tungsten-logo
Sign In
lightning-turbo-xl
lightning-turbo-xl

lightning-turbo-xl

4 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/75debd792c7d40788a0710002677cbe0/00000-1157927999.webp
https://files.tungsten.run/uploads/b1cab2daf6e5407f9e2d6e0f5e1c5954/00001-1157928000.webp
https://files.tungsten.run/uploads/ff9e41a00af843f88e0a3789a911d903/00002-1157928001.webp
This example was created by evevalentine2017
Finished in 77.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: HDR photo, masterpiece, best quality, hyper detailed, ultra detailed, male white knight vs female black knight, sitting at a coffee shop, helmets, highly detailed,, detailed, realistic style,4K texture, cinematic, photorealistic, real photo, realistic skin texture, skin imperfections, skin pores, sharp details, bright light, 8k, HDR, f.1/2, 70mm lens, Kodak, Analog style Full negative prompt: girl, woman, hair, deformed, noisy, blurry, low contrast, modernist, minimalist, abstract, long neck, asymmetrical eyes, signature, watermark, 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:03<00:18, 3.04s/it] 29%|██▊ | 2/7 [00:07<00:18, 3.62s/it] 43%|████▎ | 3/7 [00:11<00:15, 3.84s/it] 57%|█████▋ | 4/7 [00:15<00:11, 3.91s/it] 71%|███████▏ | 5/7 [00:19<00:07, 3.90s/it] 86%|████████▌ | 6/7 [00:22<00:03, 3.74s/it] 100%|██████████| 7/7 [00:23<00:00, 2.81s/it] 100%|██████████| 7/7 [00:23<00:00, 3.34s/it] Decoding latents in cuda:0... done in 1.73s Move latents to cpu... done in 0.02s 0: 480x640 3 faces, 164.0ms Speed: 3.1ms preprocess, 164.0ms inference, 22.3ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:02<00:06, 2.17s/it] 50%|█████ | 2/4 [00:04<00:04, 2.05s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.81s/it] 100%|██████████| 4/4 [00:06<00:00, 1.33s/it] 100%|██████████| 4/4 [00:06<00:00, 1.56s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:01<00:05, 1.99s/it] 50%|█████ | 2/4 [00:03<00:03, 1.99s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.76s/it] 100%|██████████| 4/4 [00:06<00:00, 1.30s/it] 100%|██████████| 4/4 [00:06<00:00, 1.51s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:02<00:06, 2.06s/it] 50%|█████ | 2/4 [00:04<00:04, 2.03s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.82s/it] 100%|██████████| 4/4 [00:06<00:00, 1.34s/it] 100%|██████████| 4/4 [00:06<00:00, 1.56s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0: 480x640 1 face, 8.2ms Speed: 2.5ms preprocess, 8.2ms inference, 1.9ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:02<00:06, 2.00s/it] 50%|█████ | 2/4 [00:03<00:03, 1.93s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.73s/it] 100%|██████████| 4/4 [00:05<00:00, 1.29s/it] 100%|██████████| 4/4 [00:05<00:00, 1.50s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0: 480x640 2 faces, 9.5ms Speed: 2.6ms preprocess, 9.5ms inference, 1.8ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:01<00:05, 1.95s/it] 50%|█████ | 2/4 [00:03<00:03, 1.90s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.71s/it] 100%|██████████| 4/4 [00:05<00:00, 1.27s/it] 100%|██████████| 4/4 [00:05<00:00, 1.48s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:01<00:05, 1.97s/it] 50%|█████ | 2/4 [00:03<00:03, 1.95s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.74s/it] 100%|██████████| 4/4 [00:05<00:00, 1.29s/it] 100%|██████████| 4/4 [00:05<00:00, 1.50s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
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/75debd792c7d40788a0710002677cbe0/00000-1157927999.webp
https://files.tungsten.run/uploads/b1cab2daf6e5407f9e2d6e0f5e1c5954/00001-1157928000.webp
https://files.tungsten.run/uploads/ff9e41a00af843f88e0a3789a911d903/00002-1157928001.webp
This example was created by evevalentine2017
Finished in 77.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: HDR photo, masterpiece, best quality, hyper detailed, ultra detailed, male white knight vs female black knight, sitting at a coffee shop, helmets, highly detailed,, detailed, realistic style,4K texture, cinematic, photorealistic, real photo, realistic skin texture, skin imperfections, skin pores, sharp details, bright light, 8k, HDR, f.1/2, 70mm lens, Kodak, Analog style Full negative prompt: girl, woman, hair, deformed, noisy, blurry, low contrast, modernist, minimalist, abstract, long neck, asymmetrical eyes, signature, watermark, 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:03<00:18, 3.04s/it] 29%|██▊ | 2/7 [00:07<00:18, 3.62s/it] 43%|████▎ | 3/7 [00:11<00:15, 3.84s/it] 57%|█████▋ | 4/7 [00:15<00:11, 3.91s/it] 71%|███████▏ | 5/7 [00:19<00:07, 3.90s/it] 86%|████████▌ | 6/7 [00:22<00:03, 3.74s/it] 100%|██████████| 7/7 [00:23<00:00, 2.81s/it] 100%|██████████| 7/7 [00:23<00:00, 3.34s/it] Decoding latents in cuda:0... done in 1.73s Move latents to cpu... done in 0.02s 0: 480x640 3 faces, 164.0ms Speed: 3.1ms preprocess, 164.0ms inference, 22.3ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:02<00:06, 2.17s/it] 50%|█████ | 2/4 [00:04<00:04, 2.05s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.81s/it] 100%|██████████| 4/4 [00:06<00:00, 1.33s/it] 100%|██████████| 4/4 [00:06<00:00, 1.56s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:01<00:05, 1.99s/it] 50%|█████ | 2/4 [00:03<00:03, 1.99s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.76s/it] 100%|██████████| 4/4 [00:06<00:00, 1.30s/it] 100%|██████████| 4/4 [00:06<00:00, 1.51s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:02<00:06, 2.06s/it] 50%|█████ | 2/4 [00:04<00:04, 2.03s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.82s/it] 100%|██████████| 4/4 [00:06<00:00, 1.34s/it] 100%|██████████| 4/4 [00:06<00:00, 1.56s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0: 480x640 1 face, 8.2ms Speed: 2.5ms preprocess, 8.2ms inference, 1.9ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:02<00:06, 2.00s/it] 50%|█████ | 2/4 [00:03<00:03, 1.93s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.73s/it] 100%|██████████| 4/4 [00:05<00:00, 1.29s/it] 100%|██████████| 4/4 [00:05<00:00, 1.50s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0: 480x640 2 faces, 9.5ms Speed: 2.6ms preprocess, 9.5ms inference, 1.8ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:01<00:05, 1.95s/it] 50%|█████ | 2/4 [00:03<00:03, 1.90s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.71s/it] 100%|██████████| 4/4 [00:05<00:00, 1.27s/it] 100%|██████████| 4/4 [00:05<00:00, 1.48s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:01<00:05, 1.97s/it] 50%|█████ | 2/4 [00:03<00:03, 1.95s/it] 75%|███████▌ | 3/4 [00:05<00:01, 1.74s/it] 100%|██████████| 4/4 [00:05<00:00, 1.29s/it] 100%|██████████| 4/4 [00:05<00:00, 1.50s/it] Decoding latents in cuda:0... done in 0.55s Move latents to cpu... done in 0.0s Uploading outputs... Finished.