tungsten-logo
Sign In
confusion-sdxl
confusion-sdxl

confusion-sdxl

10 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/e8825364a7564d1d8045b6cef063fd6b/00000-1000.webp
https://files.tungsten.run/uploads/0b577f7ad2894ba0ae8e2d50729960f1/00001-1001.webp
https://files.tungsten.run/uploads/ce53e246ead24d369797d6c23febe294/00002-1002.webp
This example was created by evevalentine2017
Finished in 90.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: amazing quality, masterpiece, best quality, absurdres, beautiful, detailed shadow, aesthetic, highly detailed, vibrant, cinematic, absurdres, upper body, 1girl, sea, star, night, <lora:EnvyAwesomizeXL01:1>, awesomize Full negative prompt: worst quality, low quality 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:02<01:44, 2.14s/it] 4%|▍ | 2/50 [00:03<01:10, 1.47s/it] 6%|▌ | 3/50 [00:04<00:58, 1.25s/it] 8%|▊ | 4/50 [00:05<00:52, 1.14s/it] 10%|█ | 5/50 [00:06<00:48, 1.09s/it] 12%|█▏ | 6/50 [00:07<00:46, 1.05s/it] 14%|█▍ | 7/50 [00:08<00:44, 1.04s/it] 16%|█▌ | 8/50 [00:09<00:42, 1.02s/it] 18%|█▊ | 9/50 [00:10<00:41, 1.01s/it] 20%|██ | 10/50 [00:11<00:40, 1.01s/it] 22%|██▏ | 11/50 [00:12<00:39, 1.01s/it] 24%|██▍ | 12/50 [00:13<00:38, 1.00s/it] 26%|██▌ | 13/50 [00:14<00:37, 1.01s/it] 28%|██▊ | 14/50 [00:15<00:36, 1.01s/it] 30%|███ | 15/50 [00:16<00:35, 1.01s/it] 32%|███▏ | 16/50 [00:17<00:34, 1.01s/it] 34%|███▍ | 17/50 [00:18<00:33, 1.01s/it] 36%|███▌ | 18/50 [00:19<00:32, 1.01s/it] 38%|███▊ | 19/50 [00:20<00:31, 1.01s/it] 40%|████ | 20/50 [00:21<00:30, 1.01s/it] 42%|████▏ | 21/50 [00:22<00:29, 1.01s/it] 44%|████▍ | 22/50 [00:23<00:28, 1.01s/it] 46%|████▌ | 23/50 [00:24<00:27, 1.01s/it] 48%|████▊ | 24/50 [00:25<00:26, 1.01s/it] 50%|█████ | 25/50 [00:26<00:25, 1.01s/it] 52%|█████▏ | 26/50 [00:27<00:24, 1.01s/it] 54%|█████▍ | 27/50 [00:28<00:23, 1.01s/it] 56%|█████▌ | 28/50 [00:29<00:22, 1.01s/it] 58%|█████▊ | 29/50 [00:30<00:21, 1.00s/it] 60%|██████ | 30/50 [00:31<00:20, 1.00s/it] 62%|██████▏ | 31/50 [00:32<00:19, 1.00s/it] 64%|██████▍ | 32/50 [00:33<00:18, 1.00s/it] 66%|██████▌ | 33/50 [00:34<00:17, 1.00s/it] 68%|██████▊ | 34/50 [00:35<00:15, 1.00it/s] 70%|███████ | 35/50 [00:36<00:14, 1.00it/s] 72%|███████▏ | 36/50 [00:37<00:13, 1.01it/s] 74%|███████▍ | 37/50 [00:38<00:12, 1.01it/s] 76%|███████▌ | 38/50 [00:39<00:11, 1.01it/s] 78%|███████▊ | 39/50 [00:40<00:10, 1.01it/s] 80%|████████ | 40/50 [00:41<00:09, 1.00it/s] 82%|████████▏ | 41/50 [00:42<00:08, 1.01it/s] 84%|████████▍ | 42/50 [00:43<00:07, 1.01it/s] 86%|████████▌ | 43/50 [00:44<00:06, 1.01it/s] 88%|████████▊ | 44/50 [00:45<00:05, 1.01it/s] 90%|█████████ | 45/50 [00:46<00:04, 1.01it/s] 92%|█████████▏| 46/50 [00:47<00:03, 1.01it/s] 94%|█████████▍| 47/50 [00:48<00:02, 1.02it/s] 96%|█████████▌| 48/50 [00:49<00:01, 1.02it/s] 98%|█████████▊| 49/50 [00:50<00:00, 1.02it/s] 100%|██████████| 50/50 [00:50<00:00, 1.02it/s] 100%|██████████| 50/50 [00:50<00:00, 1.02s/it] Decoding latents in cuda:0... done in 1.72s Move latents to cpu... done in 0.02s
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/e8825364a7564d1d8045b6cef063fd6b/00000-1000.webp
https://files.tungsten.run/uploads/0b577f7ad2894ba0ae8e2d50729960f1/00001-1001.webp
https://files.tungsten.run/uploads/ce53e246ead24d369797d6c23febe294/00002-1002.webp
This example was created by evevalentine2017
Finished in 90.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: amazing quality, masterpiece, best quality, absurdres, beautiful, detailed shadow, aesthetic, highly detailed, vibrant, cinematic, absurdres, upper body, 1girl, sea, star, night, <lora:EnvyAwesomizeXL01:1>, awesomize Full negative prompt: worst quality, low quality 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:02<01:44, 2.14s/it] 4%|▍ | 2/50 [00:03<01:10, 1.47s/it] 6%|▌ | 3/50 [00:04<00:58, 1.25s/it] 8%|▊ | 4/50 [00:05<00:52, 1.14s/it] 10%|█ | 5/50 [00:06<00:48, 1.09s/it] 12%|█▏ | 6/50 [00:07<00:46, 1.05s/it] 14%|█▍ | 7/50 [00:08<00:44, 1.04s/it] 16%|█▌ | 8/50 [00:09<00:42, 1.02s/it] 18%|█▊ | 9/50 [00:10<00:41, 1.01s/it] 20%|██ | 10/50 [00:11<00:40, 1.01s/it] 22%|██▏ | 11/50 [00:12<00:39, 1.01s/it] 24%|██▍ | 12/50 [00:13<00:38, 1.00s/it] 26%|██▌ | 13/50 [00:14<00:37, 1.01s/it] 28%|██▊ | 14/50 [00:15<00:36, 1.01s/it] 30%|███ | 15/50 [00:16<00:35, 1.01s/it] 32%|███▏ | 16/50 [00:17<00:34, 1.01s/it] 34%|███▍ | 17/50 [00:18<00:33, 1.01s/it] 36%|███▌ | 18/50 [00:19<00:32, 1.01s/it] 38%|███▊ | 19/50 [00:20<00:31, 1.01s/it] 40%|████ | 20/50 [00:21<00:30, 1.01s/it] 42%|████▏ | 21/50 [00:22<00:29, 1.01s/it] 44%|████▍ | 22/50 [00:23<00:28, 1.01s/it] 46%|████▌ | 23/50 [00:24<00:27, 1.01s/it] 48%|████▊ | 24/50 [00:25<00:26, 1.01s/it] 50%|█████ | 25/50 [00:26<00:25, 1.01s/it] 52%|█████▏ | 26/50 [00:27<00:24, 1.01s/it] 54%|█████▍ | 27/50 [00:28<00:23, 1.01s/it] 56%|█████▌ | 28/50 [00:29<00:22, 1.01s/it] 58%|█████▊ | 29/50 [00:30<00:21, 1.00s/it] 60%|██████ | 30/50 [00:31<00:20, 1.00s/it] 62%|██████▏ | 31/50 [00:32<00:19, 1.00s/it] 64%|██████▍ | 32/50 [00:33<00:18, 1.00s/it] 66%|██████▌ | 33/50 [00:34<00:17, 1.00s/it] 68%|██████▊ | 34/50 [00:35<00:15, 1.00it/s] 70%|███████ | 35/50 [00:36<00:14, 1.00it/s] 72%|███████▏ | 36/50 [00:37<00:13, 1.01it/s] 74%|███████▍ | 37/50 [00:38<00:12, 1.01it/s] 76%|███████▌ | 38/50 [00:39<00:11, 1.01it/s] 78%|███████▊ | 39/50 [00:40<00:10, 1.01it/s] 80%|████████ | 40/50 [00:41<00:09, 1.00it/s] 82%|████████▏ | 41/50 [00:42<00:08, 1.01it/s] 84%|████████▍ | 42/50 [00:43<00:07, 1.01it/s] 86%|████████▌ | 43/50 [00:44<00:06, 1.01it/s] 88%|████████▊ | 44/50 [00:45<00:05, 1.01it/s] 90%|█████████ | 45/50 [00:46<00:04, 1.01it/s] 92%|█████████▏| 46/50 [00:47<00:03, 1.01it/s] 94%|█████████▍| 47/50 [00:48<00:02, 1.02it/s] 96%|█████████▌| 48/50 [00:49<00:01, 1.02it/s] 98%|█████████▊| 49/50 [00:50<00:00, 1.02it/s] 100%|██████████| 50/50 [00:50<00:00, 1.02it/s] 100%|██████████| 50/50 [00:50<00:00, 1.02s/it] Decoding latents in cuda:0... done in 1.72s Move latents to cpu... done in 0.02s