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/e9315f478535420f98d664baa45f96f4/00000-2091981800.webp
https://files.tungsten.run/uploads/fff674554a6a4e378f537a549dc9cd32/00001-2091981801.webp
https://files.tungsten.run/uploads/fccf2042b8c2492a8f2c856d54cababe/00002-2091981802.webp
This example was created by evevalentine2017
Finished in 173.7 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: ruined ancient cities of Mars, two moons, hdr, intricate details, art drawing by Jean-Baptiste Monge, by Santiago Caruso, by Tracey Adams, by Wayne Barlowe, ((vivid colors)) Full negative prompt: ((trees)), 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%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:02<02:38, 2.68s/it] 3%|▎ | 2/60 [00:05<02:35, 2.69s/it] 5%|▌ | 3/60 [00:08<02:33, 2.69s/it] 7%|▋ | 4/60 [00:10<02:31, 2.70s/it] 8%|▊ | 5/60 [00:13<02:28, 2.71s/it] 10%|█ | 6/60 [00:16<02:26, 2.71s/it] 12%|█▏ | 7/60 [00:18<02:23, 2.71s/it] 13%|█▎ | 8/60 [00:21<02:21, 2.72s/it] 15%|█▌ | 9/60 [00:24<02:19, 2.73s/it] 17%|█▋ | 10/60 [00:27<02:16, 2.73s/it] 18%|█▊ | 11/60 [00:29<02:14, 2.74s/it] 20%|██ | 12/60 [00:32<02:11, 2.75s/it] 22%|██▏ | 13/60 [00:35<02:09, 2.75s/it] 23%|██▎ | 14/60 [00:38<02:06, 2.76s/it] 25%|██▌ | 15/60 [00:41<02:04, 2.77s/it] 27%|██▋ | 16/60 [00:43<02:02, 2.77s/it] 28%|██▊ | 17/60 [00:46<01:59, 2.78s/it] 30%|███ | 18/60 [00:49<01:56, 2.78s/it] 32%|███▏ | 19/60 [00:52<01:54, 2.78s/it] 33%|███▎ | 20/60 [00:54<01:51, 2.79s/it] 35%|███▌ | 21/60 [00:57<01:48, 2.78s/it] 37%|███▋ | 22/60 [01:00<01:46, 2.80s/it] 38%|███▊ | 23/60 [01:03<01:43, 2.81s/it] 40%|████ | 24/60 [01:06<01:41, 2.81s/it] 42%|████▏ | 25/60 [01:09<01:38, 2.82s/it] 43%|████▎ | 26/60 [01:11<01:35, 2.82s/it] 45%|████▌ | 27/60 [01:14<01:33, 2.82s/it] 47%|████▋ | 28/60 [01:17<01:30, 2.82s/it] 48%|████▊ | 29/60 [01:20<01:27, 2.81s/it] 50%|█████ | 30/60 [01:23<01:24, 2.81s/it] 52%|█████▏ | 31/60 [01:25<01:21, 2.81s/it] 53%|█████▎ | 32/60 [01:28<01:18, 2.80s/it] 55%|█████▌ | 33/60 [01:31<01:15, 2.80s/it] 57%|█████▋ | 34/60 [01:34<01:12, 2.80s/it] 58%|█████▊ | 35/60 [01:37<01:09, 2.80s/it] 60%|██████ | 36/60 [01:39<01:07, 2.79s/it] 62%|██████▏ | 37/60 [01:42<01:04, 2.79s/it] 63%|██████▎ | 38/60 [01:45<01:01, 2.79s/it] 65%|██████▌ | 39/60 [01:48<00:58, 2.79s/it] 67%|██████▋ | 40/60 [01:51<00:55, 2.79s/it] 68%|██████▊ | 41/60 [01:53<00:52, 2.79s/it] 70%|███████ | 42/60 [01:56<00:50, 2.79s/it] 72%|███████▏ | 43/60 [01:59<00:47, 2.79s/it] 73%|███████▎ | 44/60 [02:02<00:44, 2.79s/it] 75%|███████▌ | 45/60 [02:04<00:41, 2.79s/it] 77%|███████▋ | 46/60 [02:07<00:39, 2.79s/it] 78%|███████▊ | 47/60 [02:10<00:36, 2.79s/it] 80%|████████ | 48/60 [02:13<00:33, 2.79s/it] 82%|████████▏ | 49/60 [02:16<00:30, 2.79s/it] 83%|████████▎ | 50/60 [02:18<00:27, 2.80s/it] 85%|████████▌ | 51/60 [02:21<00:25, 2.80s/it] 87%|████████▋ | 52/60 [02:24<00:22, 2.80s/it] 88%|████████▊ | 53/60 [02:27<00:19, 2.80s/it] 90%|█████████ | 54/60 [02:30<00:16, 2.80s/it] 92%|█████████▏| 55/60 [02:32<00:14, 2.80s/it] 93%|█████████▎| 56/60 [02:35<00:11, 2.81s/it] 95%|█████████▌| 57/60 [02:38<00:08, 2.81s/it] 97%|█████████▋| 58/60 [02:41<00:05, 2.81s/it] 98%|█████████▊| 59/60 [02:44<00:02, 2.81s/it] 100%|██████████| 60/60 [02:47<00:00, 2.81s/it] 100%|██████████| 60/60 [02:47<00:00, 2.78s/it] Decoding latents in cuda:0... done in 5.18s Move latents to cpu... done in 0.06s 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/e9315f478535420f98d664baa45f96f4/00000-2091981800.webp
https://files.tungsten.run/uploads/fff674554a6a4e378f537a549dc9cd32/00001-2091981801.webp
https://files.tungsten.run/uploads/fccf2042b8c2492a8f2c856d54cababe/00002-2091981802.webp
This example was created by evevalentine2017
Finished in 173.7 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: ruined ancient cities of Mars, two moons, hdr, intricate details, art drawing by Jean-Baptiste Monge, by Santiago Caruso, by Tracey Adams, by Wayne Barlowe, ((vivid colors)) Full negative prompt: ((trees)), 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%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:02<02:38, 2.68s/it] 3%|▎ | 2/60 [00:05<02:35, 2.69s/it] 5%|▌ | 3/60 [00:08<02:33, 2.69s/it] 7%|▋ | 4/60 [00:10<02:31, 2.70s/it] 8%|▊ | 5/60 [00:13<02:28, 2.71s/it] 10%|█ | 6/60 [00:16<02:26, 2.71s/it] 12%|█▏ | 7/60 [00:18<02:23, 2.71s/it] 13%|█▎ | 8/60 [00:21<02:21, 2.72s/it] 15%|█▌ | 9/60 [00:24<02:19, 2.73s/it] 17%|█▋ | 10/60 [00:27<02:16, 2.73s/it] 18%|█▊ | 11/60 [00:29<02:14, 2.74s/it] 20%|██ | 12/60 [00:32<02:11, 2.75s/it] 22%|██▏ | 13/60 [00:35<02:09, 2.75s/it] 23%|██▎ | 14/60 [00:38<02:06, 2.76s/it] 25%|██▌ | 15/60 [00:41<02:04, 2.77s/it] 27%|██▋ | 16/60 [00:43<02:02, 2.77s/it] 28%|██▊ | 17/60 [00:46<01:59, 2.78s/it] 30%|███ | 18/60 [00:49<01:56, 2.78s/it] 32%|███▏ | 19/60 [00:52<01:54, 2.78s/it] 33%|███▎ | 20/60 [00:54<01:51, 2.79s/it] 35%|███▌ | 21/60 [00:57<01:48, 2.78s/it] 37%|███▋ | 22/60 [01:00<01:46, 2.80s/it] 38%|███▊ | 23/60 [01:03<01:43, 2.81s/it] 40%|████ | 24/60 [01:06<01:41, 2.81s/it] 42%|████▏ | 25/60 [01:09<01:38, 2.82s/it] 43%|████▎ | 26/60 [01:11<01:35, 2.82s/it] 45%|████▌ | 27/60 [01:14<01:33, 2.82s/it] 47%|████▋ | 28/60 [01:17<01:30, 2.82s/it] 48%|████▊ | 29/60 [01:20<01:27, 2.81s/it] 50%|█████ | 30/60 [01:23<01:24, 2.81s/it] 52%|█████▏ | 31/60 [01:25<01:21, 2.81s/it] 53%|█████▎ | 32/60 [01:28<01:18, 2.80s/it] 55%|█████▌ | 33/60 [01:31<01:15, 2.80s/it] 57%|█████▋ | 34/60 [01:34<01:12, 2.80s/it] 58%|█████▊ | 35/60 [01:37<01:09, 2.80s/it] 60%|██████ | 36/60 [01:39<01:07, 2.79s/it] 62%|██████▏ | 37/60 [01:42<01:04, 2.79s/it] 63%|██████▎ | 38/60 [01:45<01:01, 2.79s/it] 65%|██████▌ | 39/60 [01:48<00:58, 2.79s/it] 67%|██████▋ | 40/60 [01:51<00:55, 2.79s/it] 68%|██████▊ | 41/60 [01:53<00:52, 2.79s/it] 70%|███████ | 42/60 [01:56<00:50, 2.79s/it] 72%|███████▏ | 43/60 [01:59<00:47, 2.79s/it] 73%|███████▎ | 44/60 [02:02<00:44, 2.79s/it] 75%|███████▌ | 45/60 [02:04<00:41, 2.79s/it] 77%|███████▋ | 46/60 [02:07<00:39, 2.79s/it] 78%|███████▊ | 47/60 [02:10<00:36, 2.79s/it] 80%|████████ | 48/60 [02:13<00:33, 2.79s/it] 82%|████████▏ | 49/60 [02:16<00:30, 2.79s/it] 83%|████████▎ | 50/60 [02:18<00:27, 2.80s/it] 85%|████████▌ | 51/60 [02:21<00:25, 2.80s/it] 87%|████████▋ | 52/60 [02:24<00:22, 2.80s/it] 88%|████████▊ | 53/60 [02:27<00:19, 2.80s/it] 90%|█████████ | 54/60 [02:30<00:16, 2.80s/it] 92%|█████████▏| 55/60 [02:32<00:14, 2.80s/it] 93%|█████████▎| 56/60 [02:35<00:11, 2.81s/it] 95%|█████████▌| 57/60 [02:38<00:08, 2.81s/it] 97%|█████████▋| 58/60 [02:41<00:05, 2.81s/it] 98%|█████████▊| 59/60 [02:44<00:02, 2.81s/it] 100%|██████████| 60/60 [02:47<00:00, 2.81s/it] 100%|██████████| 60/60 [02:47<00:00, 2.78s/it] Decoding latents in cuda:0... done in 5.18s Move latents to cpu... done in 0.06s Uploading outputs... Finished.