ | 27/80 [00:54<01:45, 2.00s/it] 35%|███▌ | 28/80 [00:56<01:42, 1.98s/it] 36%|███▋ | 29/80 [00:57<01:41, 1.98s/it] 38%|███▊ | 30/80 [00:59<01:34, 1.90s/it] 39%|███▉ | 31/80 [01:01<01:33, 1.90s/it] 40%|████ | 32/80 [01:03<01:29, 1.87s/it] 41%|████▏ | 33/80 [01:05<01:29, 1.90s/it] 42%|████▎ | 34/80 [01:07<01:26, 1.89s/it] 44%|████▍ | 35/80 [01:09<01:24, 1.88s/it] 45%|████▌ | 36/80 [01:11<01:24, 1.92s/it] 46%|████▋ | 37/80 [01:12<01:20, 1.87s/it] 48%|████▊ | 38/80 [01:14<01:18, 1.86s/it] 49%|████▉ | 39/80 [01:16<01:18, 1.92s/it] 50%|█████ | 40/80 [01:18<01:16, 1.90s/it] 51%|█████▏ | 41/80 [01:20<01:13, 1.88s/it] 52%|█████▎ | 42/80 [01:22<01:12, 1.90s/it] 54%|█████▍ | 43/80 [01:24<01:08, 1.86s/it] 55%|█████▌ | 44/80 [01:26<01:08, 1.91s/it] 56%|█████▋ | 45/80 [01:28<01:06, 1.89s/it] 57%|█████▊ | 46/80 [01:29<01:04, 1.91s/it] 59%|█████▉ | 47/80 [01:31<01:01, 1.88s/it] 60%|██████ | 48/80 [01:33<01:01, 1.91s/it] 61%|██████▏ | 49/80 [01:35<00:58, 1.89s/it] 62%|██████▎ | 50/80 [01:37<00:56, 1.88s/it] 64%|██████▍ | 51/80 [01:39<00:54, 1.89s/it] 65%|██████▌ | 52/80 [01:41<00:53, 1.92s/it] 66%|██████▋ | 53/80 [01:42<00:49, 1.83s/it] 68%|██████▊ | 54/80 [01:44<00:45, 1.77s/it] 69%|██████▉ | 55/80 [01:46<00:43, 1.75s/it] 70%|███████ | 56/80 [01:48<00:43, 1.83s/it] 71%|███████▏ | 57/80 [01:50<00:41, 1.81s/it] 72%|███████▎ | 58/80 [01:51<00:39, 1.79s/it] 74%|███████▍ | 59/80 [01:53<00:36, 1.76s/it] 75%|███████▌ | 60/80 [01:55<00:35, 1.78s/it] 76%|███████▋ | 61/80 [01:57<00:33, 1.77s/it] 78%|███████▊ | 62/80 [01:58<00:31, 1.73s/it] 79%|███████▉ | 63/80 [02:00<00:30, 1.77s/it] 80%|████████ | 64/80 [02:02<00:27, 1.73s/it] 81%|████████▏ | 65/80 [02:03<00:25, 1.69s/it] 82%|████████▎ | 66/80 [02:05<00:24, 1.76s/it] 84%|████████▍ | 67/80 [02:07<00:22, 1.75s/it] 85%|████████▌ | 68/80 [02:09<00:21, 1.76s/it] 86%|████████▋ | 69/80 [02:10<00:18, 1.70s/it] 88%|████████▊ | 70/80 [02:12<00:17, 1.75s/it] 89%|████████▉ | 71/80 [02:14<00:15, 1.69s/it] 90%|█████████ | 72/80 [02:15<00:12, 1.62s/it] 91%|█████████▏| 73/80 [02:17<00:11, 1.68s/it] 92%|█████████▎| 74/80 [02:19<00:09, 1.62s/it] 94%|█████████▍| 75/80 [02:20<00:08, 1.65s/it] 95%|█████████▌| 76/80 [02:22<00:06, 1.63s/it] 96%|█████████▋| 77/80 [02:24<00:04, 1.66s/it] 98%|█████████▊| 78/80 [02:25<00:03, 1.63s/it] 99%|█████████▉| 79/80 [02:26<00:01, 1.46s/it] 100%|██████████| 80/80 [02:27<00:00, 1.30s/it] 100%|██████████| 80/80 [02:27<00:00, 1.85s/it] Decoding latents in cuda:0... done in 1.73s Move latents to cpu... done in 0.02s 0: 480x640 (no detections), 178.2ms Speed: 2.6ms preprocess, 178.2ms inference, 1.0ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 480x640 (no detections), 8.1ms Speed: 2.4ms preprocess, 8.1ms inference, 0.7ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 480x640 (no detections), 7.8ms Speed: 2.3ms preprocess, 7.8ms inference, 1.0ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. Uploading outputs... Finished.
prompt
Specify things to see in the output
A deep underwater scene with a sunken pirate ship, surrounded by ais-darkpartz that move like ghostly sea creatures in the dark waters
negative_prompt
Specify things to not see in the output
desaturated, old, baggy eyes, tired, simple background, large breasts, clones, twins, nipples, nsfw
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
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
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.
993554368
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++ 3M SDE Exponential
samping_steps
Number of denoising steps
80
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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/67d4dd5fb23a416ba86b8b46be9cc3bf/00000-993554368.webp
https://files.tungsten.run/uploads/e732d72f44df4438aca40c4d5afe48b4/00001-993554369.webp
https://files.tungsten.run/uploads/70fd0a4671e84b2d93424194e2265582/00002-993554370.webp
Finished in 157.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: A deep underwater scene with a sunken pirate ship, surrounded by ais-darkpartz that move like ghostly sea creatures in the dark waters Full negative prompt: desaturated, old, baggy eyes, tired, simple background, large breasts, clones, twins, nipples, nsfw 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:01<02:06, 1.60s/it] 2%|▎ | 2/80 [00:03<02:25, 1.87s/it] 4%|▍ | 3/80 [00:05<02:30, 1.96s/it] 5%|▌ | 4/80 [00:07<02:34, 2.03s/it] 6%|▋ | 5/80 [00:09<02:34, 2.06s/it] 8%|▊ | 6/80 [00:11<02:29, 2.02s/it] 9%|▉ | 7/80 [00:13<02:24, 1.98s/it] 10%|█ | 8/80 [00:15<02:23, 2.00s/it] 11%|█▏ | 9/80 [00:17<02:25, 2.05s/it] 12%|█▎ | 10/80 [00:20<02:23, 2.05s/it] 14%|█▍ | 11/80 [00:22<02:21, 2.06s/it] 15%|█▌ | 12/80 [00:24<02:17, 2.02s/it] 16%|█▋ | 13/80 [00:26<02:14, 2.00s/it] 18%|█▊ | 14/80 [00:28<02:12, 2.01s/it] 19%|█▉ | 15/80 [00:29<02:09, 1.99s/it] 20%|██ | 16/80 [00:31<02:07, 1.99s/it] 21%|██▏ | 17/80 [00:33<02:05, 1.99s/it] 22%|██▎ | 18/80 [00:36<02:05, 2.03s/it] 24%|██▍ | 19/80 [00:38<02:03, 2.02s/it] 25%|██▌ | 20/80 [00:40<02:01, 2.02s/it] 26%|██▋ | 21/80 [00:42<01:57, 1.99s/it] 28%|██▊ | 22/80 [00:44<01:56, 2.00s/it] 29%|██▉ | 23/80 [00:46<01:55, 2.02s/it] 30%|███ | 24/80 [00:48<01:52, 2.01s/it] 31%|███▏ | 25/80 [00:50<01:49, 1.98s/it] 32%|███▎ | 26/80 [00:52<01:47, 2.00s/it] 34%|███▍ | 27/80 [00:54<01:45, 2.00s/it] 35%|███▌ | 28/80 [00:56<01:42, 1.98s/it] 36%|███▋ | 29/80 [00:57<01:41, 1.98s/it] 38%|███▊ | 30/80 [00:59<01:34, 1.90s/it] 39%|███▉ | 31/80 [01:01<01:33, 1.90s/it] 40%|████ | 32/80 [01:03<01:29, 1.87s/it] 41%|████▏ | 33/80 [01:05<01:29, 1.90s/it] 42%|████▎ | 34/80 [01:07<01:26, 1.89s/it] 44%|████▍ | 35/80 [01:09<01:24, 1.88s/it] 45%|████▌ | 36/80 [01:11<01:24, 1.92s/it] 46%|████▋ | 37/80 [01:12<01:20, 1.87s/it] 48%|████▊ | 38/80 [01:14<01:18, 1.86s/it] 49%|████▉ | 39/80 [01:16<01:18, 1.92s/it] 50%|█████ | 40/80 [01:18<01:16, 1.90s/it] 51%|█████▏ | 41/80 [01:20<01:13, 1.88s/it] 52%|█████▎ | 42/80 [01:22<01:12, 1.90s/it] 54%|█████▍ | 43/80 [01:24<01:08, 1.86s/it] 55%|█████▌ | 44/80 [01:26<01:08, 1.91s/it] 56%|█████▋ | 45/80 [01:28<01:06, 1.89s/it] 57%|█████▊ | 46/80 [01:29<01:04, 1.91s/it] 59%|█████▉ | 47/80 [01:31<01:01, 1.88s/it] 60%|██████ | 48/80 [01:33<01:01, 1.91s/it] 61%|██████▏ | 49/80 [01:35<00:58, 1.89s/it] 62%|██████▎ | 50/80 [01:37<00:56, 1.88s/it] 64%|██████▍ | 51/80 [01:39<00:54, 1.89s/it] 65%|██████▌ | 52/80 [01:41<00:53, 1.92s/it] 66%|██████▋ | 53/80 [01:42<00:49, 1.83s/it] 68%|██████▊ | 54/80 [01:44<00:45, 1.77s/it] 69%|██████▉ | 55/80 [01:46<00:43, 1.75s/it] 70%|███████ | 56/80 [01:48<00:43, 1.83s/it] 71%|███████▏ | 57/80 [01:50<00:41, 1.81s/it] 72%|███████▎ | 58/80 [01:51<00:39, 1.79s/it] 74%|███████▍ | 59/80 [01:53<00:36, 1.76s/it] 75%|███████▌ | 60/80 [01:55<00:35, 1.78s/it] 76%|███████▋ | 61/80 [01:57<00:33, 1.77s/it] 78%|███████▊ | 62/80 [01:58<00:31, 1.73s/it] 79%|███████▉ | 63/80 [02:00<00:30, 1.77s/it] 80%|████████ | 64/80 [02:02<00:27, 1.73s/it] 81%|████████▏ | 65/80 [02:03<00:25, 1.69s/it] 82%|████████▎ | 66/80 [02:05<00:24, 1.76s/it] 84%|████████▍ | 67/80 [02:07<00:22, 1.75s/it] 85%|████████▌ | 68/80 [02:09<00:21, 1.76s/it] 86%|████████▋ | 69/80 [02:10<00:18, 1.70s/it] 88%|████████▊ | 70/80 [02:12<00:17, 1.75s/it] 89%|████████▉ | 71/80 [02:14<00:15, 1.69s/it] 90%|█████████ | 72/80 [02:15<00:12, 1.62s/it] 91%|█████████▏| 73/80 [02:17<00:11, 1.68s/it] 92%|█████████▎| 74/80 [02:19<00:09, 1.62s/it] 94%|█████████▍| 75/80 [02:20<00:08, 1.65s/it] 95%|█████████▌| 76/80 [02:22<00:06, 1.63s/it] 96%|█████████▋| 77/80 [02:24<00:04, 1.66s/it] 98%|█████████▊| 78/80 [02:25<00:03, 1.63s/it] 99%|█████████▉| 79/80 [02:26<00:01, 1.46s/it] 100%|██████████| 80/80 [02:27<00:00, 1.30s/it] 100%|██████████| 80/80 [02:27<00:00, 1.85s/it] Decoding latents in cuda:0... done in 1.73s Move latents to cpu... done in 0.02s 0: 480x640 (no detections), 178.2ms Speed: 2.6ms preprocess, 178.2ms inference, 1.0ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 480x640 (no detections), 8.1ms Speed: 2.4ms preprocess, 8.1ms inference, 0.7ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 480x640 (no detections), 7.8ms Speed: 2.3ms preprocess, 7.8ms inference, 1.0ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. Uploading outputs... Finished.