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/d0ee2349c99e4c94a5e6661a2f44066b/00000-1714589370.webp
https://files.tungsten.run/uploads/4ac9f4db12fc4edf8f32c4d49405b998/00001-1714589371.webp
https://files.tungsten.run/uploads/3e50fda0288a496e8dc25cdb29ca11b8/00002-1714589372.webp
This example was created by evevalentine2017
Finished in 191.6 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: 3D Pixar style, 3D animation, a little and cute chibi ogre is cooking dinner, outdoors, forest, night, bonfire, glossy skin Full negative prompt: anime, cartoon, 2d, flat colors, cinematic, photorealistic, realistic, deformed, glitch, noisy, low contrast, porcelain hair, long neck, asymmetrical eyes, black background, signature, watermark 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:03<02:30, 3.08s/it] 4%|▍ | 2/50 [00:06<02:49, 3.54s/it] 6%|▌ | 3/50 [00:11<03:03, 3.91s/it] 8%|▊ | 4/50 [00:15<03:02, 3.97s/it] 10%|█ | 5/50 [00:19<03:00, 4.01s/it] 12%|█▏ | 6/50 [00:24<03:11, 4.36s/it] 14%|█▍ | 7/50 [00:28<03:07, 4.36s/it] 16%|█▌ | 8/50 [00:32<02:59, 4.28s/it] 18%|█▊ | 9/50 [00:37<02:52, 4.22s/it] 20%|██ | 10/50 [00:40<02:45, 4.13s/it] 22%|██▏ | 11/50 [00:45<02:42, 4.16s/it] 24%|██▍ | 12/50 [00:49<02:38, 4.17s/it] 26%|██▌ | 13/50 [00:53<02:30, 4.06s/it] 28%|██▊ | 14/50 [00:58<02:36, 4.34s/it] 30%|███ | 15/50 [01:02<02:29, 4.28s/it] 32%|███▏ | 16/50 [01:06<02:23, 4.22s/it] 34%|███▍ | 17/50 [01:09<02:10, 3.94s/it] 36%|███▌ | 18/50 [01:13<02:05, 3.94s/it] 38%|███▊ | 19/50 [01:17<02:02, 3.94s/it] 40%|████ | 20/50 [01:21<01:57, 3.91s/it] 42%|████▏ | 21/50 [01:24<01:49, 3.78s/it] 44%|████▍ | 22/50 [01:28<01:46, 3.79s/it] 46%|████▌ | 23/50 [01:32<01:42, 3.81s/it] 48%|████▊ | 24/50 [01:36<01:39, 3.81s/it] 50%|█████ | 25/50 [01:39<01:31, 3.67s/it] 52%|█████▏ | 26/50 [01:43<01:28, 3.67s/it] 54%|█████▍ | 27/50 [01:47<01:25, 3.71s/it] 56%|█████▌ | 28/50 [01:51<01:22, 3.76s/it] 58%|█████▊ | 29/50 [01:54<01:14, 3.55s/it] 60%|██████ | 30/50 [01:57<01:08, 3.42s/it] 62%|██████▏ | 31/50 [02:00<01:02, 3.29s/it] 64%|██████▍ | 32/50 [02:03<01:00, 3.38s/it] 66%|██████▌ | 33/50 [02:06<00:54, 3.22s/it] 68%|██████▊ | 34/50 [02:10<00:54, 3.39s/it] 70%|███████ | 35/50 [02:14<00:53, 3.60s/it] 72%|███████▏ | 36/50 [02:17<00:48, 3.47s/it] 74%|███████▍ | 37/50 [02:21<00:44, 3.43s/it] 76%|███████▌ | 38/50 [02:24<00:40, 3.39s/it] 78%|███████▊ | 39/50 [02:27<00:36, 3.30s/it] 80%|████████ | 40/50 [02:31<00:34, 3.45s/it] 82%|████████▏ | 41/50 [02:34<00:30, 3.35s/it] 84%|████████▍ | 42/50 [02:37<00:26, 3.31s/it] 86%|████████▌ | 43/50 [02:40<00:22, 3.27s/it] 88%|████████▊ | 44/50 [02:43<00:19, 3.25s/it] 90%|█████████ | 45/50 [02:47<00:17, 3.40s/it] 92%|█████████▏| 46/50 [02:51<00:13, 3.48s/it] 94%|█████████▍| 47/50 [02:54<00:10, 3.36s/it] 96%|█████████▌| 48/50 [02:57<00:06, 3.37s/it] 98%|█████████▊| 49/50 [03:00<00:03, 3.20s/it] 100%|██████████| 50/50 [03:01<00:00, 2.52s/it] 100%|██████████| 50/50 [03:01<00:00, 3.63s/it] Decoding latents in cuda:0... done in 1.71s Move latents to cpu... done in 0.02s 0: 640x480 (no detections), 160.7ms Speed: 2.8ms preprocess, 160.7ms inference, 1.1ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x480 (no detections), 8.1ms Speed: 2.4ms preprocess, 8.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x480 (no detections), 8.1ms Speed: 2.3ms preprocess, 8.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] 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/d0ee2349c99e4c94a5e6661a2f44066b/00000-1714589370.webp
https://files.tungsten.run/uploads/4ac9f4db12fc4edf8f32c4d49405b998/00001-1714589371.webp
https://files.tungsten.run/uploads/3e50fda0288a496e8dc25cdb29ca11b8/00002-1714589372.webp
This example was created by evevalentine2017
Finished in 191.6 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: 3D Pixar style, 3D animation, a little and cute chibi ogre is cooking dinner, outdoors, forest, night, bonfire, glossy skin Full negative prompt: anime, cartoon, 2d, flat colors, cinematic, photorealistic, realistic, deformed, glitch, noisy, low contrast, porcelain hair, long neck, asymmetrical eyes, black background, signature, watermark 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:03<02:30, 3.08s/it] 4%|▍ | 2/50 [00:06<02:49, 3.54s/it] 6%|▌ | 3/50 [00:11<03:03, 3.91s/it] 8%|▊ | 4/50 [00:15<03:02, 3.97s/it] 10%|█ | 5/50 [00:19<03:00, 4.01s/it] 12%|█▏ | 6/50 [00:24<03:11, 4.36s/it] 14%|█▍ | 7/50 [00:28<03:07, 4.36s/it] 16%|█▌ | 8/50 [00:32<02:59, 4.28s/it] 18%|█▊ | 9/50 [00:37<02:52, 4.22s/it] 20%|██ | 10/50 [00:40<02:45, 4.13s/it] 22%|██▏ | 11/50 [00:45<02:42, 4.16s/it] 24%|██▍ | 12/50 [00:49<02:38, 4.17s/it] 26%|██▌ | 13/50 [00:53<02:30, 4.06s/it] 28%|██▊ | 14/50 [00:58<02:36, 4.34s/it] 30%|███ | 15/50 [01:02<02:29, 4.28s/it] 32%|███▏ | 16/50 [01:06<02:23, 4.22s/it] 34%|███▍ | 17/50 [01:09<02:10, 3.94s/it] 36%|███▌ | 18/50 [01:13<02:05, 3.94s/it] 38%|███▊ | 19/50 [01:17<02:02, 3.94s/it] 40%|████ | 20/50 [01:21<01:57, 3.91s/it] 42%|████▏ | 21/50 [01:24<01:49, 3.78s/it] 44%|████▍ | 22/50 [01:28<01:46, 3.79s/it] 46%|████▌ | 23/50 [01:32<01:42, 3.81s/it] 48%|████▊ | 24/50 [01:36<01:39, 3.81s/it] 50%|█████ | 25/50 [01:39<01:31, 3.67s/it] 52%|█████▏ | 26/50 [01:43<01:28, 3.67s/it] 54%|█████▍ | 27/50 [01:47<01:25, 3.71s/it] 56%|█████▌ | 28/50 [01:51<01:22, 3.76s/it] 58%|█████▊ | 29/50 [01:54<01:14, 3.55s/it] 60%|██████ | 30/50 [01:57<01:08, 3.42s/it] 62%|██████▏ | 31/50 [02:00<01:02, 3.29s/it] 64%|██████▍ | 32/50 [02:03<01:00, 3.38s/it] 66%|██████▌ | 33/50 [02:06<00:54, 3.22s/it] 68%|██████▊ | 34/50 [02:10<00:54, 3.39s/it] 70%|███████ | 35/50 [02:14<00:53, 3.60s/it] 72%|███████▏ | 36/50 [02:17<00:48, 3.47s/it] 74%|███████▍ | 37/50 [02:21<00:44, 3.43s/it] 76%|███████▌ | 38/50 [02:24<00:40, 3.39s/it] 78%|███████▊ | 39/50 [02:27<00:36, 3.30s/it] 80%|████████ | 40/50 [02:31<00:34, 3.45s/it] 82%|████████▏ | 41/50 [02:34<00:30, 3.35s/it] 84%|████████▍ | 42/50 [02:37<00:26, 3.31s/it] 86%|████████▌ | 43/50 [02:40<00:22, 3.27s/it] 88%|████████▊ | 44/50 [02:43<00:19, 3.25s/it] 90%|█████████ | 45/50 [02:47<00:17, 3.40s/it] 92%|█████████▏| 46/50 [02:51<00:13, 3.48s/it] 94%|█████████▍| 47/50 [02:54<00:10, 3.36s/it] 96%|█████████▌| 48/50 [02:57<00:06, 3.37s/it] 98%|█████████▊| 49/50 [03:00<00:03, 3.20s/it] 100%|██████████| 50/50 [03:01<00:00, 2.52s/it] 100%|██████████| 50/50 [03:01<00:00, 3.63s/it] Decoding latents in cuda:0... done in 1.71s Move latents to cpu... done in 0.02s 0: 640x480 (no detections), 160.7ms Speed: 2.8ms preprocess, 160.7ms inference, 1.1ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x480 (no detections), 8.1ms Speed: 2.4ms preprocess, 8.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x480 (no detections), 8.1ms Speed: 2.3ms preprocess, 8.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 3 with 1st settings. Uploading outputs... Finished.