tungsten-logo
Sign In
Glowing Jellyfishes with Fantastique SDXL
fantastique-sdxl:v1.0
evevalentine2017
evevalentine2017
·
May 24
7
Input
prompt
Specify things to see in the output
a bunch of jellyfish lost inside an unknown ecosystem all in different colors, glowing, glimmers, sparkels
negative_prompt
Specify things to not see in the output
incomplete, multiple, duplicate, many, watermark, signature, title, copyright, artist name, condom, stray fingers, extra limbs
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
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.
60
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 Karras
samping_steps
Number of denoising steps
60
cfg_scale
Scale for classifier-free guidance
4.5
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/22f9f13ee6be420f9df1fc7cf163b721/00000-60.webp
https://files.tungsten.run/uploads/7a27c1a0da554fbdac3948138c61c234/00001-61.webp
https://files.tungsten.run/uploads/a8e5a8651f41425db06486d83d4ff1f0/00002-62.webp
Finished in 179.6 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: a bunch of jellyfish lost inside an unknown ecosystem all in different colors, glowing, glimmers, sparkels Full negative prompt: incomplete, multiple, duplicate, many, watermark, signature, title, copyright, artist name, condom, stray fingers, extra limbs 0%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:01<01:34, 1.60s/it] 3%|▎ | 2/60 [00:03<01:50, 1.90s/it] 5%|▌ | 3/60 [00:05<01:52, 1.97s/it] 7%|▋ | 4/60 [00:07<01:51, 1.99s/it] 8%|▊ | 5/60 [00:09<01:51, 2.03s/it] 10%|█ | 6/60 [00:11<01:50, 2.04s/it] 12%|█▏ | 7/60 [00:13<01:46, 2.01s/it] 13%|█▎ | 8/60 [00:15<01:42, 1.96s/it] 15%|█▌ | 9/60 [00:17<01:40, 1.97s/it] 17%|█▋ | 10/60 [00:19<01:38, 1.98s/it] 18%|█▊ | 11/60 [00:21<01:39, 2.03s/it] 20%|██ | 12/60 [00:23<01:38, 2.04s/it] 22%|██▏ | 13/60 [00:25<01:35, 2.03s/it] 23%|██▎ | 14/60 [00:28<01:36, 2.09s/it] 25%|██▌ | 15/60 [00:30<01:32, 2.05s/it] 27%|██▋ | 16/60 [00:32<01:31, 2.08s/it] 28%|██▊ | 17/60 [00:34<01:27, 2.02s/it] 30%|███ | 18/60 [00:36<01:22, 1.97s/it] 32%|███▏ | 19/60 [00:37<01:19, 1.93s/it] 33%|███▎ | 20/60 [00:39<01:17, 1.94s/it] 35%|███▌ | 21/60 [00:41<01:16, 1.95s/it] 37%|███▋ | 22/60 [00:43<01:16, 2.00s/it] 38%|███▊ | 23/60 [00:45<01:13, 1.98s/it] 40%|████ | 24/60 [00:47<01:12, 2.00s/it] 42%|████▏ | 25/60 [00:49<01:09, 1.97s/it] 43%|████▎ | 26/60 [00:51<01:07, 1.97s/it] 45%|████▌ | 27/60 [00:53<01:06, 2.01s/it] 47%|████▋ | 28/60 [00:55<01:04, 2.02s/it] 48%|████▊ | 29/60 [00:57<01:01, 1.97s/it] 50%|█████ | 30/60 [00:59<00:59, 1.98s/it] 52%|█████▏ | 31/60 [01:01<00:57, 1.97s/it] 53%|█████▎ | 32/60 [01:03<00:54, 1.96s/it] 55%|█████▌ | 33/60 [01:05<00:53, 1.97s/it] 57%|█████▋ | 34/60 [01:07<00:51, 1.99s/it] 58%|█████▊ | 35/60 [01:09<00:49, 1.99s/it] 60%|██████ | 36/60 [01:11<00:47, 1.98s/it] 62%|██████▏ | 37/60 [01:13<00:44, 1.94s/it] 63%|██████▎ | 38/60 [01:15<00:43, 1.96s/it] 65%|██████▌ | 39/60 [01:17<00:40, 1.94s/it] 67%|██████▋ | 40/60 [01:19<00:38, 1.95s/it] 68%|██████▊ | 41/60 [01:21<00:36, 1.93s/it] 70%|███████ | 42/60 [01:23<00:35, 1.95s/it] 72%|███████▏ | 43/60 [01:25<00:32, 1.92s/it] 73%|███████▎ | 44/60 [01:26<00:30, 1.91s/it] 75%|███████▌ | 45/60 [01:28<00:28, 1.92s/it] 77%|███████▋ | 46/60 [01:30<00:26, 1.90s/it] 78%|███████▊ | 47/60 [01:32<00:25, 1.93s/it] 80%|████████ | 48/60 [01:34<00:22, 1.89s/it] 82%|████████▏ | 49/60 [01:36<00:19, 1.78s/it] 83%|████████▎ | 50/60 [01:37<00:17, 1.78s/it] 85%|████████▌ | 51/60 [01:39<00:16, 1.78s/it] 87%|████████▋ | 52/60 [01:41<00:14, 1.81s/it] 88%|████████▊ | 53/60 [01:43<00:12, 1.80s/it] 90%|█████████ | 54/60 [01:45<00:10, 1.80s/it] 92%|█████████▏| 55/60 [01:46<00:08, 1.74s/it] 93%|█████████▎| 56/60 [01:48<00:07, 1.77s/it] 95%|█████████▌| 57/60 [01:50<00:05, 1.76s/it] 97%|█████████▋| 58/60 [01:51<00:03, 1.70s/it] 98%|█████████▊| 59/60 [01:52<00:01, 1.51s/it] 100%|██████████| 60/60 [01:53<00:00, 1.34s/it] 100%|██████████| 60/60 [01:53<00:00, 1.90s/it] Decoding latents in cuda:0... done in 1.74s Move latents to cpu... done in 0.02s 0: 640x480 1 face, 158.5ms Speed: 3.3ms preprocess, 158.5ms inference, 21.4ms postprocess per image at shape (1, 3, 640, 480)
prompt
Specify things to see in the output
a bunch of jellyfish lost inside an unknown ecosystem all in different colors, glowing, glimmers, sparkels
negative_prompt
Specify things to not see in the output
incomplete, multiple, duplicate, many, watermark, signature, title, copyright, artist name, condom, stray fingers, extra limbs
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
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.
60
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 Karras
samping_steps
Number of denoising steps
60
cfg_scale
Scale for classifier-free guidance
4.5
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/22f9f13ee6be420f9df1fc7cf163b721/00000-60.webp
https://files.tungsten.run/uploads/7a27c1a0da554fbdac3948138c61c234/00001-61.webp
https://files.tungsten.run/uploads/a8e5a8651f41425db06486d83d4ff1f0/00002-62.webp
Finished in 179.6 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: a bunch of jellyfish lost inside an unknown ecosystem all in different colors, glowing, glimmers, sparkels Full negative prompt: incomplete, multiple, duplicate, many, watermark, signature, title, copyright, artist name, condom, stray fingers, extra limbs 0%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:01<01:34, 1.60s/it] 3%|▎ | 2/60 [00:03<01:50, 1.90s/it] 5%|▌ | 3/60 [00:05<01:52, 1.97s/it] 7%|▋ | 4/60 [00:07<01:51, 1.99s/it] 8%|▊ | 5/60 [00:09<01:51, 2.03s/it] 10%|█ | 6/60 [00:11<01:50, 2.04s/it] 12%|█▏ | 7/60 [00:13<01:46, 2.01s/it] 13%|█▎ | 8/60 [00:15<01:42, 1.96s/it] 15%|█▌ | 9/60 [00:17<01:40, 1.97s/it] 17%|█▋ | 10/60 [00:19<01:38, 1.98s/it] 18%|█▊ | 11/60 [00:21<01:39, 2.03s/it] 20%|██ | 12/60 [00:23<01:38, 2.04s/it] 22%|██▏ | 13/60 [00:25<01:35, 2.03s/it] 23%|██▎ | 14/60 [00:28<01:36, 2.09s/it] 25%|██▌ | 15/60 [00:30<01:32, 2.05s/it] 27%|██▋ | 16/60 [00:32<01:31, 2.08s/it] 28%|██▊ | 17/60 [00:34<01:27, 2.02s/it] 30%|███ | 18/60 [00:36<01:22, 1.97s/it] 32%|███▏ | 19/60 [00:37<01:19, 1.93s/it] 33%|███▎ | 20/60 [00:39<01:17, 1.94s/it] 35%|███▌ | 21/60 [00:41<01:16, 1.95s/it] 37%|███▋ | 22/60 [00:43<01:16, 2.00s/it] 38%|███▊ | 23/60 [00:45<01:13, 1.98s/it] 40%|████ | 24/60 [00:47<01:12, 2.00s/it] 42%|████▏ | 25/60 [00:49<01:09, 1.97s/it] 43%|████▎ | 26/60 [00:51<01:07, 1.97s/it] 45%|████▌ | 27/60 [00:53<01:06, 2.01s/it] 47%|████▋ | 28/60 [00:55<01:04, 2.02s/it] 48%|████▊ | 29/60 [00:57<01:01, 1.97s/it] 50%|█████ | 30/60 [00:59<00:59, 1.98s/it] 52%|█████▏ | 31/60 [01:01<00:57, 1.97s/it] 53%|█████▎ | 32/60 [01:03<00:54, 1.96s/it] 55%|█████▌ | 33/60 [01:05<00:53, 1.97s/it] 57%|█████▋ | 34/60 [01:07<00:51, 1.99s/it] 58%|█████▊ | 35/60 [01:09<00:49, 1.99s/it] 60%|██████ | 36/60 [01:11<00:47, 1.98s/it] 62%|██████▏ | 37/60 [01:13<00:44, 1.94s/it] 63%|██████▎ | 38/60 [01:15<00:43, 1.96s/it] 65%|██████▌ | 39/60 [01:17<00:40, 1.94s/it] 67%|██████▋ | 40/60 [01:19<00:38, 1.95s/it] 68%|██████▊ | 41/60 [01:21<00:36, 1.93s/it] 70%|███████ | 42/60 [01:23<00:35, 1.95s/it] 72%|███████▏ | 43/60 [01:25<00:32, 1.92s/it] 73%|███████▎ | 44/60 [01:26<00:30, 1.91s/it] 75%|███████▌ | 45/60 [01:28<00:28, 1.92s/it] 77%|███████▋ | 46/60 [01:30<00:26, 1.90s/it] 78%|███████▊ | 47/60 [01:32<00:25, 1.93s/it] 80%|████████ | 48/60 [01:34<00:22, 1.89s/it] 82%|████████▏ | 49/60 [01:36<00:19, 1.78s/it] 83%|████████▎ | 50/60 [01:37<00:17, 1.78s/it] 85%|████████▌ | 51/60 [01:39<00:16, 1.78s/it] 87%|████████▋ | 52/60 [01:41<00:14, 1.81s/it] 88%|████████▊ | 53/60 [01:43<00:12, 1.80s/it] 90%|█████████ | 54/60 [01:45<00:10, 1.80s/it] 92%|█████████▏| 55/60 [01:46<00:08, 1.74s/it] 93%|█████████▎| 56/60 [01:48<00:07, 1.77s/it] 95%|█████████▌| 57/60 [01:50<00:05, 1.76s/it] 97%|█████████▋| 58/60 [01:51<00:03, 1.70s/it] 98%|█████████▊| 59/60 [01:52<00:01, 1.51s/it] 100%|██████████| 60/60 [01:53<00:00, 1.34s/it] 100%|██████████| 60/60 [01:53<00:00, 1.90s/it] Decoding latents in cuda:0... done in 1.74s Move latents to cpu... done in 0.02s 0: 640x480 1 face, 158.5ms Speed: 3.3ms preprocess, 158.5ms inference, 21.4ms postprocess per image at shape (1, 3, 640, 480)