tungsten-logo
Sign In
Tiny Blue Ghost with Aurora SDXL
aurora-sdxl:v1.0
evevalentine2017
evevalentine2017
·
Mar 15
351
Input
prompt
Specify things to see in the output
Envision a whimsical fantasy world where a colossal, cute, blushed, and irresistibly translucent transparent ethereal very tiny blue ghost takes center stage. Picture the ghost with a mischievous charm, its surface reflecting a soft glow. Amidst its translucent body, an unexpected sight catches the eye, blue forget me not flowers suspended within its stomach. This charming and slightly perplexing scene invites you to explore the magical and endearing mysteries of this fantastical realm, where even the most mundane objects take on a delightful and surreal twist within the embrace of the giant, lovable slime. very detailed, hd, RAW photograph, masterpiece, top quality, best quality, official art,highest detailed, atmospheric lighting, cinematic composition, complex multiple subjects, 4k HDR, vibrant, highly detailed, Leica Q2 with Summilux 35mm f/1.2 ASPH, Ultra High Resolution, wallpaper, 8K, Rich texture details, hyper detailed, detailed eyes, detailed background, dramatic angle, epic composition, high quality , (8k, RAW photo, highest quality), hyperrealistic,
negative_prompt
Specify things to not see in the output
Bra, Unrealistic AND fake, anime, pixar, ugly, bad art, imperfections, cartoony, malformed, noisy, open mouth, (blur), (guassian blur), paintings, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast text, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast
num_outputs
Number of output images
3
width
Output image width
1024
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.
1714589370
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
samping_steps
Number of denoising steps
50
cfg_scale
Scale for classifier-free guidance
7.5
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/65cc351212e2438f93f76818e91db546/00000-1714589370.webp
https://files.tungsten.run/uploads/a47ad21b424441cbb25ae4004ce933b7/00001-1714589371.webp
https://files.tungsten.run/uploads/87a5e05904d140ce8f5d8d09879f9e09/00002-1714589372.webp
Finished in 265.9 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: Envision a whimsical fantasy world where a colossal, cute, blushed, and irresistibly translucent transparent ethereal very tiny blue ghost takes center stage. Picture the ghost with a mischievous charm, its surface reflecting a soft glow. Amidst its translucent body, an unexpected sight catches the eye, blue forget me not flowers suspended within its stomach. This charming and slightly perplexing scene invites you to explore the magical and endearing mysteries of this fantastical realm, where even the most mundane objects take on a delightful and surreal twist within the embrace of the giant, lovable slime. very detailed, hd, RAW photograph, masterpiece, top quality, best quality, official art,highest detailed, atmospheric lighting, cinematic composition, complex multiple subjects, 4k HDR, vibrant, highly detailed, Leica Q2 with Summilux 35mm f/1.2 ASPH, Ultra High Resolution, wallpaper, 8K, Rich texture details, hyper detailed, detailed eyes, detailed background, dramatic angle, epic composition, high quality , (8k, RAW photo, highest quality), hyperrealistic, Full negative prompt: Bra, Unrealistic AND fake, anime, pixar, ugly, bad art, imperfections, cartoony, malformed, noisy, open mouth, (blur), (guassian blur), paintings, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast text, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:04<03:30, 4.29s/it] 4%|▍ | 2/50 [00:09<03:56, 4.94s/it] 6%|▌ | 3/50 [00:15<04:15, 5.43s/it] 8%|▊ | 4/50 [00:21<04:12, 5.49s/it] 10%|█ | 5/50 [00:27<04:12, 5.62s/it] 12%|█▏ | 6/50 [00:33<04:12, 5.75s/it] 14%|█▍ | 7/50 [00:39<04:11, 5.84s/it] 16%|█▌ | 8/50 [00:44<04:03, 5.81s/it] 18%|█▊ | 9/50 [00:50<03:56, 5.77s/it] 20%|██ | 10/50 [00:56<03:48, 5.70s/it] 22%|██▏ | 11/50 [01:02<03:50, 5.90s/it] 24%|██▍ | 12/50 [01:08<03:43, 5.88s/it] 26%|██▌ | 13/50 [01:13<03:32, 5.74s/it] 28%|██▊ | 14/50 [01:19<03:30, 5.84s/it] 30%|███ | 15/50 [01:25<03:22, 5.80s/it] 32%|███▏ | 16/50 [01:31<03:15, 5.74s/it] 34%|███▍ | 17/50 [01:35<03:00, 5.46s/it] 36%|███▌ | 18/50 [01:41<02:55, 5.48s/it] 38%|███▊ | 19/50 [01:46<02:50, 5.50s/it] 40%|████ | 20/50 [01:52<02:44, 5.49s/it] 42%|████▏ | 21/50 [01:57<02:34, 5.32s/it] 44%|████▍ | 22/50 [02:02<02:29, 5.33s/it] 46%|████▌ | 23/50 [02:08<02:26, 5.43s/it] 48%|████▊ | 24/50 [02:13<02:20, 5.42s/it] 50%|█████ | 25/50 [02:18<02:11, 5.25s/it] 52%|█████▏ | 26/50 [02:23<02:05, 5.24s/it] 54%|█████▍ | 27/50 [02:29<02:01, 5.28s/it] 56%|█████▌ | 28/50 [02:34<01:57, 5.34s/it] 58%|█████▊ | 29/50 [02:39<01:45, 5.04s/it] 60%|██████ | 30/50 [02:43<01:37, 4.86s/it] 62%|██████▏ | 31/50 [02:47<01:28, 4.67s/it] 64%|██████▍ | 32/50 [02:52<01:25, 4.76s/it] 66%|██████▌ | 33/50 [02:56<01:17, 4.56s/it] 68%|██████▊ | 34/50 [03:02<01:16, 4.77s/it] 70%|███████ | 35/50 [03:07<01:15, 5.04s/it] 72%|███████▏ | 36/50 [03:12<01:08, 4.88s/it] 74%|███████▍ | 37/50 [03:16<01:02, 4.78s/it] 76%|███████▌ | 38/50 [03:21<00:56, 4.73s/it] 78%|███████▊ | 39/50 [03:25<00:51, 4.64s/it] 80%|████████ | 40/50 [03:31<00:48, 4.87s/it] 82%|████████▏ | 41/50 [03:35<00:42, 4.74s/it] 84%|████████▍ | 42/50 [03:40<00:37, 4.70s/it] 86%|████████▌ | 43/50 [03:44<00:32, 4.67s/it] 88%|████████▊ | 44/50 [03:49<00:27, 4.65s/it] 90%|█████████ | 45/50 [03:54<00:24, 4.85s/it] 92%|█████████▏| 46/50 [04:00<00:19, 4.96s/it] 94%|█████████▍| 47/50 [04:04<00:14, 4.82s/it] 96%|█████████▌| 48/50 [04:09<00:09, 4.84s/it] 98%|█████████▊| 49/50 [04:13<00:04, 4.60s/it] 100%|██████████| 50/50 [04:14<00:00, 3.64s/it] 100%|██████████| 50/50 [04:14<00:00, 5.10s/it] Decoding latents in cuda:0... done in 2.38s Move latents to cpu... done in 0.03s 0: 640x640 (no detections), 8.3ms Speed: 3.9ms preprocess, 8.3ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 7.8ms Speed: 3.1ms preprocess, 7.8ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 (no detections), 8.5ms Speed: 3.1ms preprocess, 8.5ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. Uploading outputs... Finished.
prompt
Specify things to see in the output
Envision a whimsical fantasy world where a colossal, cute, blushed, and irresistibly translucent transparent ethereal very tiny blue ghost takes center stage. Picture the ghost with a mischievous charm, its surface reflecting a soft glow. Amidst its translucent body, an unexpected sight catches the eye, blue forget me not flowers suspended within its stomach. This charming and slightly perplexing scene invites you to explore the magical and endearing mysteries of this fantastical realm, where even the most mundane objects take on a delightful and surreal twist within the embrace of the giant, lovable slime. very detailed, hd, RAW photograph, masterpiece, top quality, best quality, official art,highest detailed, atmospheric lighting, cinematic composition, complex multiple subjects, 4k HDR, vibrant, highly detailed, Leica Q2 with Summilux 35mm f/1.2 ASPH, Ultra High Resolution, wallpaper, 8K, Rich texture details, hyper detailed, detailed eyes, detailed background, dramatic angle, epic composition, high quality , (8k, RAW photo, highest quality), hyperrealistic,
negative_prompt
Specify things to not see in the output
Bra, Unrealistic AND fake, anime, pixar, ugly, bad art, imperfections, cartoony, malformed, noisy, open mouth, (blur), (guassian blur), paintings, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast text, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast
num_outputs
Number of output images
3
width
Output image width
1024
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.
1714589370
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
samping_steps
Number of denoising steps
50
cfg_scale
Scale for classifier-free guidance
7.5
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/65cc351212e2438f93f76818e91db546/00000-1714589370.webp
https://files.tungsten.run/uploads/a47ad21b424441cbb25ae4004ce933b7/00001-1714589371.webp
https://files.tungsten.run/uploads/87a5e05904d140ce8f5d8d09879f9e09/00002-1714589372.webp
Finished in 265.9 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: Envision a whimsical fantasy world where a colossal, cute, blushed, and irresistibly translucent transparent ethereal very tiny blue ghost takes center stage. Picture the ghost with a mischievous charm, its surface reflecting a soft glow. Amidst its translucent body, an unexpected sight catches the eye, blue forget me not flowers suspended within its stomach. This charming and slightly perplexing scene invites you to explore the magical and endearing mysteries of this fantastical realm, where even the most mundane objects take on a delightful and surreal twist within the embrace of the giant, lovable slime. very detailed, hd, RAW photograph, masterpiece, top quality, best quality, official art,highest detailed, atmospheric lighting, cinematic composition, complex multiple subjects, 4k HDR, vibrant, highly detailed, Leica Q2 with Summilux 35mm f/1.2 ASPH, Ultra High Resolution, wallpaper, 8K, Rich texture details, hyper detailed, detailed eyes, detailed background, dramatic angle, epic composition, high quality , (8k, RAW photo, highest quality), hyperrealistic, Full negative prompt: Bra, Unrealistic AND fake, anime, pixar, ugly, bad art, imperfections, cartoony, malformed, noisy, open mouth, (blur), (guassian blur), paintings, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast text, watermark, low-quality, signature, moir pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:04<03:30, 4.29s/it] 4%|▍ | 2/50 [00:09<03:56, 4.94s/it] 6%|▌ | 3/50 [00:15<04:15, 5.43s/it] 8%|▊ | 4/50 [00:21<04:12, 5.49s/it] 10%|█ | 5/50 [00:27<04:12, 5.62s/it] 12%|█▏ | 6/50 [00:33<04:12, 5.75s/it] 14%|█▍ | 7/50 [00:39<04:11, 5.84s/it] 16%|█▌ | 8/50 [00:44<04:03, 5.81s/it] 18%|█▊ | 9/50 [00:50<03:56, 5.77s/it] 20%|██ | 10/50 [00:56<03:48, 5.70s/it] 22%|██▏ | 11/50 [01:02<03:50, 5.90s/it] 24%|██▍ | 12/50 [01:08<03:43, 5.88s/it] 26%|██▌ | 13/50 [01:13<03:32, 5.74s/it] 28%|██▊ | 14/50 [01:19<03:30, 5.84s/it] 30%|███ | 15/50 [01:25<03:22, 5.80s/it] 32%|███▏ | 16/50 [01:31<03:15, 5.74s/it] 34%|███▍ | 17/50 [01:35<03:00, 5.46s/it] 36%|███▌ | 18/50 [01:41<02:55, 5.48s/it] 38%|███▊ | 19/50 [01:46<02:50, 5.50s/it] 40%|████ | 20/50 [01:52<02:44, 5.49s/it] 42%|████▏ | 21/50 [01:57<02:34, 5.32s/it] 44%|████▍ | 22/50 [02:02<02:29, 5.33s/it] 46%|████▌ | 23/50 [02:08<02:26, 5.43s/it] 48%|████▊ | 24/50 [02:13<02:20, 5.42s/it] 50%|█████ | 25/50 [02:18<02:11, 5.25s/it] 52%|█████▏ | 26/50 [02:23<02:05, 5.24s/it] 54%|█████▍ | 27/50 [02:29<02:01, 5.28s/it] 56%|█████▌ | 28/50 [02:34<01:57, 5.34s/it] 58%|█████▊ | 29/50 [02:39<01:45, 5.04s/it] 60%|██████ | 30/50 [02:43<01:37, 4.86s/it] 62%|██████▏ | 31/50 [02:47<01:28, 4.67s/it] 64%|██████▍ | 32/50 [02:52<01:25, 4.76s/it] 66%|██████▌ | 33/50 [02:56<01:17, 4.56s/it] 68%|██████▊ | 34/50 [03:02<01:16, 4.77s/it] 70%|███████ | 35/50 [03:07<01:15, 5.04s/it] 72%|███████▏ | 36/50 [03:12<01:08, 4.88s/it] 74%|███████▍ | 37/50 [03:16<01:02, 4.78s/it] 76%|███████▌ | 38/50 [03:21<00:56, 4.73s/it] 78%|███████▊ | 39/50 [03:25<00:51, 4.64s/it] 80%|████████ | 40/50 [03:31<00:48, 4.87s/it] 82%|████████▏ | 41/50 [03:35<00:42, 4.74s/it] 84%|████████▍ | 42/50 [03:40<00:37, 4.70s/it] 86%|████████▌ | 43/50 [03:44<00:32, 4.67s/it] 88%|████████▊ | 44/50 [03:49<00:27, 4.65s/it] 90%|█████████ | 45/50 [03:54<00:24, 4.85s/it] 92%|█████████▏| 46/50 [04:00<00:19, 4.96s/it] 94%|█████████▍| 47/50 [04:04<00:14, 4.82s/it] 96%|█████████▌| 48/50 [04:09<00:09, 4.84s/it] 98%|█████████▊| 49/50 [04:13<00:04, 4.60s/it] 100%|██████████| 50/50 [04:14<00:00, 3.64s/it] 100%|██████████| 50/50 [04:14<00:00, 5.10s/it] Decoding latents in cuda:0... done in 2.38s Move latents to cpu... done in 0.03s 0: 640x640 (no detections), 8.3ms Speed: 3.9ms preprocess, 8.3ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 7.8ms Speed: 3.1ms preprocess, 7.8ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x640 (no detections), 8.5ms Speed: 3.1ms preprocess, 8.5ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. Uploading outputs... Finished.