tungsten-logo
Sign In
deepblue-xl
deepblue-xl

deepblue-xl

6 stars
Version: v2.5
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/3582abfae9bb48e09477711712ff8d62/00000-648349014.webp
https://files.tungsten.run/uploads/d143cac49f6b42ae90f53eea77f7aa0d/00001-648349015.webp
https://files.tungsten.run/uploads/b0a40d78c1d947e7aabf7b1e61dfb2d1/00002-648349016.webp
This example was created by evevalentine2017
Finished in 71.8 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Illustration, Asuka Langley from Neon Genesis Evangelion, chibi, happy, she is holding up a small wooden plaque carved with the word "tungsten" in the center. Full negative prompt: desaturated 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:01<00:29, 1.56s/it] 10%|█ | 2/20 [00:03<00:32, 1.80s/it] 15%|█▌ | 3/20 [00:05<00:32, 1.93s/it] 20%|██ | 4/20 [00:07<00:32, 2.01s/it] 25%|██▌ | 5/20 [00:09<00:30, 2.03s/it] 30%|███ | 6/20 [00:12<00:29, 2.11s/it] 35%|███▌ | 7/20 [00:14<00:27, 2.10s/it] 40%|████ | 8/20 [00:16<00:24, 2.08s/it] 45%|████▌ | 9/20 [00:18<00:22, 2.08s/it] 50%|█████ | 10/20 [00:20<00:20, 2.05s/it] 55%|█████▌ | 11/20 [00:22<00:17, 2.00s/it] 60%|██████ | 12/20 [00:24<00:15, 1.98s/it] 65%|██████▌ | 13/20 [00:26<00:13, 1.99s/it] 70%|███████ | 14/20 [00:27<00:11, 1.95s/it] 75%|███████▌ | 15/20 [00:29<00:09, 1.96s/it] 80%|████████ | 16/20 [00:31<00:07, 1.92s/it] 85%|████████▌ | 17/20 [00:33<00:05, 1.89s/it] 90%|█████████ | 18/20 [00:35<00:03, 1.85s/it] 95%|█████████▌| 19/20 [00:36<00:01, 1.67s/it] 100%|██████████| 20/20 [00:37<00:00, 1.46s/it] 100%|██████████| 20/20 [00:37<00:00, 1.88s/it] Decoding latents in cuda:0... done in 1.77s Move latents to cpu... done in 0.02s 0: 640x480 1 face, 167.3ms Speed: 3.2ms preprocess, 167.3ms inference, 20.1ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:07, 1.17it/s] 20%|██ | 2/10 [00:01<00:06, 1.14it/s] 30%|███ | 3/10 [00:02<00:06, 1.15it/s] 40%|████ | 4/10 [00:03<00:05, 1.19it/s] 50%|█████ | 5/10 [00:04<00:04, 1.17it/s] 60%|██████ | 6/10 [00:04<00:03, 1.24it/s] 70%|███████ | 7/10 [00:05<00:02, 1.29it/s] 80%|████████ | 8/10 [00:06<00:01, 1.38it/s] 90%|█████████ | 9/10 [00:06<00:00, 1.56it/s] 100%|██████████| 10/10 [00:07<00:00, 1.79it/s] 100%|██████████| 10/10 [00:07<00:00, 1.40it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.2ms Speed: 2.6ms preprocess, 8.2ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:06, 1.37it/s] 20%|██ | 2/10 [00:01<00:05, 1.41it/s] 30%|███ | 3/10 [00:02<00:04, 1.43it/s] 40%|████ | 4/10 [00:02<00:04, 1.44it/s] 50%|█████ | 5/10 [00:03<00:03, 1.42it/s] 60%|██████ | 6/10 [00:04<00:02, 1.44it/s] 70%|███████ | 7/10 [00:04<00:02, 1.46it/s] 80%|████████ | 8/10 [00:05<00:01, 1.49it/s] 90%|█████████ | 9/10 [00:05<00:00, 1.64it/s] 100%|██████████| 10/10 [00:06<00:00, 1.91it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.2ms Speed: 2.5ms preprocess, 8.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:05, 1.52it/s] 20%|██ | 2/10 [00:01<00:05, 1.40it/s] 30%|███ | 3/10 [00:02<00:05, 1.37it/s] 40%|████ | 4/10 [00:02<00:04, 1.40it/s] 50%|█████ | 5/10 [00:03<00:03, 1.39it/s] 60%|██████ | 6/10 [00:04<00:02, 1.40it/s] 70%|███████ | 7/10 [00:05<00:02, 1.39it/s] 80%|████████ | 8/10 [00:05<00:01, 1.45it/s] 90%|█████████ | 9/10 [00:06<00:00, 1.63it/s] 100%|██████████| 10/10 [00:06<00:00, 1.89it/s] 100%|██████████| 10/10 [00:06<00:00, 1.56it/s] Decoding latents in cuda:0... done in 0.58s 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/3582abfae9bb48e09477711712ff8d62/00000-648349014.webp
https://files.tungsten.run/uploads/d143cac49f6b42ae90f53eea77f7aa0d/00001-648349015.webp
https://files.tungsten.run/uploads/b0a40d78c1d947e7aabf7b1e61dfb2d1/00002-648349016.webp
This example was created by evevalentine2017
Finished in 71.8 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Illustration, Asuka Langley from Neon Genesis Evangelion, chibi, happy, she is holding up a small wooden plaque carved with the word "tungsten" in the center. Full negative prompt: desaturated 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:01<00:29, 1.56s/it] 10%|█ | 2/20 [00:03<00:32, 1.80s/it] 15%|█▌ | 3/20 [00:05<00:32, 1.93s/it] 20%|██ | 4/20 [00:07<00:32, 2.01s/it] 25%|██▌ | 5/20 [00:09<00:30, 2.03s/it] 30%|███ | 6/20 [00:12<00:29, 2.11s/it] 35%|███▌ | 7/20 [00:14<00:27, 2.10s/it] 40%|████ | 8/20 [00:16<00:24, 2.08s/it] 45%|████▌ | 9/20 [00:18<00:22, 2.08s/it] 50%|█████ | 10/20 [00:20<00:20, 2.05s/it] 55%|█████▌ | 11/20 [00:22<00:17, 2.00s/it] 60%|██████ | 12/20 [00:24<00:15, 1.98s/it] 65%|██████▌ | 13/20 [00:26<00:13, 1.99s/it] 70%|███████ | 14/20 [00:27<00:11, 1.95s/it] 75%|███████▌ | 15/20 [00:29<00:09, 1.96s/it] 80%|████████ | 16/20 [00:31<00:07, 1.92s/it] 85%|████████▌ | 17/20 [00:33<00:05, 1.89s/it] 90%|█████████ | 18/20 [00:35<00:03, 1.85s/it] 95%|█████████▌| 19/20 [00:36<00:01, 1.67s/it] 100%|██████████| 20/20 [00:37<00:00, 1.46s/it] 100%|██████████| 20/20 [00:37<00:00, 1.88s/it] Decoding latents in cuda:0... done in 1.77s Move latents to cpu... done in 0.02s 0: 640x480 1 face, 167.3ms Speed: 3.2ms preprocess, 167.3ms inference, 20.1ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:07, 1.17it/s] 20%|██ | 2/10 [00:01<00:06, 1.14it/s] 30%|███ | 3/10 [00:02<00:06, 1.15it/s] 40%|████ | 4/10 [00:03<00:05, 1.19it/s] 50%|█████ | 5/10 [00:04<00:04, 1.17it/s] 60%|██████ | 6/10 [00:04<00:03, 1.24it/s] 70%|███████ | 7/10 [00:05<00:02, 1.29it/s] 80%|████████ | 8/10 [00:06<00:01, 1.38it/s] 90%|█████████ | 9/10 [00:06<00:00, 1.56it/s] 100%|██████████| 10/10 [00:07<00:00, 1.79it/s] 100%|██████████| 10/10 [00:07<00:00, 1.40it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.2ms Speed: 2.6ms preprocess, 8.2ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:06, 1.37it/s] 20%|██ | 2/10 [00:01<00:05, 1.41it/s] 30%|███ | 3/10 [00:02<00:04, 1.43it/s] 40%|████ | 4/10 [00:02<00:04, 1.44it/s] 50%|█████ | 5/10 [00:03<00:03, 1.42it/s] 60%|██████ | 6/10 [00:04<00:02, 1.44it/s] 70%|███████ | 7/10 [00:04<00:02, 1.46it/s] 80%|████████ | 8/10 [00:05<00:01, 1.49it/s] 90%|█████████ | 9/10 [00:05<00:00, 1.64it/s] 100%|██████████| 10/10 [00:06<00:00, 1.91it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.2ms Speed: 2.5ms preprocess, 8.2ms inference, 1.5ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:05, 1.52it/s] 20%|██ | 2/10 [00:01<00:05, 1.40it/s] 30%|███ | 3/10 [00:02<00:05, 1.37it/s] 40%|████ | 4/10 [00:02<00:04, 1.40it/s] 50%|█████ | 5/10 [00:03<00:03, 1.39it/s] 60%|██████ | 6/10 [00:04<00:02, 1.40it/s] 70%|███████ | 7/10 [00:05<00:02, 1.39it/s] 80%|████████ | 8/10 [00:05<00:01, 1.45it/s] 90%|█████████ | 9/10 [00:06<00:00, 1.63it/s] 100%|██████████| 10/10 [00:06<00:00, 1.89it/s] 100%|██████████| 10/10 [00:06<00:00, 1.56it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s Uploading outputs... Finished.