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/341d31d923ac4c51bd084e9609b551fd/00000-2683478307.webp
https://files.tungsten.run/uploads/071693e4b02b4b449ba59ac2ad432722/00001-2683478308.webp
https://files.tungsten.run/uploads/5cd5088b9da64a2f9606bfed5da5b754/00002-2683478309.webp
This example was created by evevalentine2017
Finished in 88.2 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: (supreme grand masterpiece), (extremely detailed), the greatest mythpunk, biopunk, robotpunk, nanopunk, retro cyberpunk, raypunk, post-cyberpunk, teslapunk, dieselpunk, atompunk, clockpunk, solarpunk, cyberpunk, steampunk, stonepunk, decopunk, spacepunk, art ever Full negative prompt: nope never heard of it 0%| | 0/9 [00:00<?, ?it/s] 11%|█ | 1/9 [00:04<00:34, 4.27s/it] 22%|██▏ | 2/9 [00:10<00:36, 5.22s/it] 33%|███▎ | 3/9 [00:16<00:33, 5.61s/it] 44%|████▍ | 4/9 [00:21<00:27, 5.56s/it] 56%|█████▌ | 5/9 [00:27<00:22, 5.58s/it] 67%|██████▋ | 6/9 [00:32<00:16, 5.56s/it] 78%|███████▊ | 7/9 [00:38<00:11, 5.57s/it] 89%|████████▉ | 8/9 [00:42<00:05, 5.11s/it] 100%|██████████| 9/9 [00:43<00:00, 3.93s/it] 100%|██████████| 9/9 [00:43<00:00, 4.88s/it] Decoding latents in cuda:0... done in 2.38s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.7ms Speed: 3.4ms preprocess, 7.7ms inference, 21.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:01<00:07, 1.83s/it] 40%|████ | 2/5 [00:03<00:05, 1.75s/it] 60%|██████ | 3/5 [00:05<00:03, 1.72s/it] 80%|████████ | 4/5 [00:06<00:01, 1.50s/it] 100%|██████████| 5/5 [00:06<00:00, 1.11s/it] 100%|██████████| 5/5 [00:06<00:00, 1.36s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 2 faces, 7.7ms Speed: 3.0ms preprocess, 7.7ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:01<00:07, 1.77s/it] 40%|████ | 2/5 [00:03<00:05, 1.75s/it] 60%|██████ | 3/5 [00:05<00:03, 1.71s/it] 80%|████████ | 4/5 [00:06<00:01, 1.50s/it] 100%|██████████| 5/5 [00:06<00:00, 1.10s/it] 100%|██████████| 5/5 [00:06<00:00, 1.35s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:01<00:07, 1.78s/it] 40%|████ | 2/5 [00:03<00:05, 1.74s/it] 60%|██████ | 3/5 [00:05<00:03, 1.74s/it] 80%|████████ | 4/5 [00:06<00:01, 1.52s/it] 100%|██████████| 5/5 [00:06<00:00, 1.11s/it] 100%|██████████| 5/5 [00:06<00:00, 1.36s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.7ms Speed: 2.9ms preprocess, 7.7ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:01<00:07, 1.77s/it] 40%|████ | 2/5 [00:03<00:05, 1.72s/it] 60%|██████ | 3/5 [00:05<00:03, 1.69s/it] 80%|████████ | 4/5 [00:06<00:01, 1.48s/it] 100%|██████████| 5/5 [00:06<00:00, 1.09s/it] 100%|██████████| 5/5 [00:06<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.79s 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/341d31d923ac4c51bd084e9609b551fd/00000-2683478307.webp
https://files.tungsten.run/uploads/071693e4b02b4b449ba59ac2ad432722/00001-2683478308.webp
https://files.tungsten.run/uploads/5cd5088b9da64a2f9606bfed5da5b754/00002-2683478309.webp
This example was created by evevalentine2017
Finished in 88.2 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: (supreme grand masterpiece), (extremely detailed), the greatest mythpunk, biopunk, robotpunk, nanopunk, retro cyberpunk, raypunk, post-cyberpunk, teslapunk, dieselpunk, atompunk, clockpunk, solarpunk, cyberpunk, steampunk, stonepunk, decopunk, spacepunk, art ever Full negative prompt: nope never heard of it 0%| | 0/9 [00:00<?, ?it/s] 11%|█ | 1/9 [00:04<00:34, 4.27s/it] 22%|██▏ | 2/9 [00:10<00:36, 5.22s/it] 33%|███▎ | 3/9 [00:16<00:33, 5.61s/it] 44%|████▍ | 4/9 [00:21<00:27, 5.56s/it] 56%|█████▌ | 5/9 [00:27<00:22, 5.58s/it] 67%|██████▋ | 6/9 [00:32<00:16, 5.56s/it] 78%|███████▊ | 7/9 [00:38<00:11, 5.57s/it] 89%|████████▉ | 8/9 [00:42<00:05, 5.11s/it] 100%|██████████| 9/9 [00:43<00:00, 3.93s/it] 100%|██████████| 9/9 [00:43<00:00, 4.88s/it] Decoding latents in cuda:0... done in 2.38s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.7ms Speed: 3.4ms preprocess, 7.7ms inference, 21.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:01<00:07, 1.83s/it] 40%|████ | 2/5 [00:03<00:05, 1.75s/it] 60%|██████ | 3/5 [00:05<00:03, 1.72s/it] 80%|████████ | 4/5 [00:06<00:01, 1.50s/it] 100%|██████████| 5/5 [00:06<00:00, 1.11s/it] 100%|██████████| 5/5 [00:06<00:00, 1.36s/it] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s 0: 640x640 2 faces, 7.7ms Speed: 3.0ms preprocess, 7.7ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:01<00:07, 1.77s/it] 40%|████ | 2/5 [00:03<00:05, 1.75s/it] 60%|██████ | 3/5 [00:05<00:03, 1.71s/it] 80%|████████ | 4/5 [00:06<00:01, 1.50s/it] 100%|██████████| 5/5 [00:06<00:00, 1.10s/it] 100%|██████████| 5/5 [00:06<00:00, 1.35s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:01<00:07, 1.78s/it] 40%|████ | 2/5 [00:03<00:05, 1.74s/it] 60%|██████ | 3/5 [00:05<00:03, 1.74s/it] 80%|████████ | 4/5 [00:06<00:01, 1.52s/it] 100%|██████████| 5/5 [00:06<00:00, 1.11s/it] 100%|██████████| 5/5 [00:06<00:00, 1.36s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.7ms Speed: 2.9ms preprocess, 7.7ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:01<00:07, 1.77s/it] 40%|████ | 2/5 [00:03<00:05, 1.72s/it] 60%|██████ | 3/5 [00:05<00:03, 1.69s/it] 80%|████████ | 4/5 [00:06<00:01, 1.48s/it] 100%|██████████| 5/5 [00:06<00:00, 1.09s/it] 100%|██████████| 5/5 [00:06<00:00, 1.33s/it] Decoding latents in cuda:0... done in 0.79s Move latents to cpu... done in 0.0s Uploading outputs... Finished.