tungsten-logo
Sign In
Female Cyborgs with DreamTech XL
dreamtech-xl:v1.0
evevalentine2017
evevalentine2017
·
May 8
9
Input
prompt
Specify things to see in the output
Photorealistic, ultra detailed, absurdres, a stunning cinematic photo, cinematic angle, Fujifilm XT3, Canon R5, Fujicolor Fujichrome Velvia 100, (full body:1), cybernetic robot masterpiece, best quality, (robotic face:1), (wires in the hair:1.1), absurdres, high details, 8K, photorealistic, amazing body, at distance, cowboy shot, posing, flirting, (playful gaze, smirking:1.1), 1girl, android, AI, machine, metal, (wires:1), tech, futuristic, highly detailed, masterpiece, best quality, hyperdetailed, highest detailed, high resolution textures, cinematic film shot, highly detailed, ultra-high resolutions, 32K UHD, sharp focus, best quality, masterpiece, realistic, real photo, sharp details, bright light, 8k, HDR, f.1/2, 70mm lens, Kodak, Analog style, epiCPhoto, <lora:add-detail-xl:1>,
negative_prompt
Specify things to not see in the output
(hair:1.5), (human skin:1), (portrait:1), (focus on face:1), (face close up), Bad quality, low details, cross eyed, worst quality, normal quality, low-res, sketch, poor design, deformed, disfigured, soft, bad composition, simple design, boring, watermark, text, error, cropped, blurry, BeyondBetaSDXLv4, epiCNegative
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
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.
0
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
Restart
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
6
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>
add-detail-xl.safetensors
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)
BeyondBetaSDXLv4.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
epiCNegative.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
epiCPhoto.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
Output
https://files.tungsten.run/uploads/e18e47f1a49d4bf18d115f9976a009b0/00000-0.webp
https://files.tungsten.run/uploads/85a161f247454a9ba6fff6fb66b7ec2b/00001-1.webp
https://files.tungsten.run/uploads/45359e28062244e9b77860ddc2bad0d9/00002-2.webp
Finished in 104.9 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: Photorealistic, ultra detailed, absurdres, a stunning cinematic photo, cinematic angle, Fujifilm XT3, Canon R5, Fujicolor Fujichrome Velvia 100, (full body:1), cybernetic robot masterpiece, best quality, (robotic face:1), (wires in the hair:1.1), absurdres, high details, 8K, photorealistic, amazing body, at distance, cowboy shot, posing, flirting, (playful gaze, smirking:1.1), 1girl, android, AI, machine, metal, (wires:1), tech, futuristic, highly detailed, masterpiece, best quality, hyperdetailed, highest detailed, high resolution textures, cinematic film shot, highly detailed, ultra-high resolutions, 32K UHD, sharp focus, best quality, masterpiece, realistic, real photo, sharp details, bright light, 8k, HDR, f.1/2, 70mm lens, Kodak, Analog style, epiCPhoto, Full negative prompt: (hair:1.5), (human skin:1), (portrait:1), (focus on face:1), (face close up), Bad quality, low details, cross eyed, worst quality, normal quality, low-res, sketch, poor design, deformed, disfigured, soft, bad composition, simple design, boring, watermark, text, error, cropped, blurry, BeyondBetaSDXLv4, epiCNegative 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:49, 1.71s/it] 7%|▋ | 2/30 [00:03<00:47, 1.71s/it] 10%|█ | 3/30 [00:05<00:46, 1.71s/it] 13%|█▎ | 4/30 [00:06<00:44, 1.71s/it] 17%|█▋ | 5/30 [00:08<00:42, 1.71s/it] 20%|██ | 6/30 [00:10<00:41, 1.72s/it] 23%|██▎ | 7/30 [00:12<00:39, 1.72s/it] 27%|██▋ | 8/30 [00:13<00:37, 1.72s/it] 30%|███ | 9/30 [00:15<00:36, 1.72s/it] 33%|███▎ | 10/30 [00:17<00:34, 1.72s/it] 37%|███▋ | 11/30 [00:18<00:32, 1.72s/it] 40%|████ | 12/30 [00:20<00:30, 1.72s/it] 43%|████▎ | 13/30 [00:22<00:29, 1.72s/it] 47%|████▋ | 14/30 [00:24<00:27, 1.72s/it] 50%|█████ | 15/30 [00:25<00:25, 1.73s/it] 53%|█████▎ | 16/30 [00:27<00:24, 1.73s/it] 57%|█████▋ | 17/30 [00:29<00:22, 1.73s/it] 60%|██████ | 18/30 [00:30<00:20, 1.73s/it] 63%|██████▎ | 19/30 [00:32<00:19, 1.73s/it] 67%|██████▋ | 20/30 [00:34<00:17, 1.73s/it] 70%|███████ | 21/30 [00:36<00:15, 1.73s/it] 73%|███████▎ | 22/30 [00:37<00:13, 1.74s/it] 77%|███████▋ | 23/30 [00:39<00:12, 1.74s/it] 80%|████████ | 24/30 [00:41<00:10, 1.74s/it] 83%|████████▎ | 25/30 [00:43<00:08, 1.74s/it] 87%|████████▋ | 26/30 [00:44<00:06, 1.74s/it] 90%|█████████ | 27/30 [00:46<00:05, 1.74s/it] 93%|█████████▎| 28/30 [00:48<00:03, 1.74s/it] 97%|█████████▋| 29/30 [00:50<00:01, 1.74s/it] 100%|██████████| 30/30 [00:50<00:00, 1.48s/it] 100%|██████████| 30/30 [00:50<00:00, 1.70s/it] Decoding latents in cuda:0... done in 1.69s Move latents to cpu... done in 0.01s 0: 640x480 1 face, 122.0ms Speed: 1.8ms preprocess, 122.0ms inference, 21.6ms postprocess per image at shape (1, 3, 640, 480)
prompt
Specify things to see in the output
Photorealistic, ultra detailed, absurdres, a stunning cinematic photo, cinematic angle, Fujifilm XT3, Canon R5, Fujicolor Fujichrome Velvia 100, (full body:1), cybernetic robot masterpiece, best quality, (robotic face:1), (wires in the hair:1.1), absurdres, high details, 8K, photorealistic, amazing body, at distance, cowboy shot, posing, flirting, (playful gaze, smirking:1.1), 1girl, android, AI, machine, metal, (wires:1), tech, futuristic, highly detailed, masterpiece, best quality, hyperdetailed, highest detailed, high resolution textures, cinematic film shot, highly detailed, ultra-high resolutions, 32K UHD, sharp focus, best quality, masterpiece, realistic, real photo, sharp details, bright light, 8k, HDR, f.1/2, 70mm lens, Kodak, Analog style, epiCPhoto, <lora:add-detail-xl:1>,
negative_prompt
Specify things to not see in the output
(hair:1.5), (human skin:1), (portrait:1), (focus on face:1), (face close up), Bad quality, low details, cross eyed, worst quality, normal quality, low-res, sketch, poor design, deformed, disfigured, soft, bad composition, simple design, boring, watermark, text, error, cropped, blurry, BeyondBetaSDXLv4, epiCNegative
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
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.
0
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
Restart
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
6
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>
add-detail-xl.safetensors
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)
BeyondBetaSDXLv4.safetensors
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
epiCNegative.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
epiCPhoto.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/e18e47f1a49d4bf18d115f9976a009b0/00000-0.webp
https://files.tungsten.run/uploads/85a161f247454a9ba6fff6fb66b7ec2b/00001-1.webp
https://files.tungsten.run/uploads/45359e28062244e9b77860ddc2bad0d9/00002-2.webp
Finished in 104.9 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: Photorealistic, ultra detailed, absurdres, a stunning cinematic photo, cinematic angle, Fujifilm XT3, Canon R5, Fujicolor Fujichrome Velvia 100, (full body:1), cybernetic robot masterpiece, best quality, (robotic face:1), (wires in the hair:1.1), absurdres, high details, 8K, photorealistic, amazing body, at distance, cowboy shot, posing, flirting, (playful gaze, smirking:1.1), 1girl, android, AI, machine, metal, (wires:1), tech, futuristic, highly detailed, masterpiece, best quality, hyperdetailed, highest detailed, high resolution textures, cinematic film shot, highly detailed, ultra-high resolutions, 32K UHD, sharp focus, best quality, masterpiece, realistic, real photo, sharp details, bright light, 8k, HDR, f.1/2, 70mm lens, Kodak, Analog style, epiCPhoto, Full negative prompt: (hair:1.5), (human skin:1), (portrait:1), (focus on face:1), (face close up), Bad quality, low details, cross eyed, worst quality, normal quality, low-res, sketch, poor design, deformed, disfigured, soft, bad composition, simple design, boring, watermark, text, error, cropped, blurry, BeyondBetaSDXLv4, epiCNegative 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:01<00:49, 1.71s/it] 7%|▋ | 2/30 [00:03<00:47, 1.71s/it] 10%|█ | 3/30 [00:05<00:46, 1.71s/it] 13%|█▎ | 4/30 [00:06<00:44, 1.71s/it] 17%|█▋ | 5/30 [00:08<00:42, 1.71s/it] 20%|██ | 6/30 [00:10<00:41, 1.72s/it] 23%|██▎ | 7/30 [00:12<00:39, 1.72s/it] 27%|██▋ | 8/30 [00:13<00:37, 1.72s/it] 30%|███ | 9/30 [00:15<00:36, 1.72s/it] 33%|███▎ | 10/30 [00:17<00:34, 1.72s/it] 37%|███▋ | 11/30 [00:18<00:32, 1.72s/it] 40%|████ | 12/30 [00:20<00:30, 1.72s/it] 43%|████▎ | 13/30 [00:22<00:29, 1.72s/it] 47%|████▋ | 14/30 [00:24<00:27, 1.72s/it] 50%|█████ | 15/30 [00:25<00:25, 1.73s/it] 53%|█████▎ | 16/30 [00:27<00:24, 1.73s/it] 57%|█████▋ | 17/30 [00:29<00:22, 1.73s/it] 60%|██████ | 18/30 [00:30<00:20, 1.73s/it] 63%|██████▎ | 19/30 [00:32<00:19, 1.73s/it] 67%|██████▋ | 20/30 [00:34<00:17, 1.73s/it] 70%|███████ | 21/30 [00:36<00:15, 1.73s/it] 73%|███████▎ | 22/30 [00:37<00:13, 1.74s/it] 77%|███████▋ | 23/30 [00:39<00:12, 1.74s/it] 80%|████████ | 24/30 [00:41<00:10, 1.74s/it] 83%|████████▎ | 25/30 [00:43<00:08, 1.74s/it] 87%|████████▋ | 26/30 [00:44<00:06, 1.74s/it] 90%|█████████ | 27/30 [00:46<00:05, 1.74s/it] 93%|█████████▎| 28/30 [00:48<00:03, 1.74s/it] 97%|█████████▋| 29/30 [00:50<00:01, 1.74s/it] 100%|██████████| 30/30 [00:50<00:00, 1.48s/it] 100%|██████████| 30/30 [00:50<00:00, 1.70s/it] Decoding latents in cuda:0... done in 1.69s Move latents to cpu... done in 0.01s 0: 640x480 1 face, 122.0ms Speed: 1.8ms preprocess, 122.0ms inference, 21.6ms postprocess per image at shape (1, 3, 640, 480)