tungsten-logo
Sign In
Blueprint with Artisanal SDXL
artisanal-sdxl:alpha-1
evevalentine2017
evevalentine2017
·
Mar 6
356
Input
prompt
Specify things to see in the output
1 blueprint elven woman, cleavage, low angle, golden ratio, sketch art by Richard Gerstl
negative_prompt
Specify things to not see in the output
unaestheticXL2v10, Dramatic lighting, Cinematic, Shadows,
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
1.2
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.
330499600
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++ 3M SDE Karras
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
4
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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)
unaestheticXL2v10.safetensors
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/90b7ccf4a5104f779cc25bfec41f611b/00000-330499600.webp
https://files.tungsten.run/uploads/a81a5f18dab240a69b403b2c8180d5ab/00001-330499601.webp
https://files.tungsten.run/uploads/d482a9b11f0747919259513221bb1dd4/00002-330499602.webp
Finished in 102.4 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1 blueprint elven woman, cleavage, low angle, golden ratio, sketch art by Richard Gerstl, <lora:add-detail-xl:1.2> Full negative prompt: unaestheticXL2v10, Dramatic lighting, Cinematic, Shadows, 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:29, 3.08s/it] 7%|▋ | 2/30 [00:05<01:10, 2.50s/it] 10%|█ | 3/30 [00:07<01:01, 2.28s/it] 13%|█▎ | 4/30 [00:09<00:58, 2.25s/it] 17%|█▋ | 5/30 [00:11<00:54, 2.16s/it] 20%|██ | 6/30 [00:13<00:51, 2.14s/it] 23%|██▎ | 7/30 [00:15<00:50, 2.19s/it] 27%|██▋ | 8/30 [00:17<00:46, 2.10s/it] 30%|███ | 9/30 [00:19<00:42, 2.04s/it] 33%|███▎ | 10/30 [00:21<00:40, 2.04s/it] 37%|███▋ | 11/30 [00:23<00:39, 2.06s/it] 40%|████ | 12/30 [00:25<00:36, 2.03s/it] 43%|████▎ | 13/30 [00:27<00:34, 2.04s/it] 47%|████▋ | 14/30 [00:29<00:32, 2.05s/it] 50%|█████ | 15/30 [00:31<00:30, 2.06s/it] 53%|█████▎ | 16/30 [00:33<00:28, 2.02s/it] 57%|█████▋ | 17/30 [00:35<00:26, 2.02s/it] 60%|██████ | 18/30 [00:37<00:24, 2.00s/it] 63%|██████▎ | 19/30 [00:39<00:21, 1.99s/it] 67%|██████▋ | 20/30 [00:41<00:20, 2.00s/it] 70%|███████ | 21/30 [00:43<00:17, 2.00s/it] 73%|███████▎ | 22/30 [00:45<00:15, 1.89s/it] 77%|███████▋ | 23/30 [00:47<00:13, 1.88s/it] 80%|████████ | 24/30 [00:49<00:11, 1.86s/it] 83%|████████▎ | 25/30 [00:51<00:09, 1.88s/it] 87%|████████▋ | 26/30 [00:52<00:07, 1.84s/it] 90%|█████████ | 27/30 [00:54<00:05, 1.85s/it] 93%|█████████▎| 28/30 [00:56<00:03, 1.80s/it] 97%|█████████▋| 29/30 [00:57<00:01, 1.57s/it] 100%|██████████| 30/30 [00:58<00:00, 1.37s/it] 100%|██████████| 30/30 [00:58<00:00, 1.94s/it] Decoding latents in cuda:0... done in 1.73s Move latents to cpu... done in 0.02s 0: 640x480 1 face, 193.5ms Speed: 3.5ms preprocess, 193.5ms inference, 24.8ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:10, 1.19it/s] 14%|█▍ | 2/14 [00:01<00:09, 1.33it/s] 21%|██▏ | 3/14 [00:02<00:07, 1.41it/s] 29%|██▊ | 4/14 [00:02<00:07, 1.39it/s] 36%|███▌ | 5/14 [00:03<00:06, 1.39it/s] 43%|████▎ | 6/14 [00:04<00:05, 1.45it/s] 50%|█████ | 7/14 [00:04<00:04, 1.45it/s] 57%|█████▋ | 8/14 [00:05<00:04, 1.49it/s] 64%|██████▍ | 9/14 [00:06<00:03, 1.46it/s] 71%|███████▏ | 10/14 [00:06<00:02, 1.50it/s] 79%|███████▊ | 11/14 [00:07<00:01, 1.53it/s] 86%|████████▌ | 12/14 [00:08<00:01, 1.59it/s] 93%|█████████▎| 13/14 [00:08<00:00, 1.78it/s] 100%|██████████| 14/14 [00:08<00:00, 2.02it/s] 100%|██████████| 14/14 [00:08<00:00, 1.58it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.2ms Speed: 2.5ms preprocess, 8.2ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:09, 1.44it/s] 14%|█▍ | 2/14 [00:01<00:08, 1.43it/s] 21%|██▏ | 3/14 [00:02<00:07, 1.45it/s] 29%|██▊ | 4/14 [00:02<00:06, 1.45it/s] 36%|███▌ | 5/14 [00:03<00:06, 1.47it/s] 43%|████▎ | 6/14 [00:04<00:05, 1.54it/s] 50%|█████ | 7/14 [00:04<00:04, 1.56it/s] 57%|█████▋ | 8/14 [00:05<00:03, 1.57it/s] 64%|██████▍ | 9/14 [00:05<00:03, 1.54it/s] 71%|███████▏ | 10/14 [00:06<00:02, 1.58it/s] 79%|███████▊ | 11/14 [00:07<00:01, 1.56it/s] 86%|████████▌ | 12/14 [00:07<00:01, 1.62it/s] 93%|█████████▎| 13/14 [00:08<00:00, 1.84it/s] 100%|██████████| 14/14 [00:08<00:00, 2.08it/s] 100%|██████████| 14/14 [00:08<00:00, 1.65it/s] Decoding latents in cuda:0... done in 0.59s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.1ms Speed: 2.5ms preprocess, 8.1ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:09, 1.42it/s] 14%|█▍ | 2/14 [00:01<00:08, 1.47it/s] 21%|██▏ | 3/14 [00:02<00:07, 1.47it/s] 29%|██▊ | 4/14 [00:02<00:06, 1.47it/s] 36%|███▌ | 5/14 [00:03<00:06, 1.48it/s] 43%|████▎ | 6/14 [00:04<00:05, 1.52it/s] 50%|█████ | 7/14 [00:04<00:04, 1.54it/s] 57%|█████▋ | 8/14 [00:05<00:03, 1.56it/s] 64%|██████▍ | 9/14 [00:05<00:03, 1.55it/s] 71%|███████▏ | 10/14 [00:06<00:02, 1.57it/s] 79%|███████▊ | 11/14 [00:07<00:01, 1.55it/s] 86%|████████▌ | 12/14 [00:07<00:01, 1.58it/s] 93%|█████████▎| 13/14 [00:08<00:00, 1.80it/s] 100%|██████████| 14/14 [00:08<00:00, 2.04it/s] 100%|██████████| 14/14 [00:08<00:00, 1.64it/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
1 blueprint elven woman, cleavage, low angle, golden ratio, sketch art by Richard Gerstl
negative_prompt
Specify things to not see in the output
unaestheticXL2v10, Dramatic lighting, Cinematic, Shadows,
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
1.2
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.
330499600
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++ 3M SDE Karras
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
4
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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)
unaestheticXL2v10.safetensors
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/90b7ccf4a5104f779cc25bfec41f611b/00000-330499600.webp
https://files.tungsten.run/uploads/a81a5f18dab240a69b403b2c8180d5ab/00001-330499601.webp
https://files.tungsten.run/uploads/d482a9b11f0747919259513221bb1dd4/00002-330499602.webp
Finished in 102.4 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1 blueprint elven woman, cleavage, low angle, golden ratio, sketch art by Richard Gerstl, <lora:add-detail-xl:1.2> Full negative prompt: unaestheticXL2v10, Dramatic lighting, Cinematic, Shadows, 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:29, 3.08s/it] 7%|▋ | 2/30 [00:05<01:10, 2.50s/it] 10%|█ | 3/30 [00:07<01:01, 2.28s/it] 13%|█▎ | 4/30 [00:09<00:58, 2.25s/it] 17%|█▋ | 5/30 [00:11<00:54, 2.16s/it] 20%|██ | 6/30 [00:13<00:51, 2.14s/it] 23%|██▎ | 7/30 [00:15<00:50, 2.19s/it] 27%|██▋ | 8/30 [00:17<00:46, 2.10s/it] 30%|███ | 9/30 [00:19<00:42, 2.04s/it] 33%|███▎ | 10/30 [00:21<00:40, 2.04s/it] 37%|███▋ | 11/30 [00:23<00:39, 2.06s/it] 40%|████ | 12/30 [00:25<00:36, 2.03s/it] 43%|████▎ | 13/30 [00:27<00:34, 2.04s/it] 47%|████▋ | 14/30 [00:29<00:32, 2.05s/it] 50%|█████ | 15/30 [00:31<00:30, 2.06s/it] 53%|█████▎ | 16/30 [00:33<00:28, 2.02s/it] 57%|█████▋ | 17/30 [00:35<00:26, 2.02s/it] 60%|██████ | 18/30 [00:37<00:24, 2.00s/it] 63%|██████▎ | 19/30 [00:39<00:21, 1.99s/it] 67%|██████▋ | 20/30 [00:41<00:20, 2.00s/it] 70%|███████ | 21/30 [00:43<00:17, 2.00s/it] 73%|███████▎ | 22/30 [00:45<00:15, 1.89s/it] 77%|███████▋ | 23/30 [00:47<00:13, 1.88s/it] 80%|████████ | 24/30 [00:49<00:11, 1.86s/it] 83%|████████▎ | 25/30 [00:51<00:09, 1.88s/it] 87%|████████▋ | 26/30 [00:52<00:07, 1.84s/it] 90%|█████████ | 27/30 [00:54<00:05, 1.85s/it] 93%|█████████▎| 28/30 [00:56<00:03, 1.80s/it] 97%|█████████▋| 29/30 [00:57<00:01, 1.57s/it] 100%|██████████| 30/30 [00:58<00:00, 1.37s/it] 100%|██████████| 30/30 [00:58<00:00, 1.94s/it] Decoding latents in cuda:0... done in 1.73s Move latents to cpu... done in 0.02s 0: 640x480 1 face, 193.5ms Speed: 3.5ms preprocess, 193.5ms inference, 24.8ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:10, 1.19it/s] 14%|█▍ | 2/14 [00:01<00:09, 1.33it/s] 21%|██▏ | 3/14 [00:02<00:07, 1.41it/s] 29%|██▊ | 4/14 [00:02<00:07, 1.39it/s] 36%|███▌ | 5/14 [00:03<00:06, 1.39it/s] 43%|████▎ | 6/14 [00:04<00:05, 1.45it/s] 50%|█████ | 7/14 [00:04<00:04, 1.45it/s] 57%|█████▋ | 8/14 [00:05<00:04, 1.49it/s] 64%|██████▍ | 9/14 [00:06<00:03, 1.46it/s] 71%|███████▏ | 10/14 [00:06<00:02, 1.50it/s] 79%|███████▊ | 11/14 [00:07<00:01, 1.53it/s] 86%|████████▌ | 12/14 [00:08<00:01, 1.59it/s] 93%|█████████▎| 13/14 [00:08<00:00, 1.78it/s] 100%|██████████| 14/14 [00:08<00:00, 2.02it/s] 100%|██████████| 14/14 [00:08<00:00, 1.58it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.2ms Speed: 2.5ms preprocess, 8.2ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:09, 1.44it/s] 14%|█▍ | 2/14 [00:01<00:08, 1.43it/s] 21%|██▏ | 3/14 [00:02<00:07, 1.45it/s] 29%|██▊ | 4/14 [00:02<00:06, 1.45it/s] 36%|███▌ | 5/14 [00:03<00:06, 1.47it/s] 43%|████▎ | 6/14 [00:04<00:05, 1.54it/s] 50%|█████ | 7/14 [00:04<00:04, 1.56it/s] 57%|█████▋ | 8/14 [00:05<00:03, 1.57it/s] 64%|██████▍ | 9/14 [00:05<00:03, 1.54it/s] 71%|███████▏ | 10/14 [00:06<00:02, 1.58it/s] 79%|███████▊ | 11/14 [00:07<00:01, 1.56it/s] 86%|████████▌ | 12/14 [00:07<00:01, 1.62it/s] 93%|█████████▎| 13/14 [00:08<00:00, 1.84it/s] 100%|██████████| 14/14 [00:08<00:00, 2.08it/s] 100%|██████████| 14/14 [00:08<00:00, 1.65it/s] Decoding latents in cuda:0... done in 0.59s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.1ms Speed: 2.5ms preprocess, 8.1ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:09, 1.42it/s] 14%|█▍ | 2/14 [00:01<00:08, 1.47it/s] 21%|██▏ | 3/14 [00:02<00:07, 1.47it/s] 29%|██▊ | 4/14 [00:02<00:06, 1.47it/s] 36%|███▌ | 5/14 [00:03<00:06, 1.48it/s] 43%|████▎ | 6/14 [00:04<00:05, 1.52it/s] 50%|█████ | 7/14 [00:04<00:04, 1.54it/s] 57%|█████▋ | 8/14 [00:05<00:03, 1.56it/s] 64%|██████▍ | 9/14 [00:05<00:03, 1.55it/s] 71%|███████▏ | 10/14 [00:06<00:02, 1.57it/s] 79%|███████▊ | 11/14 [00:07<00:01, 1.55it/s] 86%|████████▌ | 12/14 [00:07<00:01, 1.58it/s] 93%|█████████▎| 13/14 [00:08<00:00, 1.80it/s] 100%|██████████| 14/14 [00:08<00:00, 2.04it/s] 100%|██████████| 14/14 [00:08<00:00, 1.64it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s Uploading outputs... Finished.