tungsten-logo
Sign In
Maniac with Cinematic Model SDXL
cinematic-model-sdxl:v1.0
evevalentine2017
evevalentine2017
·
Mar 22
373
Input
prompt
Specify things to see in the output
A cinematic film still framing the charismatic, unsettling smile of a cult leader, their teeth bared in a predatory grin as they captivate their followers with their magnetic presence, cinematic, 4k, hdri lighting, award-winning, atmospheric, gritty, volumetric fog, dramatic lighting, film grain, kodachrome, technicolor, IMAX quality
negative_prompt
Specify things to not see in the output
text, watermark, blur, deformed, noised, drawing, fake looking, unrealistic, painting., drawing, fake looking, unrealistic, painting.
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
1918899952
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M SDE Karras
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
5.5
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
None
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.
false
Output
https://files.tungsten.run/uploads/7c616ee15078438686b621edbf9be85a/00000-1918899952.webp
https://files.tungsten.run/uploads/080bd824509642e996a1b1ef34c784ee/00001-1918899953.webp
https://files.tungsten.run/uploads/a8fa289ae18849ada93410646c2d3f87/00002-1918899954.webp
Finished in 208.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: A cinematic film still framing the charismatic, unsettling smile of a cult leader, their teeth bared in a predatory grin as they captivate their followers with their magnetic presence, cinematic, 4k, hdri lighting, award-winning, atmospheric, gritty, volumetric fog, dramatic lighting, film grain, kodachrome, technicolor, IMAX quality Full negative prompt: text, watermark, blur, deformed, noised, drawing, fake looking, unrealistic, painting., drawing, fake looking, unrealistic, painting. 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:47, 1.65s/it] 7%|▋ | 2/30 [00:03<00:57, 2.04s/it] 10%|█ | 3/30 [00:06<00:58, 2.18s/it] 13%|█▎ | 4/30 [00:08<00:59, 2.30s/it] 17%|█▋ | 5/30 [00:11<00:57, 2.31s/it] 20%|██ | 6/30 [00:13<00:55, 2.29s/it] 23%|██▎ | 7/30 [00:15<00:52, 2.30s/it] 27%|██▋ | 8/30 [00:17<00:49, 2.27s/it] 30%|███ | 9/30 [00:19<00:46, 2.20s/it] 33%|███▎ | 10/30 [00:22<00:43, 2.17s/it] 37%|███▋ | 11/30 [00:24<00:40, 2.13s/it] 40%|████ | 12/30 [00:26<00:37, 2.11s/it] 43%|████▎ | 13/30 [00:28<00:36, 2.12s/it] 47%|████▋ | 14/30 [00:30<00:32, 2.05s/it] 50%|█████ | 15/30 [00:32<00:30, 2.05s/it] 53%|█████▎ | 16/30 [00:34<00:28, 2.04s/it] 57%|█████▋ | 17/30 [00:36<00:26, 2.01s/it] 60%|██████ | 18/30 [00:38<00:24, 2.02s/it] 63%|██████▎ | 19/30 [00:40<00:22, 2.01s/it] 67%|██████▋ | 20/30 [00:42<00:20, 2.01s/it] 70%|███████ | 21/30 [00:44<00:17, 1.99s/it] 73%|███████▎ | 22/30 [00:46<00:16, 2.00s/it] 77%|███████▋ | 23/30 [00:48<00:13, 1.96s/it] 80%|████████ | 24/30 [00:50<00:11, 1.96s/it] 83%|████████▎ | 25/30 [00:51<00:09, 1.91s/it] 87%|████████▋ | 26/30 [00:53<00:07, 1.92s/it] 90%|█████████ | 27/30 [00:55<00:05, 1.85s/it] 93%|█████████▎| 28/30 [00:57<00:03, 1.80s/it] 97%|█████████▋| 29/30 [00:58<00:01, 1.58s/it] 100%|██████████| 30/30 [00:59<00:00, 1.39s/it] 100%|██████████| 30/30 [00:59<00:00, 1.97s/it] Decoding latents in cuda:0... done in 1.7s Move latents to cpu... done in 0.02s 0: 480x640 5 faces, 166.7ms Speed: 3.5ms preprocess, 166.7ms inference, 25.3ms postprocess per image at shape (1, 3, 480, 640)
prompt
Specify things to see in the output
A cinematic film still framing the charismatic, unsettling smile of a cult leader, their teeth bared in a predatory grin as they captivate their followers with their magnetic presence, cinematic, 4k, hdri lighting, award-winning, atmospheric, gritty, volumetric fog, dramatic lighting, film grain, kodachrome, technicolor, IMAX quality
negative_prompt
Specify things to not see in the output
text, watermark, blur, deformed, noised, drawing, fake looking, unrealistic, painting., drawing, fake looking, unrealistic, painting.
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
1918899952
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M SDE Karras
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
5.5
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
None
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.
false
https://files.tungsten.run/uploads/7c616ee15078438686b621edbf9be85a/00000-1918899952.webp
https://files.tungsten.run/uploads/080bd824509642e996a1b1ef34c784ee/00001-1918899953.webp
https://files.tungsten.run/uploads/a8fa289ae18849ada93410646c2d3f87/00002-1918899954.webp
Finished in 208.8 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: A cinematic film still framing the charismatic, unsettling smile of a cult leader, their teeth bared in a predatory grin as they captivate their followers with their magnetic presence, cinematic, 4k, hdri lighting, award-winning, atmospheric, gritty, volumetric fog, dramatic lighting, film grain, kodachrome, technicolor, IMAX quality Full negative prompt: text, watermark, blur, deformed, noised, drawing, fake looking, unrealistic, painting., drawing, fake looking, unrealistic, painting. 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:47, 1.65s/it] 7%|▋ | 2/30 [00:03<00:57, 2.04s/it] 10%|█ | 3/30 [00:06<00:58, 2.18s/it] 13%|█▎ | 4/30 [00:08<00:59, 2.30s/it] 17%|█▋ | 5/30 [00:11<00:57, 2.31s/it] 20%|██ | 6/30 [00:13<00:55, 2.29s/it] 23%|██▎ | 7/30 [00:15<00:52, 2.30s/it] 27%|██▋ | 8/30 [00:17<00:49, 2.27s/it] 30%|███ | 9/30 [00:19<00:46, 2.20s/it] 33%|███▎ | 10/30 [00:22<00:43, 2.17s/it] 37%|███▋ | 11/30 [00:24<00:40, 2.13s/it] 40%|████ | 12/30 [00:26<00:37, 2.11s/it] 43%|████▎ | 13/30 [00:28<00:36, 2.12s/it] 47%|████▋ | 14/30 [00:30<00:32, 2.05s/it] 50%|█████ | 15/30 [00:32<00:30, 2.05s/it] 53%|█████▎ | 16/30 [00:34<00:28, 2.04s/it] 57%|█████▋ | 17/30 [00:36<00:26, 2.01s/it] 60%|██████ | 18/30 [00:38<00:24, 2.02s/it] 63%|██████▎ | 19/30 [00:40<00:22, 2.01s/it] 67%|██████▋ | 20/30 [00:42<00:20, 2.01s/it] 70%|███████ | 21/30 [00:44<00:17, 1.99s/it] 73%|███████▎ | 22/30 [00:46<00:16, 2.00s/it] 77%|███████▋ | 23/30 [00:48<00:13, 1.96s/it] 80%|████████ | 24/30 [00:50<00:11, 1.96s/it] 83%|████████▎ | 25/30 [00:51<00:09, 1.91s/it] 87%|████████▋ | 26/30 [00:53<00:07, 1.92s/it] 90%|█████████ | 27/30 [00:55<00:05, 1.85s/it] 93%|█████████▎| 28/30 [00:57<00:03, 1.80s/it] 97%|█████████▋| 29/30 [00:58<00:01, 1.58s/it] 100%|██████████| 30/30 [00:59<00:00, 1.39s/it] 100%|██████████| 30/30 [00:59<00:00, 1.97s/it] Decoding latents in cuda:0... done in 1.7s Move latents to cpu... done in 0.02s 0: 480x640 5 faces, 166.7ms Speed: 3.5ms preprocess, 166.7ms inference, 25.3ms postprocess per image at shape (1, 3, 480, 640)