tungsten-logo
Sign In
mohawk-xl
mohawk-xl

mohawk-xl

8 stars
Version: v2.0
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/8477faca91fd47d6ae6b1759d093b4a1/00000-2764314057.webp
https://files.tungsten.run/uploads/3775829a9e544871b6b3b2c01c81c794/00001-2764314058.webp
https://files.tungsten.run/uploads/b68d06ed6c8a4179a093ba3da344349d/00002-2764314059.webp
This example was created by evevalentine2017
Finished in 53.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: View from head to waist, capture the ethereal dance of light and shadow in a stunning monochromatic photograph with selective color details, revealing the hidden poetry of an old man's face, ultra-sharp focus, highly detailed, 8k UHD, vibrant color, intricate, extremely beautiful, aesthetic quality, full composition, dramatic cinematic, elegant, pristine, dynamic Full negative prompt: (humans:2), blurry, blurred, amateur, ugly, low quality, sketch, low resolution, warped, crooked, deformed, cartoony, low detail, long street, (rounded architecture:0.5), 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, yellow eyes, arnold signature 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:01<00:48, 1.24s/it] 5%|▌ | 2/40 [00:02<00:46, 1.23s/it] 8%|▊ | 3/40 [00:03<00:45, 1.23s/it] 10%|█ | 4/40 [00:04<00:44, 1.23s/it] 12%|█▎ | 5/40 [00:06<00:43, 1.23s/it] 15%|█▌ | 6/40 [00:07<00:41, 1.23s/it] 18%|█▊ | 7/40 [00:08<00:40, 1.23s/it] 20%|██ | 8/40 [00:09<00:39, 1.23s/it] 22%|██▎ | 9/40 [00:11<00:38, 1.24s/it] 25%|██▌ | 10/40 [00:12<00:37, 1.24s/it] 28%|██▊ | 11/40 [00:13<00:35, 1.24s/it] 30%|███ | 12/40 [00:14<00:34, 1.24s/it] 32%|███▎ | 13/40 [00:16<00:33, 1.24s/it] 35%|███▌ | 14/40 [00:17<00:32, 1.24s/it] 38%|███▊ | 15/40 [00:18<00:31, 1.24s/it] 40%|████ | 16/40 [00:19<00:29, 1.24s/it] 42%|████▎ | 17/40 [00:21<00:28, 1.24s/it] 45%|████▌ | 18/40 [00:22<00:27, 1.25s/it] 48%|████▊ | 19/40 [00:23<00:26, 1.25s/it] 50%|█████ | 20/40 [00:24<00:24, 1.25s/it] 52%|█████▎ | 21/40 [00:26<00:23, 1.25s/it] 55%|█████▌ | 22/40 [00:27<00:22, 1.25s/it] 57%|█████▊ | 23/40 [00:28<00:21, 1.25s/it] 60%|██████ | 24/40 [00:29<00:19, 1.25s/it] 62%|██████▎ | 25/40 [00:31<00:18, 1.25s/it] 65%|██████▌ | 26/40 [00:32<00:17, 1.25s/it] 68%|██████▊ | 27/40 [00:33<00:16, 1.26s/it] 70%|███████ | 28/40 [00:34<00:15, 1.25s/it] 72%|███████▎ | 29/40 [00:36<00:13, 1.25s/it] 75%|███████▌ | 30/40 [00:37<00:12, 1.26s/it] 78%|███████▊ | 31/40 [00:38<00:11, 1.25s/it] 80%|████████ | 32/40 [00:39<00:10, 1.25s/it] 82%|████████▎ | 33/40 [00:41<00:08, 1.25s/it] 85%|████████▌ | 34/40 [00:42<00:07, 1.25s/it] 88%|████████▊ | 35/40 [00:43<00:06, 1.25s/it] 90%|█████████ | 36/40 [00:44<00:04, 1.25s/it] 92%|█████████▎| 37/40 [00:46<00:03, 1.25s/it] 95%|█████████▌| 38/40 [00:47<00:02, 1.25s/it] 98%|█████████▊| 39/40 [00:48<00:01, 1.24s/it] 100%|██████████| 40/40 [00:49<00:00, 1.24s/it] 100%|██████████| 40/40 [00:49<00:00, 1.24s/it] Decoding latents in cuda:0... done in 2.37s Move latents to cpu... done in 0.03s 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/8477faca91fd47d6ae6b1759d093b4a1/00000-2764314057.webp
https://files.tungsten.run/uploads/3775829a9e544871b6b3b2c01c81c794/00001-2764314058.webp
https://files.tungsten.run/uploads/b68d06ed6c8a4179a093ba3da344349d/00002-2764314059.webp
This example was created by evevalentine2017
Finished in 53.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: View from head to waist, capture the ethereal dance of light and shadow in a stunning monochromatic photograph with selective color details, revealing the hidden poetry of an old man's face, ultra-sharp focus, highly detailed, 8k UHD, vibrant color, intricate, extremely beautiful, aesthetic quality, full composition, dramatic cinematic, elegant, pristine, dynamic Full negative prompt: (humans:2), blurry, blurred, amateur, ugly, low quality, sketch, low resolution, warped, crooked, deformed, cartoony, low detail, long street, (rounded architecture:0.5), 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, yellow eyes, arnold signature 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:01<00:48, 1.24s/it] 5%|▌ | 2/40 [00:02<00:46, 1.23s/it] 8%|▊ | 3/40 [00:03<00:45, 1.23s/it] 10%|█ | 4/40 [00:04<00:44, 1.23s/it] 12%|█▎ | 5/40 [00:06<00:43, 1.23s/it] 15%|█▌ | 6/40 [00:07<00:41, 1.23s/it] 18%|█▊ | 7/40 [00:08<00:40, 1.23s/it] 20%|██ | 8/40 [00:09<00:39, 1.23s/it] 22%|██▎ | 9/40 [00:11<00:38, 1.24s/it] 25%|██▌ | 10/40 [00:12<00:37, 1.24s/it] 28%|██▊ | 11/40 [00:13<00:35, 1.24s/it] 30%|███ | 12/40 [00:14<00:34, 1.24s/it] 32%|███▎ | 13/40 [00:16<00:33, 1.24s/it] 35%|███▌ | 14/40 [00:17<00:32, 1.24s/it] 38%|███▊ | 15/40 [00:18<00:31, 1.24s/it] 40%|████ | 16/40 [00:19<00:29, 1.24s/it] 42%|████▎ | 17/40 [00:21<00:28, 1.24s/it] 45%|████▌ | 18/40 [00:22<00:27, 1.25s/it] 48%|████▊ | 19/40 [00:23<00:26, 1.25s/it] 50%|█████ | 20/40 [00:24<00:24, 1.25s/it] 52%|█████▎ | 21/40 [00:26<00:23, 1.25s/it] 55%|█████▌ | 22/40 [00:27<00:22, 1.25s/it] 57%|█████▊ | 23/40 [00:28<00:21, 1.25s/it] 60%|██████ | 24/40 [00:29<00:19, 1.25s/it] 62%|██████▎ | 25/40 [00:31<00:18, 1.25s/it] 65%|██████▌ | 26/40 [00:32<00:17, 1.25s/it] 68%|██████▊ | 27/40 [00:33<00:16, 1.26s/it] 70%|███████ | 28/40 [00:34<00:15, 1.25s/it] 72%|███████▎ | 29/40 [00:36<00:13, 1.25s/it] 75%|███████▌ | 30/40 [00:37<00:12, 1.26s/it] 78%|███████▊ | 31/40 [00:38<00:11, 1.25s/it] 80%|████████ | 32/40 [00:39<00:10, 1.25s/it] 82%|████████▎ | 33/40 [00:41<00:08, 1.25s/it] 85%|████████▌ | 34/40 [00:42<00:07, 1.25s/it] 88%|████████▊ | 35/40 [00:43<00:06, 1.25s/it] 90%|█████████ | 36/40 [00:44<00:04, 1.25s/it] 92%|█████████▎| 37/40 [00:46<00:03, 1.25s/it] 95%|█████████▌| 38/40 [00:47<00:02, 1.25s/it] 98%|█████████▊| 39/40 [00:48<00:01, 1.24s/it] 100%|██████████| 40/40 [00:49<00:00, 1.24s/it] 100%|██████████| 40/40 [00:49<00:00, 1.24s/it] Decoding latents in cuda:0... done in 2.37s Move latents to cpu... done in 0.03s Uploading outputs... Finished.