mermaid
Input
prompt
Input prompt
(dark magic), (grim), mermaid, masterpiece, best quality, (intricate details), dreamy, perfect eyes, dark pupils, magnificent, ethereal, volumetric lighting, lightroom, ((cinematic)), raytracing, subsurface scattering, face focus, ((full body))
negative_prompt
Specify things to not see in the output
width
Output image width
1000
height
Output image height
1460
num_outputs
Number of output images
1
seed
Random seed. Set as -1 to randomize output.
4277336656
reference_image
Image that the output should be similar to
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
35
cfg_scale
Scale for classifier-free guidance
6
clip_skip
Whether to ignore the last layer of CLIP network or not
false
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/ddaaf17ac72841f89c73b9113d870251/tmpi7dxfdgn.png
Finished in 44.5 seconds
v2.1-base-v2.2: Pulling from mjpyeon/zavy-chroma-xl a378f10b3218: Already exists c11bdfacfd25: Already exists 6846b6f09fa6: Already exists 9b7602d2af9e: Already exists 7df05b724c5b: Already exists f9ed3aff44c6: Already exists 932434c42e70: Already exists 63931b20ac09: Already exists a9170ce52a36: Already exists e23914353609: Already exists 4bde53708b26: Already exists a7c418bcea5f: Already exists 8915fc22d7d8: Already exists 63223e321fb8: Already exists 4f4fb700ef54: Already exists d70ee3dbf97c: Pull complete 0a5510ef912a: Pull complete Setting up the model... Processing... Full prompt: (dark magic), (grim), mermaid, masterpiece, best quality, (intricate details), dreamy, perfect eyes, dark pupils, magnificent, ethereal, volumetric lighting, lightroom, ((cinematic)), raytracing, subsurface scattering, face focus, ((full body)) Full negative prompt: (deformed:1.3), (distorted:1.3), (disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, tattoo, watermark, text, anime, illustration, sketch, 3d, vector art, cartoon, painting 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:01<00:35, 1.03s/it] 6%|▌ | 2/35 [00:02<00:37, 1.15s/it] 9%|▊ | 3/35 [00:03<00:40, 1.26s/it] 11%|█▏ | 4/35 [00:04<00:39, 1.27s/it] 14%|█▍ | 5/35 [00:06<00:38, 1.27s/it] 17%|█▋ | 6/35 [00:07<00:37, 1.28s/it] 20%|██ | 7/35 [00:08<00:35, 1.28s/it] 23%|██▎ | 8/35 [00:10<00:34, 1.27s/it] 26%|██▌ | 9/35 [00:11<00:32, 1.26s/it] 29%|██▊ | 10/35 [00:12<00:31, 1.28s/it] 31%|███▏ | 11/35 [00:13<00:30, 1.28s/it] 34%|███▍ | 12/35 [00:15<00:29, 1.26s/it] 37%|███▋ | 13/35 [00:16<00:28, 1.29s/it] 40%|████ | 14/35 [00:17<00:25, 1.23s/it] 43%|████▎ | 15/35 [00:18<00:24, 1.22s/it] 46%|████▌ | 16/35 [00:19<00:23, 1.22s/it] 49%|████▊ | 17/35 [00:21<00:22, 1.24s/it] 51%|█████▏ | 18/35 [00:22<00:21, 1.25s/it] 54%|█████▍ | 19/35 [00:23<00:19, 1.24s/it] 57%|█████▋ | 20/35 [00:24<00:18, 1.22s/it] 60%|██████ | 21/35 [00:26<00:17, 1.22s/it] 63%|██████▎ | 22/35 [00:27<00:15, 1.18s/it] 66%|██████▌ | 23/35 [00:28<00:14, 1.19s/it] 69%|██████▊ | 24/35 [00:29<00:13, 1.20s/it] 71%|███████▏ | 25/35 [00:30<00:11, 1.20s/it] 74%|███████▍ | 26/35 [00:32<00:10, 1.22s/it] 77%|███████▋ | 27/35 [00:33<00:09, 1.20s/it] 80%|████████ | 28/35 [00:34<00:08, 1.19s/it] 83%|████████▎ | 29/35 [00:35<00:06, 1.15s/it] 86%|████████▌ | 30/35 [00:36<00:05, 1.15s/it] 89%|████████▊ | 31/35 [00:37<00:04, 1.14s/it] 91%|█████████▏| 32/35 [00:38<00:03, 1.10s/it] 94%|█████████▍| 33/35 [00:39<00:02, 1.07s/it] 97%|█████████▋| 34/35 [00:40<00:00, 1.04it/s] 100%|██████████| 35/35 [00:41<00:00, 1.17it/s] 100%|██████████| 35/35 [00:41<00:00, 1.17s/it] Decoding latents in cuda:0... done in 1.15s Move latents to cpu... done in 0.01s Finished.
prompt
Input prompt
(dark magic), (grim), mermaid, masterpiece, best quality, (intricate details), dreamy, perfect eyes, dark pupils, magnificent, ethereal, volumetric lighting, lightroom, ((cinematic)), raytracing, subsurface scattering, face focus, ((full body))
negative_prompt
Specify things to not see in the output
width
Output image width
1000
height
Output image height
1460
num_outputs
Number of output images
1
seed
Random seed. Set as -1 to randomize output.
4277336656
reference_image
Image that the output should be similar to
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
35
cfg_scale
Scale for classifier-free guidance
6
clip_skip
Whether to ignore the last layer of CLIP network or not
false
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/ddaaf17ac72841f89c73b9113d870251/tmpi7dxfdgn.png
Finished in 44.5 seconds
v2.1-base-v2.2: Pulling from mjpyeon/zavy-chroma-xl a378f10b3218: Already exists c11bdfacfd25: Already exists 6846b6f09fa6: Already exists 9b7602d2af9e: Already exists 7df05b724c5b: Already exists f9ed3aff44c6: Already exists 932434c42e70: Already exists 63931b20ac09: Already exists a9170ce52a36: Already exists e23914353609: Already exists 4bde53708b26: Already exists a7c418bcea5f: Already exists 8915fc22d7d8: Already exists 63223e321fb8: Already exists 4f4fb700ef54: Already exists d70ee3dbf97c: Pull complete 0a5510ef912a: Pull complete Setting up the model... Processing... Full prompt: (dark magic), (grim), mermaid, masterpiece, best quality, (intricate details), dreamy, perfect eyes, dark pupils, magnificent, ethereal, volumetric lighting, lightroom, ((cinematic)), raytracing, subsurface scattering, face focus, ((full body)) Full negative prompt: (deformed:1.3), (distorted:1.3), (disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, tattoo, watermark, text, anime, illustration, sketch, 3d, vector art, cartoon, painting 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:01<00:35, 1.03s/it] 6%|▌ | 2/35 [00:02<00:37, 1.15s/it] 9%|▊ | 3/35 [00:03<00:40, 1.26s/it] 11%|█▏ | 4/35 [00:04<00:39, 1.27s/it] 14%|█▍ | 5/35 [00:06<00:38, 1.27s/it] 17%|█▋ | 6/35 [00:07<00:37, 1.28s/it] 20%|██ | 7/35 [00:08<00:35, 1.28s/it] 23%|██▎ | 8/35 [00:10<00:34, 1.27s/it] 26%|██▌ | 9/35 [00:11<00:32, 1.26s/it] 29%|██▊ | 10/35 [00:12<00:31, 1.28s/it] 31%|███▏ | 11/35 [00:13<00:30, 1.28s/it] 34%|███▍ | 12/35 [00:15<00:29, 1.26s/it] 37%|███▋ | 13/35 [00:16<00:28, 1.29s/it] 40%|████ | 14/35 [00:17<00:25, 1.23s/it] 43%|████▎ | 15/35 [00:18<00:24, 1.22s/it] 46%|████▌ | 16/35 [00:19<00:23, 1.22s/it] 49%|████▊ | 17/35 [00:21<00:22, 1.24s/it] 51%|█████▏ | 18/35 [00:22<00:21, 1.25s/it] 54%|█████▍ | 19/35 [00:23<00:19, 1.24s/it] 57%|█████▋ | 20/35 [00:24<00:18, 1.22s/it] 60%|██████ | 21/35 [00:26<00:17, 1.22s/it] 63%|██████▎ | 22/35 [00:27<00:15, 1.18s/it] 66%|██████▌ | 23/35 [00:28<00:14, 1.19s/it] 69%|██████▊ | 24/35 [00:29<00:13, 1.20s/it] 71%|███████▏ | 25/35 [00:30<00:11, 1.20s/it] 74%|███████▍ | 26/35 [00:32<00:10, 1.22s/it] 77%|███████▋ | 27/35 [00:33<00:09, 1.20s/it] 80%|████████ | 28/35 [00:34<00:08, 1.19s/it] 83%|████████▎ | 29/35 [00:35<00:06, 1.15s/it] 86%|████████▌ | 30/35 [00:36<00:05, 1.15s/it] 89%|████████▊ | 31/35 [00:37<00:04, 1.14s/it] 91%|█████████▏| 32/35 [00:38<00:03, 1.10s/it] 94%|█████████▍| 33/35 [00:39<00:02, 1.07s/it] 97%|█████████▋| 34/35 [00:40<00:00, 1.04it/s] 100%|██████████| 35/35 [00:41<00:00, 1.17it/s] 100%|██████████| 35/35 [00:41<00:00, 1.17s/it] Decoding latents in cuda:0... done in 1.15s Move latents to cpu... done in 0.01s Finished.