tungsten-logo
Sign In
unstablediffusers-xl
unstablediffusers-xl

unstablediffusers-xl

9 stars
Version: v1.1
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
sdxlyamersstyle
Sdxlyamersstyle
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/bf1bda10949647848bb43d2e9be415de/00000-3579777811.webp
https://files.tungsten.run/uploads/4aba91dee91a4b3db87fa94d3a70969a/00001-3579777812.webp
https://files.tungsten.run/uploads/046b143c21474e98b0b513ad2b0a16fd/00002-3579777813.webp
This example was created by evevalentine2017
Finished in 80.0 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: yamer style, masterpiece), (best quality), (ultra-detailed), (intricate details), (best quality:1.5), (intricate emotional details:1.5), (sharpen details), (ultra detailed), (cinematic lighting), bright colors, joyful, amazing, colorful, dramatic, the outline of a man against the golden hues of a beach sunset, palm trees, surfers, or beachgoers, <lora:xl_yamer_style-3.0:0.25> Full negative prompt: bad quality, bad anatomy, worst quality, low quality, low resolution, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image, deformation, skin moles 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:02<01:24, 2.49s/it] 6%|▌ | 2/35 [00:03<00:58, 1.78s/it] 9%|▊ | 3/35 [00:05<00:49, 1.56s/it] 11%|█▏ | 4/35 [00:06<00:45, 1.45s/it] 14%|█▍ | 5/35 [00:07<00:41, 1.40s/it] 17%|█▋ | 6/35 [00:08<00:39, 1.36s/it] 20%|██ | 7/35 [00:10<00:37, 1.34s/it] 23%|██▎ | 8/35 [00:11<00:35, 1.33s/it] 26%|██▌ | 9/35 [00:12<00:34, 1.32s/it] 29%|██▊ | 10/35 [00:14<00:32, 1.31s/it] 31%|███▏ | 11/35 [00:15<00:31, 1.31s/it] 34%|███▍ | 12/35 [00:16<00:30, 1.31s/it] 37%|███▋ | 13/35 [00:18<00:28, 1.31s/it] 40%|████ | 14/35 [00:19<00:27, 1.31s/it] 43%|████▎ | 15/35 [00:20<00:26, 1.31s/it] 46%|████▌ | 16/35 [00:21<00:24, 1.31s/it] 49%|████▊ | 17/35 [00:23<00:23, 1.31s/it] 51%|█████▏ | 18/35 [00:24<00:22, 1.32s/it] 54%|█████▍ | 19/35 [00:25<00:21, 1.32s/it] 57%|█████▋ | 20/35 [00:27<00:19, 1.33s/it] 60%|██████ | 21/35 [00:28<00:18, 1.32s/it] 63%|██████▎ | 22/35 [00:29<00:17, 1.32s/it] 66%|██████▌ | 23/35 [00:31<00:15, 1.32s/it] 69%|██████▊ | 24/35 [00:32<00:14, 1.32s/it] 71%|███████▏ | 25/35 [00:33<00:13, 1.32s/it] 74%|███████▍ | 26/35 [00:35<00:11, 1.32s/it] 77%|███████▋ | 27/35 [00:36<00:10, 1.32s/it] 80%|████████ | 28/35 [00:37<00:09, 1.32s/it] 83%|████████▎ | 29/35 [00:39<00:07, 1.32s/it] 86%|████████▌ | 30/35 [00:40<00:06, 1.31s/it] 89%|████████▊ | 31/35 [00:41<00:05, 1.32s/it] 91%|█████████▏| 32/35 [00:43<00:03, 1.32s/it] 94%|█████████▍| 33/35 [00:44<00:02, 1.32s/it] 97%|█████████▋| 34/35 [00:45<00:01, 1.32s/it] 100%|██████████| 35/35 [00:47<00:00, 1.32s/it] 100%|██████████| 35/35 [00:47<00:00, 1.34s/it] Decoding latents in cuda:0... done in 2.33s Move latents to cpu... done in 0.04s 0: 640x640 (no detections), 7.7ms Speed: 3.3ms preprocess, 7.7ms inference, 5.2ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 9.3ms Speed: 3.1ms preprocess, 9.3ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 9.0ms Speed: 3.0ms preprocess, 9.0ms inference, 10.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:07, 2.04it/s] 12%|█▎ | 2/16 [00:00<00:06, 2.30it/s] 19%|█▉ | 3/16 [00:01<00:05, 2.35it/s] 25%|██▌ | 4/16 [00:01<00:04, 2.41it/s] 31%|███▏ | 5/16 [00:02<00:04, 2.43it/s] 38%|███▊ | 6/16 [00:02<00:04, 2.44it/s] 44%|████▍ | 7/16 [00:02<00:03, 2.45it/s] 50%|█████ | 8/16 [00:03<00:03, 2.45it/s] 56%|█████▋ | 9/16 [00:03<00:02, 2.46it/s] 62%|██████▎ | 10/16 [00:04<00:02, 2.46it/s] 69%|██████▉ | 11/16 [00:04<00:02, 2.46it/s] 75%|███████▌ | 12/16 [00:04<00:01, 2.46it/s] 81%|████████▏ | 13/16 [00:05<00:01, 2.40it/s] 88%|████████▊ | 14/16 [00:05<00:00, 2.42it/s] 94%|█████████▍| 15/16 [00:06<00:00, 1.94it/s] 100%|██████████| 16/16 [00:07<00:00, 1.69it/s] 100%|██████████| 16/16 [00:07<00:00, 2.19it/s] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 18.3ms Speed: 5.3ms preprocess, 18.3ms inference, 2.2ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 (no detections), 18.1ms Speed: 5.3ms preprocess, 18.1ms inference, 1.2ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x640 1 hand, 8.6ms Speed: 3.0ms preprocess, 8.6ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:05, 2.54it/s] 12%|█▎ | 2/16 [00:00<00:05, 2.51it/s] 19%|█▉ | 3/16 [00:01<00:05, 2.47it/s] 25%|██▌ | 4/16 [00:01<00:04, 2.45it/s] 31%|███▏ | 5/16 [00:02<00:04, 2.45it/s] 38%|███▊ | 6/16 [00:02<00:04, 2.46it/s] 44%|████▍ | 7/16 [00:02<00:03, 2.47it/s] 50%|█████ | 8/16 [00:03<00:03, 2.46it/s] 56%|█████▋ | 9/16 [00:03<00:02, 2.47it/s] 62%|██████▎ | 10/16 [00:04<00:02, 2.46it/s] 69%|██████▉ | 11/16 [00:04<00:02, 2.46it/s] 75%|███████▌ | 12/16 [00:04<00:01, 2.47it/s] 81%|████████▏ | 13/16 [00:05<00:01, 2.46it/s] 88%|████████▊ | 14/16 [00:05<00:00, 2.46it/s] 94%|█████████▍| 15/16 [00:06<00:00, 2.46it/s] 100%|██████████| 16/16 [00:06<00:00, 2.46it/s] 100%|██████████| 16/16 [00:06<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
sdxlyamersstyle
Sdxlyamersstyle
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/bf1bda10949647848bb43d2e9be415de/00000-3579777811.webp
https://files.tungsten.run/uploads/4aba91dee91a4b3db87fa94d3a70969a/00001-3579777812.webp
https://files.tungsten.run/uploads/046b143c21474e98b0b513ad2b0a16fd/00002-3579777813.webp
This example was created by evevalentine2017
Finished in 80.0 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: yamer style, masterpiece), (best quality), (ultra-detailed), (intricate details), (best quality:1.5), (intricate emotional details:1.5), (sharpen details), (ultra detailed), (cinematic lighting), bright colors, joyful, amazing, colorful, dramatic, the outline of a man against the golden hues of a beach sunset, palm trees, surfers, or beachgoers, <lora:xl_yamer_style-3.0:0.25> Full negative prompt: bad quality, bad anatomy, worst quality, low quality, low resolution, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image, deformation, skin moles 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:02<01:24, 2.49s/it] 6%|▌ | 2/35 [00:03<00:58, 1.78s/it] 9%|▊ | 3/35 [00:05<00:49, 1.56s/it] 11%|█▏ | 4/35 [00:06<00:45, 1.45s/it] 14%|█▍ | 5/35 [00:07<00:41, 1.40s/it] 17%|█▋ | 6/35 [00:08<00:39, 1.36s/it] 20%|██ | 7/35 [00:10<00:37, 1.34s/it] 23%|██▎ | 8/35 [00:11<00:35, 1.33s/it] 26%|██▌ | 9/35 [00:12<00:34, 1.32s/it] 29%|██▊ | 10/35 [00:14<00:32, 1.31s/it] 31%|███▏ | 11/35 [00:15<00:31, 1.31s/it] 34%|███▍ | 12/35 [00:16<00:30, 1.31s/it] 37%|███▋ | 13/35 [00:18<00:28, 1.31s/it] 40%|████ | 14/35 [00:19<00:27, 1.31s/it] 43%|████▎ | 15/35 [00:20<00:26, 1.31s/it] 46%|████▌ | 16/35 [00:21<00:24, 1.31s/it] 49%|████▊ | 17/35 [00:23<00:23, 1.31s/it] 51%|█████▏ | 18/35 [00:24<00:22, 1.32s/it] 54%|█████▍ | 19/35 [00:25<00:21, 1.32s/it] 57%|█████▋ | 20/35 [00:27<00:19, 1.33s/it] 60%|██████ | 21/35 [00:28<00:18, 1.32s/it] 63%|██████▎ | 22/35 [00:29<00:17, 1.32s/it] 66%|██████▌ | 23/35 [00:31<00:15, 1.32s/it] 69%|██████▊ | 24/35 [00:32<00:14, 1.32s/it] 71%|███████▏ | 25/35 [00:33<00:13, 1.32s/it] 74%|███████▍ | 26/35 [00:35<00:11, 1.32s/it] 77%|███████▋ | 27/35 [00:36<00:10, 1.32s/it] 80%|████████ | 28/35 [00:37<00:09, 1.32s/it] 83%|████████▎ | 29/35 [00:39<00:07, 1.32s/it] 86%|████████▌ | 30/35 [00:40<00:06, 1.31s/it] 89%|████████▊ | 31/35 [00:41<00:05, 1.32s/it] 91%|█████████▏| 32/35 [00:43<00:03, 1.32s/it] 94%|█████████▍| 33/35 [00:44<00:02, 1.32s/it] 97%|█████████▋| 34/35 [00:45<00:01, 1.32s/it] 100%|██████████| 35/35 [00:47<00:00, 1.32s/it] 100%|██████████| 35/35 [00:47<00:00, 1.34s/it] Decoding latents in cuda:0... done in 2.33s Move latents to cpu... done in 0.04s 0: 640x640 (no detections), 7.7ms Speed: 3.3ms preprocess, 7.7ms inference, 5.2ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x640 (no detections), 9.3ms Speed: 3.1ms preprocess, 9.3ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 9.0ms Speed: 3.0ms preprocess, 9.0ms inference, 10.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:07, 2.04it/s] 12%|█▎ | 2/16 [00:00<00:06, 2.30it/s] 19%|█▉ | 3/16 [00:01<00:05, 2.35it/s] 25%|██▌ | 4/16 [00:01<00:04, 2.41it/s] 31%|███▏ | 5/16 [00:02<00:04, 2.43it/s] 38%|███▊ | 6/16 [00:02<00:04, 2.44it/s] 44%|████▍ | 7/16 [00:02<00:03, 2.45it/s] 50%|█████ | 8/16 [00:03<00:03, 2.45it/s] 56%|█████▋ | 9/16 [00:03<00:02, 2.46it/s] 62%|██████▎ | 10/16 [00:04<00:02, 2.46it/s] 69%|██████▉ | 11/16 [00:04<00:02, 2.46it/s] 75%|███████▌ | 12/16 [00:04<00:01, 2.46it/s] 81%|████████▏ | 13/16 [00:05<00:01, 2.40it/s] 88%|████████▊ | 14/16 [00:05<00:00, 2.42it/s] 94%|█████████▍| 15/16 [00:06<00:00, 1.94it/s] 100%|██████████| 16/16 [00:07<00:00, 1.69it/s] 100%|██████████| 16/16 [00:07<00:00, 2.19it/s] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 18.3ms Speed: 5.3ms preprocess, 18.3ms inference, 2.2ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 (no detections), 18.1ms Speed: 5.3ms preprocess, 18.1ms inference, 1.2ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x640 1 hand, 8.6ms Speed: 3.0ms preprocess, 8.6ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/16 [00:00<?, ?it/s] 6%|▋ | 1/16 [00:00<00:05, 2.54it/s] 12%|█▎ | 2/16 [00:00<00:05, 2.51it/s] 19%|█▉ | 3/16 [00:01<00:05, 2.47it/s] 25%|██▌ | 4/16 [00:01<00:04, 2.45it/s] 31%|███▏ | 5/16 [00:02<00:04, 2.45it/s] 38%|███▊ | 6/16 [00:02<00:04, 2.46it/s] 44%|████▍ | 7/16 [00:02<00:03, 2.47it/s] 50%|█████ | 8/16 [00:03<00:03, 2.46it/s] 56%|█████▋ | 9/16 [00:03<00:02, 2.47it/s] 62%|██████▎ | 10/16 [00:04<00:02, 2.46it/s] 69%|██████▉ | 11/16 [00:04<00:02, 2.46it/s] 75%|███████▌ | 12/16 [00:04<00:01, 2.47it/s] 81%|████████▏ | 13/16 [00:05<00:01, 2.46it/s] 88%|████████▊ | 14/16 [00:05<00:00, 2.46it/s] 94%|█████████▍| 15/16 [00:06<00:00, 2.46it/s] 100%|██████████| 16/16 [00:06<00:00, 2.46it/s] 100%|██████████| 16/16 [00:06<00:00, 2.47it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s Uploading outputs... Finished.