tungsten-logo
Sign In
ai-real-turbo-xl
ai-real-turbo-xl

ai-real-turbo-xl

12 stars
Version: lightning
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
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/5a32d0253c284cd7bf7af7bccc820da8/00000-935835686.webp
https://files.tungsten.run/uploads/bbff49ca578f45a69b05e3cb5474314c/00001-935835687.webp
https://files.tungsten.run/uploads/d08aa3d67ecc493e82faac27b71d5983/00002-935835688.webp
This example was created by evevalentine2017
Finished in 52.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: photograph of (half mechwarrior, half king kong), action shot, dynamic angle, intricately detailed, destroying a city, destroyed metro city, Ultra-HD-detailsa, Porta 160 color, shot on ARRI ALEXA 65,bokeh, sharp focus on subject, shot by Don McCullin, style by Dan Winters, RAW photography, film grain, indistinguishable from reality, photo taken with a Bolex H16, Hyperrealistic art cinematic film still photography in the style of detailed hyperrealism photoshoot Hyperrealistic art cinematic film still photography in the style of detailed hyperrealism photoshoot . 35mm photograph, film, bokeh, professional, 4k, highly detailed, Ultra-HD-details, RAW candid cinema, 16mm, color graded portra 400 film, remarkable color, ultra realistic, realistic dull skin noise, shot with cinematic camera Full negative prompt: cropped, text, watermark, low-quality, signature, moiré 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 0%| | 0/8 [00:00<?, ?it/s] 12%|█▎ | 1/8 [00:03<00:22, 3.18s/it] 25%|██▌ | 2/8 [00:07<00:22, 3.72s/it] 38%|███▊ | 3/8 [00:11<00:19, 3.88s/it] 50%|█████ | 4/8 [00:15<00:15, 3.99s/it] 62%|██████▎ | 5/8 [00:19<00:11, 4.00s/it] 75%|███████▌ | 6/8 [00:23<00:07, 3.92s/it] 88%|████████▊ | 7/8 [00:26<00:03, 3.57s/it] 100%|██████████| 8/8 [00:27<00:00, 2.73s/it] 100%|██████████| 8/8 [00:27<00:00, 3.38s/it] Decoding latents in cuda:0... done in 1.79s Move latents to cpu... done in 0.02s 0: 480x640 2 faces, 168.0ms Speed: 3.0ms preprocess, 168.0ms inference, 22.6ms postprocess per image at shape (1, 3, 480, 640)
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
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/5a32d0253c284cd7bf7af7bccc820da8/00000-935835686.webp
https://files.tungsten.run/uploads/bbff49ca578f45a69b05e3cb5474314c/00001-935835687.webp
https://files.tungsten.run/uploads/d08aa3d67ecc493e82faac27b71d5983/00002-935835688.webp
This example was created by evevalentine2017
Finished in 52.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: photograph of (half mechwarrior, half king kong), action shot, dynamic angle, intricately detailed, destroying a city, destroyed metro city, Ultra-HD-detailsa, Porta 160 color, shot on ARRI ALEXA 65,bokeh, sharp focus on subject, shot by Don McCullin, style by Dan Winters, RAW photography, film grain, indistinguishable from reality, photo taken with a Bolex H16, Hyperrealistic art cinematic film still photography in the style of detailed hyperrealism photoshoot Hyperrealistic art cinematic film still photography in the style of detailed hyperrealism photoshoot . 35mm photograph, film, bokeh, professional, 4k, highly detailed, Ultra-HD-details, RAW candid cinema, 16mm, color graded portra 400 film, remarkable color, ultra realistic, realistic dull skin noise, shot with cinematic camera Full negative prompt: cropped, text, watermark, low-quality, signature, moiré 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 0%| | 0/8 [00:00<?, ?it/s] 12%|█▎ | 1/8 [00:03<00:22, 3.18s/it] 25%|██▌ | 2/8 [00:07<00:22, 3.72s/it] 38%|███▊ | 3/8 [00:11<00:19, 3.88s/it] 50%|█████ | 4/8 [00:15<00:15, 3.99s/it] 62%|██████▎ | 5/8 [00:19<00:11, 4.00s/it] 75%|███████▌ | 6/8 [00:23<00:07, 3.92s/it] 88%|████████▊ | 7/8 [00:26<00:03, 3.57s/it] 100%|██████████| 8/8 [00:27<00:00, 2.73s/it] 100%|██████████| 8/8 [00:27<00:00, 3.38s/it] Decoding latents in cuda:0... done in 1.79s Move latents to cpu... done in 0.02s 0: 480x640 2 faces, 168.0ms Speed: 3.0ms preprocess, 168.0ms inference, 22.6ms postprocess per image at shape (1, 3, 480, 640)