tungsten-logo
Sign In
Ancient Egypt with Mohawk XL
mohawk-xl:v2.0
evevalentine2017
evevalentine2017
·
Feb 1
400
Input
prompt
Specify things to see in the output
cinematic ground view of landscape of ancient Egypt, (houses:1), 3 pyramids, harmonious, (sandy paths:1.5), (sphinxes:1.5), (statues:1.5), (temples:1.4), (desert:1.1), (ultra realistic:1.2), sandstorm in background, shallow depth of field, vignette, high budget, bokeh, cinemascope, moody, epic, gorgeous, Every element is rendered in extreme quality, aiming for an ultra-HD 8K resolution level of detail. The cinematic and hyperrealistic style makes it feel like a freeze-frame from a high-budget dark fantasy film. The use of film grain adds a texture that gives the scene a gritty, realistic feel, ((vivid colors))
negative_prompt
Specify things to not see in the output
((more than 3 pyramids: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
num_outputs
Number of output images
3
width
Output image width
2024
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2351922215
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M
samping_steps
Number of denoising steps
60
cfg_scale
Scale for classifier-free guidance
4
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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.
false
Output
https://files.tungsten.run/uploads/b4fe06161f764dd2a021f9c5a9d4d0c7/00000-2351922215.webp
https://files.tungsten.run/uploads/333c6e2e7ade487b8ffd0f6db616a0aa/00001-2351922216.webp
https://files.tungsten.run/uploads/c77e5698004b4135aa384610dd3a862f/00002-2351922217.webp
Finished in 189.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: cinematic ground view of landscape of ancient Egypt, (houses:1), 3 pyramids, harmonious, (sandy paths:1.5), (sphinxes:1.5), (statues:1.5), (temples:1.4), (desert:1.1), (ultra realistic:1.2), sandstorm in background, shallow depth of field, vignette, high budget, bokeh, cinemascope, moody, epic, gorgeous, Every element is rendered in extreme quality, aiming for an ultra-HD 8K resolution level of detail. The cinematic and hyperrealistic style makes it feel like a freeze-frame from a high-budget dark fantasy film. The use of film grain adds a texture that gives the scene a gritty, realistic feel, ((vivid colors)) Full negative prompt: ((more than 3 pyramids: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%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:02<02:54, 2.96s/it] 3%|▎ | 2/60 [00:05<02:52, 2.98s/it] 5%|▌ | 3/60 [00:08<02:50, 2.99s/it] 7%|▋ | 4/60 [00:11<02:48, 3.01s/it] 8%|▊ | 5/60 [00:15<02:45, 3.02s/it] 10%|█ | 6/60 [00:18<02:43, 3.02s/it] 12%|█▏ | 7/60 [00:21<02:40, 3.03s/it] 13%|█▎ | 8/60 [00:24<02:38, 3.04s/it] 15%|█▌ | 9/60 [00:27<02:35, 3.05s/it] 17%|█▋ | 10/60 [00:30<02:32, 3.06s/it] 18%|█▊ | 11/60 [00:33<02:30, 3.07s/it] 20%|██ | 12/60 [00:36<02:27, 3.08s/it] 22%|██▏ | 13/60 [00:39<02:24, 3.08s/it] 23%|██▎ | 14/60 [00:42<02:21, 3.08s/it] 25%|██▌ | 15/60 [00:45<02:18, 3.08s/it] 27%|██▋ | 16/60 [00:48<02:15, 3.08s/it] 28%|██▊ | 17/60 [00:51<02:12, 3.07s/it] 30%|███ | 18/60 [00:54<02:08, 3.07s/it] 32%|███▏ | 19/60 [00:57<02:05, 3.06s/it] 33%|███▎ | 20/60 [01:01<02:02, 3.06s/it] 35%|███▌ | 21/60 [01:04<01:58, 3.05s/it] 37%|███▋ | 22/60 [01:07<01:55, 3.05s/it] 38%|███▊ | 23/60 [01:10<01:52, 3.04s/it] 40%|████ | 24/60 [01:13<01:49, 3.04s/it] 42%|████▏ | 25/60 [01:16<01:46, 3.03s/it] 43%|████▎ | 26/60 [01:19<01:42, 3.03s/it] 45%|████▌ | 27/60 [01:22<01:39, 3.03s/it] 47%|████▋ | 28/60 [01:25<01:36, 3.02s/it] 48%|████▊ | 29/60 [01:28<01:33, 3.02s/it] 50%|█████ | 30/60 [01:31<01:30, 3.02s/it] 52%|█████▏ | 31/60 [01:34<01:27, 3.02s/it] 53%|█████▎ | 32/60 [01:37<01:24, 3.02s/it] 55%|█████▌ | 33/60 [01:40<01:21, 3.02s/it] 57%|█████▋ | 34/60 [01:43<01:18, 3.01s/it] 58%|█████▊ | 35/60 [01:46<01:15, 3.01s/it] 60%|██████ | 36/60 [01:49<01:12, 3.02s/it] 62%|██████▏ | 37/60 [01:52<01:09, 3.02s/it] 63%|██████▎ | 38/60 [01:55<01:06, 3.02s/it] 65%|██████▌ | 39/60 [01:58<01:03, 3.02s/it] 67%|██████▋ | 40/60 [02:01<01:00, 3.02s/it] 68%|██████▊ | 41/60 [02:04<00:57, 3.03s/it] 70%|███████ | 42/60 [02:07<00:54, 3.03s/it] 72%|███████▏ | 43/60 [02:10<00:51, 3.04s/it] 73%|███████▎ | 44/60 [02:13<00:48, 3.04s/it] 75%|███████▌ | 45/60 [02:16<00:45, 3.04s/it] 77%|███████▋ | 46/60 [02:19<00:42, 3.04s/it] 78%|███████▊ | 47/60 [02:22<00:39, 3.04s/it] 80%|████████ | 48/60 [02:25<00:36, 3.05s/it] 82%|████████▏ | 49/60 [02:28<00:33, 3.05s/it] 83%|████████▎ | 50/60 [02:31<00:30, 3.05s/it] 85%|████████▌ | 51/60 [02:34<00:27, 3.05s/it] 87%|████████▋ | 52/60 [02:38<00:24, 3.05s/it] 88%|████████▊ | 53/60 [02:41<00:21, 3.05s/it] 90%|█████████ | 54/60 [02:44<00:18, 3.04s/it] 92%|█████████▏| 55/60 [02:47<00:15, 3.04s/it] 93%|█████████▎| 56/60 [02:50<00:12, 3.04s/it] 95%|█████████▌| 57/60 [02:53<00:09, 3.04s/it] 97%|█████████▋| 58/60 [02:56<00:06, 3.04s/it] 98%|█████████▊| 59/60 [02:59<00:03, 3.04s/it] 100%|██████████| 60/60 [03:02<00:00, 3.04s/it] 100%|██████████| 60/60 [03:02<00:00, 3.04s/it] Decoding latents in cuda:0... done in 5.19s Move latents to cpu... done in 0.06s Uploading outputs... Finished.
prompt
Specify things to see in the output
cinematic ground view of landscape of ancient Egypt, (houses:1), 3 pyramids, harmonious, (sandy paths:1.5), (sphinxes:1.5), (statues:1.5), (temples:1.4), (desert:1.1), (ultra realistic:1.2), sandstorm in background, shallow depth of field, vignette, high budget, bokeh, cinemascope, moody, epic, gorgeous, Every element is rendered in extreme quality, aiming for an ultra-HD 8K resolution level of detail. The cinematic and hyperrealistic style makes it feel like a freeze-frame from a high-budget dark fantasy film. The use of film grain adds a texture that gives the scene a gritty, realistic feel, ((vivid colors))
negative_prompt
Specify things to not see in the output
((more than 3 pyramids: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
num_outputs
Number of output images
3
width
Output image width
2024
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2351922215
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M
samping_steps
Number of denoising steps
60
cfg_scale
Scale for classifier-free guidance
4
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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.
false
https://files.tungsten.run/uploads/b4fe06161f764dd2a021f9c5a9d4d0c7/00000-2351922215.webp
https://files.tungsten.run/uploads/333c6e2e7ade487b8ffd0f6db616a0aa/00001-2351922216.webp
https://files.tungsten.run/uploads/c77e5698004b4135aa384610dd3a862f/00002-2351922217.webp
Finished in 189.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: cinematic ground view of landscape of ancient Egypt, (houses:1), 3 pyramids, harmonious, (sandy paths:1.5), (sphinxes:1.5), (statues:1.5), (temples:1.4), (desert:1.1), (ultra realistic:1.2), sandstorm in background, shallow depth of field, vignette, high budget, bokeh, cinemascope, moody, epic, gorgeous, Every element is rendered in extreme quality, aiming for an ultra-HD 8K resolution level of detail. The cinematic and hyperrealistic style makes it feel like a freeze-frame from a high-budget dark fantasy film. The use of film grain adds a texture that gives the scene a gritty, realistic feel, ((vivid colors)) Full negative prompt: ((more than 3 pyramids: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%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:02<02:54, 2.96s/it] 3%|▎ | 2/60 [00:05<02:52, 2.98s/it] 5%|▌ | 3/60 [00:08<02:50, 2.99s/it] 7%|▋ | 4/60 [00:11<02:48, 3.01s/it] 8%|▊ | 5/60 [00:15<02:45, 3.02s/it] 10%|█ | 6/60 [00:18<02:43, 3.02s/it] 12%|█▏ | 7/60 [00:21<02:40, 3.03s/it] 13%|█▎ | 8/60 [00:24<02:38, 3.04s/it] 15%|█▌ | 9/60 [00:27<02:35, 3.05s/it] 17%|█▋ | 10/60 [00:30<02:32, 3.06s/it] 18%|█▊ | 11/60 [00:33<02:30, 3.07s/it] 20%|██ | 12/60 [00:36<02:27, 3.08s/it] 22%|██▏ | 13/60 [00:39<02:24, 3.08s/it] 23%|██▎ | 14/60 [00:42<02:21, 3.08s/it] 25%|██▌ | 15/60 [00:45<02:18, 3.08s/it] 27%|██▋ | 16/60 [00:48<02:15, 3.08s/it] 28%|██▊ | 17/60 [00:51<02:12, 3.07s/it] 30%|███ | 18/60 [00:54<02:08, 3.07s/it] 32%|███▏ | 19/60 [00:57<02:05, 3.06s/it] 33%|███▎ | 20/60 [01:01<02:02, 3.06s/it] 35%|███▌ | 21/60 [01:04<01:58, 3.05s/it] 37%|███▋ | 22/60 [01:07<01:55, 3.05s/it] 38%|███▊ | 23/60 [01:10<01:52, 3.04s/it] 40%|████ | 24/60 [01:13<01:49, 3.04s/it] 42%|████▏ | 25/60 [01:16<01:46, 3.03s/it] 43%|████▎ | 26/60 [01:19<01:42, 3.03s/it] 45%|████▌ | 27/60 [01:22<01:39, 3.03s/it] 47%|████▋ | 28/60 [01:25<01:36, 3.02s/it] 48%|████▊ | 29/60 [01:28<01:33, 3.02s/it] 50%|█████ | 30/60 [01:31<01:30, 3.02s/it] 52%|█████▏ | 31/60 [01:34<01:27, 3.02s/it] 53%|█████▎ | 32/60 [01:37<01:24, 3.02s/it] 55%|█████▌ | 33/60 [01:40<01:21, 3.02s/it] 57%|█████▋ | 34/60 [01:43<01:18, 3.01s/it] 58%|█████▊ | 35/60 [01:46<01:15, 3.01s/it] 60%|██████ | 36/60 [01:49<01:12, 3.02s/it] 62%|██████▏ | 37/60 [01:52<01:09, 3.02s/it] 63%|██████▎ | 38/60 [01:55<01:06, 3.02s/it] 65%|██████▌ | 39/60 [01:58<01:03, 3.02s/it] 67%|██████▋ | 40/60 [02:01<01:00, 3.02s/it] 68%|██████▊ | 41/60 [02:04<00:57, 3.03s/it] 70%|███████ | 42/60 [02:07<00:54, 3.03s/it] 72%|███████▏ | 43/60 [02:10<00:51, 3.04s/it] 73%|███████▎ | 44/60 [02:13<00:48, 3.04s/it] 75%|███████▌ | 45/60 [02:16<00:45, 3.04s/it] 77%|███████▋ | 46/60 [02:19<00:42, 3.04s/it] 78%|███████▊ | 47/60 [02:22<00:39, 3.04s/it] 80%|████████ | 48/60 [02:25<00:36, 3.05s/it] 82%|████████▏ | 49/60 [02:28<00:33, 3.05s/it] 83%|████████▎ | 50/60 [02:31<00:30, 3.05s/it] 85%|████████▌ | 51/60 [02:34<00:27, 3.05s/it] 87%|████████▋ | 52/60 [02:38<00:24, 3.05s/it] 88%|████████▊ | 53/60 [02:41<00:21, 3.05s/it] 90%|█████████ | 54/60 [02:44<00:18, 3.04s/it] 92%|█████████▏| 55/60 [02:47<00:15, 3.04s/it] 93%|█████████▎| 56/60 [02:50<00:12, 3.04s/it] 95%|█████████▌| 57/60 [02:53<00:09, 3.04s/it] 97%|█████████▋| 58/60 [02:56<00:06, 3.04s/it] 98%|█████████▊| 59/60 [02:59<00:03, 3.04s/it] 100%|██████████| 60/60 [03:02<00:00, 3.04s/it] 100%|██████████| 60/60 [03:02<00:00, 3.04s/it] Decoding latents in cuda:0... done in 5.19s Move latents to cpu... done in 0.06s Uploading outputs... Finished.