tungsten-logo
Sign In
aurora-sdxl
aurora-sdxl

aurora-sdxl

4 stars
Version: v1.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
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.
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.
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.
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.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
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.
Sign in to run this model for free!
Output
https://files.tungsten.run/uploads/9b18d77928114bbcac688b3e94043131/00000-1714589370.webp
https://files.tungsten.run/uploads/2e3fa7e875004588ac484f98b1af81ef/00001-1714589371.webp
https://files.tungsten.run/uploads/04b37ed2337f4790a064abc2170ca3c7/00002-1714589372.webp
This example was created by evevalentine2017
Finished in 184.6 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: best quality, masterpiece, realistic art style, ethereal fantasy concept art of best quality, fractal art, dream city in the style of structured chaos, golden palette, unique yokai illustrations, CryEngine, large-scale murals, ornate complexity, vivid energy, magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy Full negative prompt: 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 [00:03<02:27, 3.02s/it] 4%|▍ | 2/50 [00:06<02:44, 3.43s/it] 6%|▌ | 3/50 [00:10<02:58, 3.79s/it] 8%|▊ | 4/50 [00:14<02:56, 3.83s/it] 10%|█ | 5/50 [00:18<02:54, 3.88s/it] 12%|█▏ | 6/50 [00:22<02:54, 3.96s/it] 14%|█▍ | 7/50 [00:27<02:53, 4.03s/it] 16%|█▌ | 8/50 [00:31<02:48, 4.01s/it] 18%|█▊ | 9/50 [00:34<02:42, 3.97s/it] 20%|██ | 10/50 [00:38<02:36, 3.91s/it] 22%|██▏ | 11/50 [00:43<02:46, 4.26s/it] 24%|██▍ | 12/50 [00:47<02:38, 4.18s/it] 26%|██▌ | 13/50 [00:51<02:29, 4.03s/it] 28%|██▊ | 14/50 [00:55<02:25, 4.05s/it] 30%|███ | 15/50 [00:59<02:19, 4.00s/it] 32%|███▏ | 16/50 [01:03<02:15, 3.98s/it] 34%|███▍ | 17/50 [01:06<02:03, 3.73s/it] 36%|███▌ | 18/50 [01:10<01:59, 3.73s/it] 38%|███▊ | 19/50 [01:14<01:55, 3.73s/it] 40%|████ | 20/50 [01:17<01:51, 3.71s/it] 42%|████▏ | 21/50 [01:21<01:44, 3.60s/it] 44%|████▍ | 22/50 [01:24<01:40, 3.61s/it] 46%|████▌ | 23/50 [01:28<01:38, 3.64s/it] 48%|████▊ | 24/50 [01:32<01:34, 3.65s/it] 50%|█████ | 25/50 [01:35<01:31, 3.67s/it] 52%|█████▏ | 26/50 [01:39<01:29, 3.75s/it] 54%|█████▍ | 27/50 [01:43<01:25, 3.73s/it] 56%|█████▌ | 28/50 [01:47<01:21, 3.71s/it] 58%|█████▊ | 29/50 [01:49<01:13, 3.48s/it] 60%|██████ | 30/50 [01:53<01:06, 3.35s/it] 62%|██████▏ | 31/50 [01:55<01:01, 3.23s/it] 64%|██████▍ | 32/50 [01:59<00:59, 3.28s/it] 66%|██████▌ | 33/50 [02:02<00:53, 3.13s/it] 68%|██████▊ | 34/50 [02:05<00:52, 3.26s/it] 70%|███████ | 35/50 [02:09<00:52, 3.47s/it] 72%|███████▏ | 36/50 [02:12<00:46, 3.34s/it] 74%|███████▍ | 37/50 [02:15<00:42, 3.27s/it] 76%|███████▌ | 38/50 [02:18<00:38, 3.24s/it] 78%|███████▊ | 39/50 [02:21<00:34, 3.16s/it] 80%|████████ | 40/50 [02:25<00:33, 3.31s/it] 82%|████████▏ | 41/50 [02:28<00:28, 3.21s/it] 84%|████████▍ | 42/50 [02:31<00:25, 3.17s/it] 86%|████████▌ | 43/50 [02:34<00:21, 3.13s/it] 88%|████████▊ | 44/50 [02:37<00:18, 3.11s/it] 90%|█████████ | 45/50 [02:41<00:16, 3.24s/it] 92%|█████████▏| 46/50 [02:44<00:13, 3.33s/it] 94%|█████████▍| 47/50 [02:47<00:09, 3.22s/it] 96%|█████████▌| 48/50 [02:50<00:06, 3.21s/it] 98%|█████████▊| 49/50 [02:53<00:03, 3.05s/it] 100%|██████████| 50/50 [02:54<00:00, 2.40s/it] 100%|██████████| 50/50 [02:54<00:00, 3.49s/it] Decoding latents in cuda:0... done in 1.74s Move latents to cpu... done in 0.02s 0: 480x640 (no detections), 165.3ms Speed: 3.1ms preprocess, 165.3ms inference, 1.3ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 480x640 (no detections), 8.5ms Speed: 2.4ms preprocess, 8.5ms 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), 8.1ms Speed: 2.3ms preprocess, 8.1ms inference, 0.7ms 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
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
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.
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.
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.
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.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
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.
Sign in to run this model for free!
https://files.tungsten.run/uploads/9b18d77928114bbcac688b3e94043131/00000-1714589370.webp
https://files.tungsten.run/uploads/2e3fa7e875004588ac484f98b1af81ef/00001-1714589371.webp
https://files.tungsten.run/uploads/04b37ed2337f4790a064abc2170ca3c7/00002-1714589372.webp
This example was created by evevalentine2017
Finished in 184.6 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: best quality, masterpiece, realistic art style, ethereal fantasy concept art of best quality, fractal art, dream city in the style of structured chaos, golden palette, unique yokai illustrations, CryEngine, large-scale murals, ornate complexity, vivid energy, magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy Full negative prompt: 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 [00:03<02:27, 3.02s/it] 4%|▍ | 2/50 [00:06<02:44, 3.43s/it] 6%|▌ | 3/50 [00:10<02:58, 3.79s/it] 8%|▊ | 4/50 [00:14<02:56, 3.83s/it] 10%|█ | 5/50 [00:18<02:54, 3.88s/it] 12%|█▏ | 6/50 [00:22<02:54, 3.96s/it] 14%|█▍ | 7/50 [00:27<02:53, 4.03s/it] 16%|█▌ | 8/50 [00:31<02:48, 4.01s/it] 18%|█▊ | 9/50 [00:34<02:42, 3.97s/it] 20%|██ | 10/50 [00:38<02:36, 3.91s/it] 22%|██▏ | 11/50 [00:43<02:46, 4.26s/it] 24%|██▍ | 12/50 [00:47<02:38, 4.18s/it] 26%|██▌ | 13/50 [00:51<02:29, 4.03s/it] 28%|██▊ | 14/50 [00:55<02:25, 4.05s/it] 30%|███ | 15/50 [00:59<02:19, 4.00s/it] 32%|███▏ | 16/50 [01:03<02:15, 3.98s/it] 34%|███▍ | 17/50 [01:06<02:03, 3.73s/it] 36%|███▌ | 18/50 [01:10<01:59, 3.73s/it] 38%|███▊ | 19/50 [01:14<01:55, 3.73s/it] 40%|████ | 20/50 [01:17<01:51, 3.71s/it] 42%|████▏ | 21/50 [01:21<01:44, 3.60s/it] 44%|████▍ | 22/50 [01:24<01:40, 3.61s/it] 46%|████▌ | 23/50 [01:28<01:38, 3.64s/it] 48%|████▊ | 24/50 [01:32<01:34, 3.65s/it] 50%|█████ | 25/50 [01:35<01:31, 3.67s/it] 52%|█████▏ | 26/50 [01:39<01:29, 3.75s/it] 54%|█████▍ | 27/50 [01:43<01:25, 3.73s/it] 56%|█████▌ | 28/50 [01:47<01:21, 3.71s/it] 58%|█████▊ | 29/50 [01:49<01:13, 3.48s/it] 60%|██████ | 30/50 [01:53<01:06, 3.35s/it] 62%|██████▏ | 31/50 [01:55<01:01, 3.23s/it] 64%|██████▍ | 32/50 [01:59<00:59, 3.28s/it] 66%|██████▌ | 33/50 [02:02<00:53, 3.13s/it] 68%|██████▊ | 34/50 [02:05<00:52, 3.26s/it] 70%|███████ | 35/50 [02:09<00:52, 3.47s/it] 72%|███████▏ | 36/50 [02:12<00:46, 3.34s/it] 74%|███████▍ | 37/50 [02:15<00:42, 3.27s/it] 76%|███████▌ | 38/50 [02:18<00:38, 3.24s/it] 78%|███████▊ | 39/50 [02:21<00:34, 3.16s/it] 80%|████████ | 40/50 [02:25<00:33, 3.31s/it] 82%|████████▏ | 41/50 [02:28<00:28, 3.21s/it] 84%|████████▍ | 42/50 [02:31<00:25, 3.17s/it] 86%|████████▌ | 43/50 [02:34<00:21, 3.13s/it] 88%|████████▊ | 44/50 [02:37<00:18, 3.11s/it] 90%|█████████ | 45/50 [02:41<00:16, 3.24s/it] 92%|█████████▏| 46/50 [02:44<00:13, 3.33s/it] 94%|█████████▍| 47/50 [02:47<00:09, 3.22s/it] 96%|█████████▌| 48/50 [02:50<00:06, 3.21s/it] 98%|█████████▊| 49/50 [02:53<00:03, 3.05s/it] 100%|██████████| 50/50 [02:54<00:00, 2.40s/it] 100%|██████████| 50/50 [02:54<00:00, 3.49s/it] Decoding latents in cuda:0... done in 1.74s Move latents to cpu... done in 0.02s 0: 480x640 (no detections), 165.3ms Speed: 3.1ms preprocess, 165.3ms inference, 1.3ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 480x640 (no detections), 8.5ms Speed: 2.4ms preprocess, 8.5ms 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), 8.1ms Speed: 2.3ms preprocess, 8.1ms inference, 0.7ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. Uploading outputs... Finished.