Sign In
FULLY_REAL_XL
15
stars
Star
Star
Overview
Models
3
Gallery
57
Version: v6.0
Input
prompt
*
Specify things to see in the output
<lora:LCMTurboMix_DPM_SDE_Karras:1>, 30-year-old woman in a black shirt with bright red hair, styled after Dan Winters. Captured in RAW photography with a Bolex H16 and Sony A7R IV, using an 18mm F/1.7 cine lens for a hyperrealistic, analog-style cinematic film still. The highly detailed image showcases perfect facial features, skin pores, and dappled lighting, achieving an 'indistinguishable from reality' effect (1.4). Shot at 8K HDR with a front view, emphasizing the upper body (0.9) and cinematic depth. The Streetpunk Sexy theme depicts the woman on a rainy city night, shot from a distance, highlighting her wet body (1.6) and indifferent expression. Messy hair, pigtails, and a candid pose add realism, while taken with a Canon EOS 5D Mark III, capturing natural skin texture, including subtle acne (0.3), under soft, sharp lighting. The image features a depth of field focusing on her against a backdrop of soothing, muted colors, creating a dark yet gorgeous (1.2) and immersive night scene.
negative_prompt
Specify things to not see in the output
boring, bad anatomy, low quality, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, blurry, rendered, CGI
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.
Drop image here or click to select
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)
Drop image here or click to select
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
Drop image here or click to select
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
Drop image here or click to select
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>
LCMTurboMix_DPM_SDE_Karras.saf...
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
Drop file here or click to select
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
Drop file here or click to select
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
Drop file here or click to select
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
Drop file here or click to select
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
Drop file here or click to select
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!
Reset
Run
Output
This example was created by sparks
Finished in 54.0 seconds
Input
Output
prompt
*
Specify things to see in the output
<lora:LCMTurboMix_DPM_SDE_Karras:1>, 30-year-old woman in a black shirt with bright red hair, styled after Dan Winters. Captured in RAW photography with a Bolex H16 and Sony A7R IV, using an 18mm F/1.7 cine lens for a hyperrealistic, analog-style cinematic film still. The highly detailed image showcases perfect facial features, skin pores, and dappled lighting, achieving an 'indistinguishable from reality' effect (1.4). Shot at 8K HDR with a front view, emphasizing the upper body (0.9) and cinematic depth. The Streetpunk Sexy theme depicts the woman on a rainy city night, shot from a distance, highlighting her wet body (1.6) and indifferent expression. Messy hair, pigtails, and a candid pose add realism, while taken with a Canon EOS 5D Mark III, capturing natural skin texture, including subtle acne (0.3), under soft, sharp lighting. The image features a depth of field focusing on her against a backdrop of soothing, muted colors, creating a dark yet gorgeous (1.2) and immersive night scene.
negative_prompt
Specify things to not see in the output
boring, bad anatomy, low quality, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, blurry, rendered, CGI
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.
Drop image here or click to select
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)
Drop image here or click to select
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
Drop image here or click to select
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
Drop image here or click to select
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>
LCMTurboMix_DPM_SDE_Karras.saf...
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
Drop file here or click to select
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
Drop file here or click to select
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
Drop file here or click to select
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
Drop file here or click to select
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
Drop file here or click to select
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!
Reset
Run
This example was created by sparks
Finished in 54.0 seconds