tungsten-logo
Sign In
allys-mix-x-sdxl
allys-mix-x-sdxl

allys-mix-x-sdxl

12 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/07f4e496d07248d7bf5fc72bb08027cb/00000-1513085771.webp
https://files.tungsten.run/uploads/3bd243d82daa4681a03c5a0eb9c48c14/00001-1513085772.webp
https://files.tungsten.run/uploads/81d3918854124ccebcb4735fc43bca7a/00002-1513085773.webp
This example was created by evevalentine2017
Finished in 76.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: biomechanical style biomechanical cyberpunk breathtaking professional, high quality sketch of (The Dracarys dragon's Lair, A deadly place where fearsome dragons dwell, shiny chrome, glossy steel :1.01), radiant light rays, street level view,crystalline, 8k resolution, detailed, focused, (style of fabian perez:0.1), award-winning, professional, highly detailed . cybernetics, human-machine fusion, dystopian, organic meets artificial, dark, intricate, highly detailed . blend of organic and mechanical elements, futuristic, cybernetic, detailed, intricate, <lora:tweak-detail-xl:1.5> Full negative prompt: grainy, blurry, pixelated, (bad quality, worst quality, low quality, poorly drawn, normal quality:1.3), childish, haze, oil painting, painting, ugly, deformed, noisy, blurry, distorted, grainy, natural, colorful, deformed, sketch, low contrast, watercolor, natural, rustic, primitive, organic, simplistic 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:04<01:17, 4.08s/it] 10%|█ | 2/20 [00:07<01:07, 3.76s/it] 15%|█▌ | 3/20 [00:11<01:03, 3.73s/it] 20%|██ | 4/20 [00:15<01:00, 3.75s/it] 25%|██▌ | 5/20 [00:18<00:55, 3.68s/it] 30%|███ | 6/20 [00:22<00:52, 3.78s/it] 35%|███▌ | 7/20 [00:27<00:54, 4.23s/it] 40%|████ | 8/20 [00:31<00:48, 4.04s/it] 45%|████▌ | 9/20 [00:35<00:43, 3.93s/it] 50%|█████ | 10/20 [00:38<00:38, 3.81s/it] 55%|█████▌ | 11/20 [00:42<00:33, 3.67s/it] 60%|██████ | 12/20 [00:45<00:28, 3.59s/it] 65%|██████▌ | 13/20 [00:48<00:25, 3.58s/it] 70%|███████ | 14/20 [00:52<00:21, 3.52s/it] 75%|███████▌ | 15/20 [00:55<00:17, 3.52s/it] 80%|████████ | 16/20 [00:59<00:13, 3.45s/it] 85%|████████▌ | 17/20 [01:02<00:10, 3.40s/it] 90%|█████████ | 18/20 [01:05<00:06, 3.32s/it] 95%|█████████▌| 19/20 [01:07<00:02, 3.00s/it] 100%|██████████| 20/20 [01:09<00:00, 2.61s/it] 100%|██████████| 20/20 [01:09<00:00, 3.48s/it] Decoding latents in cuda:0... done in 3.23s Move latents to cpu... done in 0.04s 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/07f4e496d07248d7bf5fc72bb08027cb/00000-1513085771.webp
https://files.tungsten.run/uploads/3bd243d82daa4681a03c5a0eb9c48c14/00001-1513085772.webp
https://files.tungsten.run/uploads/81d3918854124ccebcb4735fc43bca7a/00002-1513085773.webp
This example was created by evevalentine2017
Finished in 76.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: biomechanical style biomechanical cyberpunk breathtaking professional, high quality sketch of (The Dracarys dragon's Lair, A deadly place where fearsome dragons dwell, shiny chrome, glossy steel :1.01), radiant light rays, street level view,crystalline, 8k resolution, detailed, focused, (style of fabian perez:0.1), award-winning, professional, highly detailed . cybernetics, human-machine fusion, dystopian, organic meets artificial, dark, intricate, highly detailed . blend of organic and mechanical elements, futuristic, cybernetic, detailed, intricate, <lora:tweak-detail-xl:1.5> Full negative prompt: grainy, blurry, pixelated, (bad quality, worst quality, low quality, poorly drawn, normal quality:1.3), childish, haze, oil painting, painting, ugly, deformed, noisy, blurry, distorted, grainy, natural, colorful, deformed, sketch, low contrast, watercolor, natural, rustic, primitive, organic, simplistic 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:04<01:17, 4.08s/it] 10%|█ | 2/20 [00:07<01:07, 3.76s/it] 15%|█▌ | 3/20 [00:11<01:03, 3.73s/it] 20%|██ | 4/20 [00:15<01:00, 3.75s/it] 25%|██▌ | 5/20 [00:18<00:55, 3.68s/it] 30%|███ | 6/20 [00:22<00:52, 3.78s/it] 35%|███▌ | 7/20 [00:27<00:54, 4.23s/it] 40%|████ | 8/20 [00:31<00:48, 4.04s/it] 45%|████▌ | 9/20 [00:35<00:43, 3.93s/it] 50%|█████ | 10/20 [00:38<00:38, 3.81s/it] 55%|█████▌ | 11/20 [00:42<00:33, 3.67s/it] 60%|██████ | 12/20 [00:45<00:28, 3.59s/it] 65%|██████▌ | 13/20 [00:48<00:25, 3.58s/it] 70%|███████ | 14/20 [00:52<00:21, 3.52s/it] 75%|███████▌ | 15/20 [00:55<00:17, 3.52s/it] 80%|████████ | 16/20 [00:59<00:13, 3.45s/it] 85%|████████▌ | 17/20 [01:02<00:10, 3.40s/it] 90%|█████████ | 18/20 [01:05<00:06, 3.32s/it] 95%|█████████▌| 19/20 [01:07<00:02, 3.00s/it] 100%|██████████| 20/20 [01:09<00:00, 2.61s/it] 100%|██████████| 20/20 [01:09<00:00, 3.48s/it] Decoding latents in cuda:0... done in 3.23s Move latents to cpu... done in 0.04s Uploading outputs... Finished.