tungsten-logo
Sign In
SunnyRealXLTurbo
SunnyRealXLTurbo

SunnyRealXLTurbo

2 stars
Version: v1.0
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/0f789a9305644e8d98ab31f75db725f0/00000-500482189.webp
https://files.tungsten.run/uploads/4abde7006030491aa5c25a190265c0cc/00001-500482190.webp
https://files.tungsten.run/uploads/6291aa8ec5934df3b1d6f7d0272ad1ef/00002-500482191.webp
This example was created by sparks
Finished in 223.3 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: movie screenshot of the high tech futuristic martian invader skull mask, heavy armor suit, science fiction, dark, foggy, ultra detailed, hd, 8k, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: BeyondSDXLv3, ac_neg1, ac_neg2, (long neck:1.5) 0%| | 0/27 [00:00<?, ?it/s] 4%|▎ | 1/27 [00:08<03:30, 8.11s/it] 7%|▋ | 2/27 [00:17<03:41, 8.87s/it] 11%|█ | 3/27 [00:26<03:37, 9.08s/it] 15%|█▍ | 4/27 [00:35<03:24, 8.87s/it] 19%|█▊ | 5/27 [00:44<03:18, 9.02s/it] 22%|██▏ | 6/27 [00:53<03:07, 8.95s/it] 26%|██▌ | 7/27 [01:02<02:57, 8.89s/it] 30%|██▉ | 8/27 [01:10<02:47, 8.82s/it] 33%|███▎ | 9/27 [01:19<02:39, 8.87s/it] 37%|███▋ | 10/27 [01:28<02:30, 8.85s/it] 41%|████ | 11/27 [01:36<02:13, 8.37s/it] 44%|████▍ | 12/27 [01:44<02:08, 8.54s/it] 48%|████▊ | 13/27 [01:53<01:59, 8.51s/it] 52%|█████▏ | 14/27 [02:02<01:51, 8.55s/it] 56%|█████▌ | 15/27 [02:10<01:42, 8.50s/it] 59%|█████▉ | 16/27 [02:18<01:32, 8.42s/it] 63%|██████▎ | 17/27 [02:26<01:21, 8.15s/it] 67%|██████▋ | 18/27 [02:33<01:11, 7.94s/it] 70%|███████ | 19/27 [02:42<01:04, 8.10s/it] 74%|███████▍ | 20/27 [02:50<00:57, 8.21s/it] 78%|███████▊ | 21/27 [02:57<00:46, 7.80s/it] 81%|████████▏ | 22/27 [03:04<00:38, 7.62s/it] 85%|████████▌ | 23/27 [03:11<00:29, 7.45s/it] 89%|████████▉ | 24/27 [03:17<00:21, 7.08s/it] 93%|█████████▎| 25/27 [03:24<00:14, 7.09s/it] 96%|█████████▋| 26/27 [03:30<00:06, 6.74s/it] 100%|██████████| 27/27 [03:33<00:00, 5.40s/it] 100%|██████████| 27/27 [03:33<00:00, 7.90s/it] Decoding latents in cuda:0... done in 3.91s Move latents to cpu... done in 0.05s
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/0f789a9305644e8d98ab31f75db725f0/00000-500482189.webp
https://files.tungsten.run/uploads/4abde7006030491aa5c25a190265c0cc/00001-500482190.webp
https://files.tungsten.run/uploads/6291aa8ec5934df3b1d6f7d0272ad1ef/00002-500482191.webp
This example was created by sparks
Finished in 223.3 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: movie screenshot of the high tech futuristic martian invader skull mask, heavy armor suit, science fiction, dark, foggy, ultra detailed, hd, 8k, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: BeyondSDXLv3, ac_neg1, ac_neg2, (long neck:1.5) 0%| | 0/27 [00:00<?, ?it/s] 4%|▎ | 1/27 [00:08<03:30, 8.11s/it] 7%|▋ | 2/27 [00:17<03:41, 8.87s/it] 11%|█ | 3/27 [00:26<03:37, 9.08s/it] 15%|█▍ | 4/27 [00:35<03:24, 8.87s/it] 19%|█▊ | 5/27 [00:44<03:18, 9.02s/it] 22%|██▏ | 6/27 [00:53<03:07, 8.95s/it] 26%|██▌ | 7/27 [01:02<02:57, 8.89s/it] 30%|██▉ | 8/27 [01:10<02:47, 8.82s/it] 33%|███▎ | 9/27 [01:19<02:39, 8.87s/it] 37%|███▋ | 10/27 [01:28<02:30, 8.85s/it] 41%|████ | 11/27 [01:36<02:13, 8.37s/it] 44%|████▍ | 12/27 [01:44<02:08, 8.54s/it] 48%|████▊ | 13/27 [01:53<01:59, 8.51s/it] 52%|█████▏ | 14/27 [02:02<01:51, 8.55s/it] 56%|█████▌ | 15/27 [02:10<01:42, 8.50s/it] 59%|█████▉ | 16/27 [02:18<01:32, 8.42s/it] 63%|██████▎ | 17/27 [02:26<01:21, 8.15s/it] 67%|██████▋ | 18/27 [02:33<01:11, 7.94s/it] 70%|███████ | 19/27 [02:42<01:04, 8.10s/it] 74%|███████▍ | 20/27 [02:50<00:57, 8.21s/it] 78%|███████▊ | 21/27 [02:57<00:46, 7.80s/it] 81%|████████▏ | 22/27 [03:04<00:38, 7.62s/it] 85%|████████▌ | 23/27 [03:11<00:29, 7.45s/it] 89%|████████▉ | 24/27 [03:17<00:21, 7.08s/it] 93%|█████████▎| 25/27 [03:24<00:14, 7.09s/it] 96%|█████████▋| 26/27 [03:30<00:06, 6.74s/it] 100%|██████████| 27/27 [03:33<00:00, 5.40s/it] 100%|██████████| 27/27 [03:33<00:00, 7.90s/it] Decoding latents in cuda:0... done in 3.91s Move latents to cpu... done in 0.05s