tungsten-logo
Sign In
cinematic-model-sdxl
cinematic-model-sdxl

cinematic-model-sdxl

27 stars
Version: v1.0
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/830726de23a244e188069dd576c14ec4/00000-1918899952.webp
https://files.tungsten.run/uploads/3a148c3c02dc4431984cb5871a902de0/00001-1918899953.webp
https://files.tungsten.run/uploads/f90c8f053e264a58bf2f006ca40cca25/00002-1918899954.webp
This example was created by evevalentine2017
Finished in 101.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: Scene from the Terminator Movie, 1985, intricate cinematography, high quality award winning movie footage, cinematic, 4k, hdri lighting, award-winning, atmospheric, gritty, volumetric fog, dramatic lighting, film grain, kodachrome, technicolor, IMAX quality, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx Full negative prompt: text, watermark, blur, deformed, noised 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:46, 1.61s/it] 7%|▋ | 2/30 [00:03<00:52, 1.87s/it] 10%|█ | 3/30 [00:05<00:53, 1.98s/it] 13%|█▎ | 4/30 [00:07<00:53, 2.05s/it] 17%|█▋ | 5/30 [00:10<00:52, 2.09s/it] 20%|██ | 6/30 [00:12<00:49, 2.08s/it] 23%|██▎ | 7/30 [00:14<00:48, 2.10s/it] 27%|██▋ | 8/30 [00:16<00:46, 2.09s/it] 30%|███ | 9/30 [00:18<00:43, 2.07s/it] 33%|███▎ | 10/30 [00:20<00:41, 2.10s/it] 37%|███▋ | 11/30 [00:22<00:39, 2.08s/it] 40%|████ | 12/30 [00:24<00:37, 2.09s/it] 43%|████▎ | 13/30 [00:26<00:35, 2.10s/it] 47%|████▋ | 14/30 [00:28<00:32, 2.02s/it] 50%|█████ | 15/30 [00:30<00:30, 2.00s/it] 53%|█████▎ | 16/30 [00:32<00:27, 1.99s/it] 57%|█████▋ | 17/30 [00:34<00:25, 1.96s/it] 60%|██████ | 18/30 [00:36<00:23, 1.97s/it] 63%|██████▎ | 19/30 [00:38<00:21, 1.97s/it] 67%|██████▋ | 20/30 [00:40<00:19, 1.99s/it] 70%|███████ | 21/30 [00:42<00:17, 1.97s/it] 73%|███████▎ | 22/30 [00:44<00:16, 2.00s/it] 77%|███████▋ | 23/30 [00:46<00:13, 1.95s/it] 80%|████████ | 24/30 [00:48<00:11, 1.96s/it] 83%|████████▎ | 25/30 [00:50<00:09, 1.90s/it] 87%|████████▋ | 26/30 [00:52<00:07, 1.91s/it] 90%|█████████ | 27/30 [00:53<00:05, 1.83s/it] 93%|█████████▎| 28/30 [00:55<00:03, 1.78s/it] 97%|█████████▋| 29/30 [00:56<00:01, 1.55s/it] 100%|██████████| 30/30 [00:57<00:00, 1.36s/it] 100%|██████████| 30/30 [00:57<00:00, 1.91s/it] Decoding latents in cuda:0... done in 1.7s Move latents to cpu... done in 0.02s 0: 480x640 1 face, 168.0ms Speed: 2.8ms preprocess, 168.0ms inference, 22.0ms 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/830726de23a244e188069dd576c14ec4/00000-1918899952.webp
https://files.tungsten.run/uploads/3a148c3c02dc4431984cb5871a902de0/00001-1918899953.webp
https://files.tungsten.run/uploads/f90c8f053e264a58bf2f006ca40cca25/00002-1918899954.webp
This example was created by evevalentine2017
Finished in 101.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: Scene from the Terminator Movie, 1985, intricate cinematography, high quality award winning movie footage, cinematic, 4k, hdri lighting, award-winning, atmospheric, gritty, volumetric fog, dramatic lighting, film grain, kodachrome, technicolor, IMAX quality, sharp focus, dramatic, award winning, cinematic lighting, volumetrics dtx Full negative prompt: text, watermark, blur, deformed, noised 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:46, 1.61s/it] 7%|▋ | 2/30 [00:03<00:52, 1.87s/it] 10%|█ | 3/30 [00:05<00:53, 1.98s/it] 13%|█▎ | 4/30 [00:07<00:53, 2.05s/it] 17%|█▋ | 5/30 [00:10<00:52, 2.09s/it] 20%|██ | 6/30 [00:12<00:49, 2.08s/it] 23%|██▎ | 7/30 [00:14<00:48, 2.10s/it] 27%|██▋ | 8/30 [00:16<00:46, 2.09s/it] 30%|███ | 9/30 [00:18<00:43, 2.07s/it] 33%|███▎ | 10/30 [00:20<00:41, 2.10s/it] 37%|███▋ | 11/30 [00:22<00:39, 2.08s/it] 40%|████ | 12/30 [00:24<00:37, 2.09s/it] 43%|████▎ | 13/30 [00:26<00:35, 2.10s/it] 47%|████▋ | 14/30 [00:28<00:32, 2.02s/it] 50%|█████ | 15/30 [00:30<00:30, 2.00s/it] 53%|█████▎ | 16/30 [00:32<00:27, 1.99s/it] 57%|█████▋ | 17/30 [00:34<00:25, 1.96s/it] 60%|██████ | 18/30 [00:36<00:23, 1.97s/it] 63%|██████▎ | 19/30 [00:38<00:21, 1.97s/it] 67%|██████▋ | 20/30 [00:40<00:19, 1.99s/it] 70%|███████ | 21/30 [00:42<00:17, 1.97s/it] 73%|███████▎ | 22/30 [00:44<00:16, 2.00s/it] 77%|███████▋ | 23/30 [00:46<00:13, 1.95s/it] 80%|████████ | 24/30 [00:48<00:11, 1.96s/it] 83%|████████▎ | 25/30 [00:50<00:09, 1.90s/it] 87%|████████▋ | 26/30 [00:52<00:07, 1.91s/it] 90%|█████████ | 27/30 [00:53<00:05, 1.83s/it] 93%|█████████▎| 28/30 [00:55<00:03, 1.78s/it] 97%|█████████▋| 29/30 [00:56<00:01, 1.55s/it] 100%|██████████| 30/30 [00:57<00:00, 1.36s/it] 100%|██████████| 30/30 [00:57<00:00, 1.91s/it] Decoding latents in cuda:0... done in 1.7s Move latents to cpu... done in 0.02s 0: 480x640 1 face, 168.0ms Speed: 2.8ms preprocess, 168.0ms inference, 22.0ms postprocess per image at shape (1, 3, 480, 640)