tungsten-logo
Sign In
dreamtech-xl
dreamtech-xl

dreamtech-xl

5 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/e72b48b72c7c4e7f81f649817b0f54ba/00000-270691214.webp
https://files.tungsten.run/uploads/8723180b339641e2bd6451185d6c494d/00001-270691215.webp
https://files.tungsten.run/uploads/ce746bd5d43a4220897eecf0d27d6040/00002-270691216.webp
This example was created by evevalentine2017
Finished in 99.0 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, masterpiece, high quality, professional photo of a giant mecha, standing in the city, (science fiction:1), amazing quality, masterpiece, best quality, hyper detailed, ultra detailed, UHD, HDR, DOF, depth of field, perfect anatomy, sci-fi, a photograph of spawn, balanced composition, made of black goo, weathered patina, black costume, animated green cape made of liquid, "M" on chest, scary green glowing eyes, chains, moody lighting, cinematic, complex robot, biomechanical, hyper detailed, (holding a huge plasma cannon weapon with a glowing blue charged barrel), (holding), (behind him stand a loyal row of his mighty mech warriors they are ready and wanting battle to commence), (huge erupting explosions in the background, nucular mushroom bomb cloud in far distance), cinematic explosion style, extremely detailed,, high resolution textures, octane render, highly detailed, volumetric, dramatic lighting, dramatic light, highly detailed, ultra-high resolutions, 32K UHD, sharp focus, best quality, masterpiece, realistic, real photo, realistic metal textures, sharp details, bright light, 8k, HDR, f.1/2, 70mm lens, Kodak, Analog style, epiCPhoto Full negative prompt: Stormtrooper, 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 [00:02<01:11, 2.47s/it] 7%|▋ | 2/30 [00:04<01:09, 2.47s/it] 10%|█ | 3/30 [00:07<01:06, 2.47s/it] 13%|█▎ | 4/30 [00:09<01:04, 2.47s/it] 17%|█▋ | 5/30 [00:12<01:01, 2.48s/it] 20%|██ | 6/30 [00:14<00:59, 2.48s/it] 23%|██▎ | 7/30 [00:17<00:56, 2.48s/it] 27%|██▋ | 8/30 [00:19<00:54, 2.48s/it] 30%|███ | 9/30 [00:22<00:52, 2.48s/it] 33%|███▎ | 10/30 [00:24<00:49, 2.48s/it] 37%|███▋ | 11/30 [00:27<00:47, 2.48s/it] 40%|████ | 12/30 [00:29<00:44, 2.49s/it] 43%|████▎ | 13/30 [00:32<00:42, 2.49s/it] 47%|████▋ | 14/30 [00:34<00:39, 2.49s/it] 50%|█████ | 15/30 [00:37<00:37, 2.49s/it] 53%|█████▎ | 16/30 [00:39<00:34, 2.49s/it] 57%|█████▋ | 17/30 [00:42<00:32, 2.49s/it] 60%|██████ | 18/30 [00:44<00:29, 2.50s/it] 63%|██████▎ | 19/30 [00:47<00:27, 2.50s/it] 67%|██████▋ | 20/30 [00:49<00:24, 2.49s/it] 70%|███████ | 21/30 [00:52<00:22, 2.50s/it] 73%|███████▎ | 22/30 [00:54<00:19, 2.50s/it] 77%|███████▋ | 23/30 [00:57<00:17, 2.50s/it] 80%|████████ | 24/30 [00:59<00:14, 2.50s/it] 83%|████████▎ | 25/30 [01:02<00:12, 2.50s/it] 87%|████████▋ | 26/30 [01:04<00:09, 2.50s/it] 90%|█████████ | 27/30 [01:07<00:07, 2.50s/it] 93%|█████████▎| 28/30 [01:09<00:04, 2.50s/it] 97%|█████████▋| 29/30 [01:12<00:02, 2.50s/it] 100%|██████████| 30/30 [01:13<00:00, 2.13s/it] 100%|██████████| 30/30 [01:13<00:00, 2.45s/it] Decoding latents in cuda:0... done in 2.35s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 5.9ms Speed: 2.3ms preprocess, 5.9ms inference, 27.7ms postprocess per image at shape (1, 3, 640, 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/e72b48b72c7c4e7f81f649817b0f54ba/00000-270691214.webp
https://files.tungsten.run/uploads/8723180b339641e2bd6451185d6c494d/00001-270691215.webp
https://files.tungsten.run/uploads/ce746bd5d43a4220897eecf0d27d6040/00002-270691216.webp
This example was created by evevalentine2017
Finished in 99.0 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, masterpiece, high quality, professional photo of a giant mecha, standing in the city, (science fiction:1), amazing quality, masterpiece, best quality, hyper detailed, ultra detailed, UHD, HDR, DOF, depth of field, perfect anatomy, sci-fi, a photograph of spawn, balanced composition, made of black goo, weathered patina, black costume, animated green cape made of liquid, "M" on chest, scary green glowing eyes, chains, moody lighting, cinematic, complex robot, biomechanical, hyper detailed, (holding a huge plasma cannon weapon with a glowing blue charged barrel), (holding), (behind him stand a loyal row of his mighty mech warriors they are ready and wanting battle to commence), (huge erupting explosions in the background, nucular mushroom bomb cloud in far distance), cinematic explosion style, extremely detailed,, high resolution textures, octane render, highly detailed, volumetric, dramatic lighting, dramatic light, highly detailed, ultra-high resolutions, 32K UHD, sharp focus, best quality, masterpiece, realistic, real photo, realistic metal textures, sharp details, bright light, 8k, HDR, f.1/2, 70mm lens, Kodak, Analog style, epiCPhoto Full negative prompt: Stormtrooper, 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 [00:02<01:11, 2.47s/it] 7%|▋ | 2/30 [00:04<01:09, 2.47s/it] 10%|█ | 3/30 [00:07<01:06, 2.47s/it] 13%|█▎ | 4/30 [00:09<01:04, 2.47s/it] 17%|█▋ | 5/30 [00:12<01:01, 2.48s/it] 20%|██ | 6/30 [00:14<00:59, 2.48s/it] 23%|██▎ | 7/30 [00:17<00:56, 2.48s/it] 27%|██▋ | 8/30 [00:19<00:54, 2.48s/it] 30%|███ | 9/30 [00:22<00:52, 2.48s/it] 33%|███▎ | 10/30 [00:24<00:49, 2.48s/it] 37%|███▋ | 11/30 [00:27<00:47, 2.48s/it] 40%|████ | 12/30 [00:29<00:44, 2.49s/it] 43%|████▎ | 13/30 [00:32<00:42, 2.49s/it] 47%|████▋ | 14/30 [00:34<00:39, 2.49s/it] 50%|█████ | 15/30 [00:37<00:37, 2.49s/it] 53%|█████▎ | 16/30 [00:39<00:34, 2.49s/it] 57%|█████▋ | 17/30 [00:42<00:32, 2.49s/it] 60%|██████ | 18/30 [00:44<00:29, 2.50s/it] 63%|██████▎ | 19/30 [00:47<00:27, 2.50s/it] 67%|██████▋ | 20/30 [00:49<00:24, 2.49s/it] 70%|███████ | 21/30 [00:52<00:22, 2.50s/it] 73%|███████▎ | 22/30 [00:54<00:19, 2.50s/it] 77%|███████▋ | 23/30 [00:57<00:17, 2.50s/it] 80%|████████ | 24/30 [00:59<00:14, 2.50s/it] 83%|████████▎ | 25/30 [01:02<00:12, 2.50s/it] 87%|████████▋ | 26/30 [01:04<00:09, 2.50s/it] 90%|█████████ | 27/30 [01:07<00:07, 2.50s/it] 93%|█████████▎| 28/30 [01:09<00:04, 2.50s/it] 97%|█████████▋| 29/30 [01:12<00:02, 2.50s/it] 100%|██████████| 30/30 [01:13<00:00, 2.13s/it] 100%|██████████| 30/30 [01:13<00:00, 2.45s/it] Decoding latents in cuda:0... done in 2.35s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 5.9ms Speed: 2.3ms preprocess, 5.9ms inference, 27.7ms postprocess per image at shape (1, 3, 640, 640)