tungsten-logo
Sign In
Forgotten Castles with Realistic Freedom XL
realistic-freedom-xl:v1.0
evevalentine2017
evevalentine2017
·
Feb 1
355
Input
prompt
Specify things to see in the output
(masterpiece:1.2), best quality, high resolution, unity 8k wallpaper,(illustration:1), perfect lighting, scene concept, FantacyWorld, Grand scenes, ink paintings, (lava landforms), (magma everywhere), heat waves rolling everywhere, and a mysterious castle built against the mountain in a harsh environment, with large stone pagodas as the main elements, layer by layer upwards, forming a rich architectural space, (like the scene in the Tomb Raider). The well-designed and clear facade details, ancient architecture, stunning scenes, vivid light and shadow, movie atmosphere, and dramatic composition are all in place, Award winning illustration design, wide-angle lens, masterpiece, best quality, ultra realistic, realistic shadows, exquisite details, 8K, HDR, UHD, 8k, detailed, hyper realistic, shot with cinematic camera, realistic fur texture, sharp lines, raw photo, 4k, Fujifilm XT3, realistic, real photo, detailed, textured, realistic textures, bright light, [desaturated], warm colors, 8k, 16k, HDR, f.1/2, 70mm lens, Kodak, Analog style
negative_prompt
Specify things to not see in the output
low quality, low resolution, watermark, image artifacts, child, loli, underage, teen, young, young face, loli face, lolicon, flat chest, cub, small, short ,babyface, tiny, nude, naked, cartoon, comic, painting, sketch, anime, manga, 3D, nsfw,
num_outputs
Number of output images
3
width
Output image width
768
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
1
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.
-1
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 SDE Karras
samping_steps
Number of denoising steps
32
cfg_scale
Scale for classifier-free guidance
4
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
None
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)
negative_hand-neg.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
ng_deepnegative_v1_75t.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
EasyNegativeV2.safetensors
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
Output
https://files.tungsten.run/uploads/077ff21780c94caab628d50cfe9aa950/00000-2043095680.webp
https://files.tungsten.run/uploads/097d4fc2211749998cf78f52760f7085/00001-2043095681.webp
https://files.tungsten.run/uploads/f21ca068f0d040ddbdd1c459dfcfb7e9/00002-2043095682.webp
Finished in 66.5 seconds
Setting up the model... Preparing inputs... Processing... Using seed 2043095680 Full prompt: (masterpiece:1.2), best quality, high resolution, unity 8k wallpaper,(illustration:1), perfect lighting, scene concept, FantacyWorld, Grand scenes, ink paintings, (lava landforms), (magma everywhere), heat waves rolling everywhere, and a mysterious castle built against the mountain in a harsh environment, with large stone pagodas as the main elements, layer by layer upwards, forming a rich architectural space, (like the scene in the Tomb Raider). The well-designed and clear facade details, ancient architecture, stunning scenes, vivid light and shadow, movie atmosphere, and dramatic composition are all in place, Award winning illustration design, wide-angle lens, masterpiece, best quality, ultra realistic, realistic shadows, exquisite details, 8K, HDR, UHD, 8k, detailed, hyper realistic, shot with cinematic camera, realistic fur texture, sharp lines, raw photo, 4k, Fujifilm XT3, realistic, real photo, detailed, textured, realistic textures, bright light, [desaturated], warm colors, 8k, 16k, HDR, f.1/2, 70mm lens, Kodak, Analog style, <lora:add-detail-xl:1.0> Full negative prompt: low quality, low resolution, watermark, image artifacts, child, loli, underage, teen, young, young face, loli face, lolicon, flat chest, cub, small, short ,babyface, tiny, nude, naked, cartoon, comic, painting, sketch, anime, manga, 3D, nsfw, 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:02<01:32, 2.98s/it] 6%|▋ | 2/32 [00:05<01:12, 2.42s/it] 9%|▉ | 3/32 [00:07<01:05, 2.27s/it] 12%|█▎ | 4/32 [00:09<01:01, 2.19s/it] 16%|█▌ | 5/32 [00:11<00:58, 2.18s/it] 19%|█▉ | 6/32 [00:13<00:54, 2.10s/it] 22%|██▏ | 7/32 [00:15<00:52, 2.10s/it] 25%|██▌ | 8/32 [00:17<00:48, 2.03s/it] 28%|██▊ | 9/32 [00:19<00:47, 2.05s/it] 31%|███▏ | 10/32 [00:21<00:44, 2.04s/it] 34%|███▍ | 11/32 [00:23<00:43, 2.07s/it] 38%|███▊ | 12/32 [00:25<00:40, 2.05s/it] 41%|████ | 13/32 [00:27<00:38, 2.02s/it] 44%|████▍ | 14/32 [00:29<00:35, 1.96s/it] 47%|████▋ | 15/32 [00:31<00:32, 1.93s/it] 50%|█████ | 16/32 [00:33<00:30, 1.93s/it] 53%|█████▎ | 17/32 [00:34<00:28, 1.88s/it] 56%|█████▋ | 18/32 [00:36<00:26, 1.90s/it] 59%|█████▉ | 19/32 [00:38<00:24, 1.87s/it] 62%|██████▎ | 20/32 [00:40<00:22, 1.88s/it] 66%|██████▌ | 21/32 [00:42<00:21, 1.91s/it] 69%|██████▉ | 22/32 [00:44<00:19, 1.90s/it] 72%|███████▏ | 23/32 [00:46<00:16, 1.85s/it] 75%|███████▌ | 24/32 [00:47<00:14, 1.81s/it] 78%|███████▊ | 25/32 [00:49<00:12, 1.78s/it] 81%|████████▏ | 26/32 [00:51<00:10, 1.80s/it] 84%|████████▍ | 27/32 [00:53<00:08, 1.78s/it] 88%|████████▊ | 28/32 [00:54<00:07, 1.80s/it] 91%|█████████ | 29/32 [00:56<00:05, 1.79s/it] 94%|█████████▍| 30/32 [00:58<00:03, 1.73s/it] 97%|█████████▋| 31/32 [00:59<00:01, 1.51s/it] 100%|██████████| 32/32 [01:00<00:00, 1.33s/it] 100%|██████████| 32/32 [01:00<00:00, 1.88s/it] Decoding latents in cuda:0... done in 1.76s Move latents to cpu... done in 0.02s Uploading outputs... Finished.
prompt
Specify things to see in the output
(masterpiece:1.2), best quality, high resolution, unity 8k wallpaper,(illustration:1), perfect lighting, scene concept, FantacyWorld, Grand scenes, ink paintings, (lava landforms), (magma everywhere), heat waves rolling everywhere, and a mysterious castle built against the mountain in a harsh environment, with large stone pagodas as the main elements, layer by layer upwards, forming a rich architectural space, (like the scene in the Tomb Raider). The well-designed and clear facade details, ancient architecture, stunning scenes, vivid light and shadow, movie atmosphere, and dramatic composition are all in place, Award winning illustration design, wide-angle lens, masterpiece, best quality, ultra realistic, realistic shadows, exquisite details, 8K, HDR, UHD, 8k, detailed, hyper realistic, shot with cinematic camera, realistic fur texture, sharp lines, raw photo, 4k, Fujifilm XT3, realistic, real photo, detailed, textured, realistic textures, bright light, [desaturated], warm colors, 8k, 16k, HDR, f.1/2, 70mm lens, Kodak, Analog style
negative_prompt
Specify things to not see in the output
low quality, low resolution, watermark, image artifacts, child, loli, underage, teen, young, young face, loli face, lolicon, flat chest, cub, small, short ,babyface, tiny, nude, naked, cartoon, comic, painting, sketch, anime, manga, 3D, nsfw,
num_outputs
Number of output images
3
width
Output image width
768
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
1
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.
-1
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 SDE Karras
samping_steps
Number of denoising steps
32
cfg_scale
Scale for classifier-free guidance
4
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
None
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)
negative_hand-neg.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
ng_deepnegative_v1_75t.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
EasyNegativeV2.safetensors
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/077ff21780c94caab628d50cfe9aa950/00000-2043095680.webp
https://files.tungsten.run/uploads/097d4fc2211749998cf78f52760f7085/00001-2043095681.webp
https://files.tungsten.run/uploads/f21ca068f0d040ddbdd1c459dfcfb7e9/00002-2043095682.webp
Finished in 66.5 seconds
Setting up the model... Preparing inputs... Processing... Using seed 2043095680 Full prompt: (masterpiece:1.2), best quality, high resolution, unity 8k wallpaper,(illustration:1), perfect lighting, scene concept, FantacyWorld, Grand scenes, ink paintings, (lava landforms), (magma everywhere), heat waves rolling everywhere, and a mysterious castle built against the mountain in a harsh environment, with large stone pagodas as the main elements, layer by layer upwards, forming a rich architectural space, (like the scene in the Tomb Raider). The well-designed and clear facade details, ancient architecture, stunning scenes, vivid light and shadow, movie atmosphere, and dramatic composition are all in place, Award winning illustration design, wide-angle lens, masterpiece, best quality, ultra realistic, realistic shadows, exquisite details, 8K, HDR, UHD, 8k, detailed, hyper realistic, shot with cinematic camera, realistic fur texture, sharp lines, raw photo, 4k, Fujifilm XT3, realistic, real photo, detailed, textured, realistic textures, bright light, [desaturated], warm colors, 8k, 16k, HDR, f.1/2, 70mm lens, Kodak, Analog style, <lora:add-detail-xl:1.0> Full negative prompt: low quality, low resolution, watermark, image artifacts, child, loli, underage, teen, young, young face, loli face, lolicon, flat chest, cub, small, short ,babyface, tiny, nude, naked, cartoon, comic, painting, sketch, anime, manga, 3D, nsfw, 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:02<01:32, 2.98s/it] 6%|▋ | 2/32 [00:05<01:12, 2.42s/it] 9%|▉ | 3/32 [00:07<01:05, 2.27s/it] 12%|█▎ | 4/32 [00:09<01:01, 2.19s/it] 16%|█▌ | 5/32 [00:11<00:58, 2.18s/it] 19%|█▉ | 6/32 [00:13<00:54, 2.10s/it] 22%|██▏ | 7/32 [00:15<00:52, 2.10s/it] 25%|██▌ | 8/32 [00:17<00:48, 2.03s/it] 28%|██▊ | 9/32 [00:19<00:47, 2.05s/it] 31%|███▏ | 10/32 [00:21<00:44, 2.04s/it] 34%|███▍ | 11/32 [00:23<00:43, 2.07s/it] 38%|███▊ | 12/32 [00:25<00:40, 2.05s/it] 41%|████ | 13/32 [00:27<00:38, 2.02s/it] 44%|████▍ | 14/32 [00:29<00:35, 1.96s/it] 47%|████▋ | 15/32 [00:31<00:32, 1.93s/it] 50%|█████ | 16/32 [00:33<00:30, 1.93s/it] 53%|█████▎ | 17/32 [00:34<00:28, 1.88s/it] 56%|█████▋ | 18/32 [00:36<00:26, 1.90s/it] 59%|█████▉ | 19/32 [00:38<00:24, 1.87s/it] 62%|██████▎ | 20/32 [00:40<00:22, 1.88s/it] 66%|██████▌ | 21/32 [00:42<00:21, 1.91s/it] 69%|██████▉ | 22/32 [00:44<00:19, 1.90s/it] 72%|███████▏ | 23/32 [00:46<00:16, 1.85s/it] 75%|███████▌ | 24/32 [00:47<00:14, 1.81s/it] 78%|███████▊ | 25/32 [00:49<00:12, 1.78s/it] 81%|████████▏ | 26/32 [00:51<00:10, 1.80s/it] 84%|████████▍ | 27/32 [00:53<00:08, 1.78s/it] 88%|████████▊ | 28/32 [00:54<00:07, 1.80s/it] 91%|█████████ | 29/32 [00:56<00:05, 1.79s/it] 94%|█████████▍| 30/32 [00:58<00:03, 1.73s/it] 97%|█████████▋| 31/32 [00:59<00:01, 1.51s/it] 100%|██████████| 32/32 [01:00<00:00, 1.33s/it] 100%|██████████| 32/32 [01:00<00:00, 1.88s/it] Decoding latents in cuda:0... done in 1.76s Move latents to cpu... done in 0.02s Uploading outputs... Finished.