tungsten-logo
Sign In
Hillside
Hillside

Hillside

9 stars
Version: v2.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
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/a6ea7306ea9748ec92858b5c5759612e/00000-3464107305.webp
https://files.tungsten.run/uploads/340025b281e949b0affabedac4b7a9a8/00001-3464107306.webp
https://files.tungsten.run/uploads/e048ca8a26b343fcad57001810befd6f/00002-3464107307.webp
This example was created by sparks
Finished in 65.1 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: HDR photo of (red Zombie:1.2) Hyperrealistic, cinematic photo, Horror-themed, (Zombie:1.8) hybrid (Peter Parker:0.9), (cataract:1.3), big eyes, Eerie, unsettling, dark, spooky, suspenseful, grim, highly detailed. 35mm photograph, film, professional, 4k, highly detailed, logo spider, night dark city BG . High dynamic range, vivid, rich details, clear shadows and highlights, realistic, intense, enhanced contrast, highly detailed, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: flat, low contrast, oversaturated, underexposed, overexposed, blurred, noisy, simplified, abstract, unrealistic, impressionistic, low resolution, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, cheerful, bright, vibrant, light-hearted, cute, bokeh 0%| | 0/42 [00:00<?, ?it/s] 2%|▏ | 1/42 [00:01<00:59, 1.44s/it] 5%|▍ | 2/42 [00:02<00:57, 1.44s/it] 7%|▋ | 3/42 [00:04<00:56, 1.45s/it] 10%|▉ | 4/42 [00:05<00:55, 1.45s/it] 12%|█▏ | 5/42 [00:07<00:53, 1.45s/it] 14%|█▍ | 6/42 [00:08<00:52, 1.45s/it] 17%|█▋ | 7/42 [00:10<00:50, 1.45s/it] 19%|█▉ | 8/42 [00:11<00:49, 1.45s/it] 21%|██▏ | 9/42 [00:13<00:47, 1.45s/it] 24%|██▍ | 10/42 [00:14<00:46, 1.46s/it] 26%|██▌ | 11/42 [00:15<00:45, 1.46s/it] 29%|██▊ | 12/42 [00:17<00:43, 1.46s/it] 31%|███ | 13/42 [00:18<00:42, 1.46s/it] 33%|███▎ | 14/42 [00:20<00:40, 1.46s/it] 36%|███▌ | 15/42 [00:21<00:39, 1.46s/it] 38%|███▊ | 16/42 [00:23<00:37, 1.46s/it] 40%|████ | 17/42 [00:24<00:36, 1.46s/it] 43%|████▎ | 18/42 [00:26<00:35, 1.46s/it] 45%|████▌ | 19/42 [00:27<00:33, 1.46s/it] 48%|████▊ | 20/42 [00:29<00:32, 1.46s/it] 50%|█████ | 21/42 [00:30<00:30, 1.46s/it] 52%|█████▏ | 22/42 [00:32<00:29, 1.46s/it] 55%|█████▍ | 23/42 [00:33<00:27, 1.47s/it] 57%|█████▋ | 24/42 [00:35<00:26, 1.47s/it] 60%|█████▉ | 25/42 [00:36<00:24, 1.47s/it] 62%|██████▏ | 26/42 [00:37<00:23, 1.47s/it] 64%|██████▍ | 27/42 [00:39<00:22, 1.47s/it] 67%|██████▋ | 28/42 [00:40<00:20, 1.47s/it] 69%|██████▉ | 29/42 [00:42<00:19, 1.47s/it] 71%|███████▏ | 30/42 [00:43<00:17, 1.47s/it] 74%|███████▍ | 31/42 [00:45<00:16, 1.47s/it] 76%|███████▌ | 32/42 [00:46<00:14, 1.47s/it] 79%|███████▊ | 33/42 [00:48<00:13, 1.47s/it] 81%|████████ | 34/42 [00:49<00:11, 1.47s/it] 83%|████████▎ | 35/42 [00:51<00:10, 1.47s/it] 86%|████████▌ | 36/42 [00:52<00:08, 1.47s/it] 88%|████████▊ | 37/42 [00:54<00:07, 1.47s/it] 90%|█████████ | 38/42 [00:55<00:05, 1.47s/it] 93%|█████████▎| 39/42 [00:57<00:04, 1.47s/it] 95%|█████████▌| 40/42 [00:58<00:02, 1.47s/it] 98%|█████████▊| 41/42 [01:00<00:01, 1.47s/it] 100%|██████████| 42/42 [01:01<00:00, 1.47s/it] 100%|██████████| 42/42 [01:01<00:00, 1.46s/it] Decoding latents in cuda:0... done in 2.78s Move latents to cpu... done in 0.02s
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
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/a6ea7306ea9748ec92858b5c5759612e/00000-3464107305.webp
https://files.tungsten.run/uploads/340025b281e949b0affabedac4b7a9a8/00001-3464107306.webp
https://files.tungsten.run/uploads/e048ca8a26b343fcad57001810befd6f/00002-3464107307.webp
This example was created by sparks
Finished in 65.1 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: HDR photo of (red Zombie:1.2) Hyperrealistic, cinematic photo, Horror-themed, (Zombie:1.8) hybrid (Peter Parker:0.9), (cataract:1.3), big eyes, Eerie, unsettling, dark, spooky, suspenseful, grim, highly detailed. 35mm photograph, film, professional, 4k, highly detailed, logo spider, night dark city BG . High dynamic range, vivid, rich details, clear shadows and highlights, realistic, intense, enhanced contrast, highly detailed, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: flat, low contrast, oversaturated, underexposed, overexposed, blurred, noisy, simplified, abstract, unrealistic, impressionistic, low resolution, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, cheerful, bright, vibrant, light-hearted, cute, bokeh 0%| | 0/42 [00:00<?, ?it/s] 2%|▏ | 1/42 [00:01<00:59, 1.44s/it] 5%|▍ | 2/42 [00:02<00:57, 1.44s/it] 7%|▋ | 3/42 [00:04<00:56, 1.45s/it] 10%|▉ | 4/42 [00:05<00:55, 1.45s/it] 12%|█▏ | 5/42 [00:07<00:53, 1.45s/it] 14%|█▍ | 6/42 [00:08<00:52, 1.45s/it] 17%|█▋ | 7/42 [00:10<00:50, 1.45s/it] 19%|█▉ | 8/42 [00:11<00:49, 1.45s/it] 21%|██▏ | 9/42 [00:13<00:47, 1.45s/it] 24%|██▍ | 10/42 [00:14<00:46, 1.46s/it] 26%|██▌ | 11/42 [00:15<00:45, 1.46s/it] 29%|██▊ | 12/42 [00:17<00:43, 1.46s/it] 31%|███ | 13/42 [00:18<00:42, 1.46s/it] 33%|███▎ | 14/42 [00:20<00:40, 1.46s/it] 36%|███▌ | 15/42 [00:21<00:39, 1.46s/it] 38%|███▊ | 16/42 [00:23<00:37, 1.46s/it] 40%|████ | 17/42 [00:24<00:36, 1.46s/it] 43%|████▎ | 18/42 [00:26<00:35, 1.46s/it] 45%|████▌ | 19/42 [00:27<00:33, 1.46s/it] 48%|████▊ | 20/42 [00:29<00:32, 1.46s/it] 50%|█████ | 21/42 [00:30<00:30, 1.46s/it] 52%|█████▏ | 22/42 [00:32<00:29, 1.46s/it] 55%|█████▍ | 23/42 [00:33<00:27, 1.47s/it] 57%|█████▋ | 24/42 [00:35<00:26, 1.47s/it] 60%|█████▉ | 25/42 [00:36<00:24, 1.47s/it] 62%|██████▏ | 26/42 [00:37<00:23, 1.47s/it] 64%|██████▍ | 27/42 [00:39<00:22, 1.47s/it] 67%|██████▋ | 28/42 [00:40<00:20, 1.47s/it] 69%|██████▉ | 29/42 [00:42<00:19, 1.47s/it] 71%|███████▏ | 30/42 [00:43<00:17, 1.47s/it] 74%|███████▍ | 31/42 [00:45<00:16, 1.47s/it] 76%|███████▌ | 32/42 [00:46<00:14, 1.47s/it] 79%|███████▊ | 33/42 [00:48<00:13, 1.47s/it] 81%|████████ | 34/42 [00:49<00:11, 1.47s/it] 83%|████████▎ | 35/42 [00:51<00:10, 1.47s/it] 86%|████████▌ | 36/42 [00:52<00:08, 1.47s/it] 88%|████████▊ | 37/42 [00:54<00:07, 1.47s/it] 90%|█████████ | 38/42 [00:55<00:05, 1.47s/it] 93%|█████████▎| 39/42 [00:57<00:04, 1.47s/it] 95%|█████████▌| 40/42 [00:58<00:02, 1.47s/it] 98%|█████████▊| 41/42 [01:00<00:01, 1.47s/it] 100%|██████████| 42/42 [01:01<00:00, 1.47s/it] 100%|██████████| 42/42 [01:01<00:00, 1.46s/it] Decoding latents in cuda:0... done in 2.78s Move latents to cpu... done in 0.02s