tungsten-logo
Sign In
Putin Caricature with Albedo Base XL
albedo-base-xl:v2.0
evevalentine2017
evevalentine2017
·
Feb 16
361
Input
prompt
Specify things to see in the output
Caricature, best quality
negative_prompt
Specify things to not see in the output
bad quality, worst quality, realistic
num_outputs
Number of output images
3
width
Output image width
1344
height
Output image height
1344
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
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.
2264445158
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.
https://files.tungsten.run/uploads/cb4fa4d2993444b5aba33412a06cd2f0/%D0%92%D0%BB%D0%B0%D0%B4%D0%B8%D0%BC%D0%B8%D1%80_%D0%9F%D1%83%D1%82%D0%B8%D0%BD_(18-06-2023)_(cropped).jpg
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0
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 Karras
samping_steps
Number of denoising steps
40
cfg_scale
Scale for classifier-free guidance
12
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>
SDXL Detail.safetensors
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)
badhandv4.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
negative_hand-neg.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-hands-5.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/d74aa345fa5e4f1884c6e93cdd318e38/00000-2264445158.webp
https://files.tungsten.run/uploads/4237c6447c2f49649507bfbd8217e5b8/00001-2264445159.webp
https://files.tungsten.run/uploads/12df2bfb46ef4d95a5772c5f1bc4a42b/00002-2264445160.webp
Finished in 72.7 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Caricature, best quality Full negative prompt: bad quality, worst quality, realistic 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████| 1/1 [00:02<00:00, 2.45s/it] 100%|██████████| 1/1 [00:02<00:00, 2.45s/it] Decoding latents in cuda:0... done in 4.4s Move latents to cpu... done in 0.05s 0: 640x640 1 face, 7.8ms Speed: 3.7ms preprocess, 7.8ms inference, 32.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:13, 1.31it/s] 11%|█ | 2/19 [00:01<00:13, 1.30it/s] 16%|█▌ | 3/19 [00:02<00:12, 1.30it/s] 21%|██ | 4/19 [00:03<00:11, 1.31it/s] 26%|██▋ | 5/19 [00:03<00:10, 1.31it/s] 32%|███▏ | 6/19 [00:04<00:09, 1.31it/s] 37%|███▋ | 7/19 [00:05<00:09, 1.30it/s] 42%|████▏ | 8/19 [00:06<00:08, 1.30it/s] 47%|████▋ | 9/19 [00:06<00:07, 1.30it/s] 53%|█████▎ | 10/19 [00:07<00:06, 1.30it/s] 58%|█████▊ | 11/19 [00:08<00:06, 1.30it/s] 63%|██████▎ | 12/19 [00:09<00:05, 1.29it/s] 68%|██████▊ | 13/19 [00:10<00:04, 1.29it/s] 74%|███████▎ | 14/19 [00:10<00:03, 1.29it/s] 79%|███████▉ | 15/19 [00:11<00:03, 1.29it/s] 84%|████████▍ | 16/19 [00:12<00:02, 1.28it/s] 89%|████████▉ | 17/19 [00:13<00:01, 1.28it/s] 95%|█████████▍| 18/19 [00:13<00:00, 1.28it/s] 100%|██████████| 19/19 [00:14<00:00, 1.28it/s] 100%|██████████| 19/19 [00:14<00:00, 1.29it/s] Decoding latents in cuda:0... done in 1.48s Move latents to cpu... done in 0.02s 0: 640x640 (no detections), 7.2ms Speed: 3.6ms preprocess, 7.2ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:13, 1.35it/s] 11%|█ | 2/19 [00:01<00:12, 1.32it/s] 16%|█▌ | 3/19 [00:02<00:12, 1.31it/s] 21%|██ | 4/19 [00:03<00:11, 1.31it/s] 26%|██▋ | 5/19 [00:03<00:10, 1.32it/s] 32%|███▏ | 6/19 [00:04<00:09, 1.31it/s] 37%|███▋ | 7/19 [00:05<00:09, 1.31it/s] 42%|████▏ | 8/19 [00:06<00:08, 1.31it/s] 47%|████▋ | 9/19 [00:06<00:07, 1.32it/s] 53%|█████▎ | 10/19 [00:07<00:06, 1.32it/s] 58%|█████▊ | 11/19 [00:08<00:06, 1.32it/s] 63%|██████▎ | 12/19 [00:09<00:05, 1.32it/s] 68%|██████▊ | 13/19 [00:09<00:04, 1.32it/s] 74%|███████▎ | 14/19 [00:10<00:03, 1.32it/s] 79%|███████▉ | 15/19 [00:11<00:03, 1.32it/s] 84%|████████▍ | 16/19 [00:12<00:02, 1.32it/s] 89%|████████▉ | 17/19 [00:12<00:01, 1.32it/s] 95%|█████████▍| 18/19 [00:13<00:00, 1.33it/s] 100%|██████████| 19/19 [00:14<00:00, 1.33it/s] 100%|██████████| 19/19 [00:14<00:00, 1.32it/s] Decoding latents in cuda:0... done in 1.46s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.1ms Speed: 3.4ms preprocess, 7.1ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:13, 1.37it/s] 11%|█ | 2/19 [00:01<00:12, 1.33it/s] 16%|█▌ | 3/19 [00:02<00:12, 1.32it/s] 21%|██ | 4/19 [00:03<00:11, 1.33it/s] 26%|██▋ | 5/19 [00:03<00:10, 1.33it/s] 32%|███▏ | 6/19 [00:04<00:09, 1.33it/s] 37%|███▋ | 7/19 [00:05<00:09, 1.33it/s] 42%|████▏ | 8/19 [00:06<00:08, 1.32it/s] 47%|████▋ | 9/19 [00:06<00:07, 1.32it/s] 53%|█████▎ | 10/19 [00:07<00:06, 1.32it/s] 58%|█████▊ | 11/19 [00:08<00:06, 1.31it/s] 63%|██████▎ | 12/19 [00:09<00:05, 1.31it/s] 68%|██████▊ | 13/19 [00:09<00:04, 1.31it/s] 74%|███████▎ | 14/19 [00:10<00:03, 1.31it/s] 79%|███████▉ | 15/19 [00:11<00:03, 1.31it/s] 84%|████████▍ | 16/19 [00:12<00:02, 1.31it/s] 89%|████████▉ | 17/19 [00:12<00:01, 1.31it/s] 95%|█████████▍| 18/19 [00:13<00:00, 1.31it/s] 100%|██████████| 19/19 [00:14<00:00, 1.32it/s] 100%|██████████| 19/19 [00:14<00:00, 1.32it/s] Decoding latents in cuda:0... done in 1.45s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.5ms Speed: 3.6ms preprocess, 7.5ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.
prompt
Specify things to see in the output
Caricature, best quality
negative_prompt
Specify things to not see in the output
bad quality, worst quality, realistic
num_outputs
Number of output images
3
width
Output image width
1344
height
Output image height
1344
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
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.
2264445158
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.
https://files.tungsten.run/uploads/cb4fa4d2993444b5aba33412a06cd2f0/%D0%92%D0%BB%D0%B0%D0%B4%D0%B8%D0%BC%D0%B8%D1%80_%D0%9F%D1%83%D1%82%D0%B8%D0%BD_(18-06-2023)_(cropped).jpg
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
0
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 Karras
samping_steps
Number of denoising steps
40
cfg_scale
Scale for classifier-free guidance
12
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>
SDXL Detail.safetensors
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)
badhandv4.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
negative_hand-neg.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-hands-5.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/d74aa345fa5e4f1884c6e93cdd318e38/00000-2264445158.webp
https://files.tungsten.run/uploads/4237c6447c2f49649507bfbd8217e5b8/00001-2264445159.webp
https://files.tungsten.run/uploads/12df2bfb46ef4d95a5772c5f1bc4a42b/00002-2264445160.webp
Finished in 72.7 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Caricature, best quality Full negative prompt: bad quality, worst quality, realistic 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████| 1/1 [00:02<00:00, 2.45s/it] 100%|██████████| 1/1 [00:02<00:00, 2.45s/it] Decoding latents in cuda:0... done in 4.4s Move latents to cpu... done in 0.05s 0: 640x640 1 face, 7.8ms Speed: 3.7ms preprocess, 7.8ms inference, 32.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:13, 1.31it/s] 11%|█ | 2/19 [00:01<00:13, 1.30it/s] 16%|█▌ | 3/19 [00:02<00:12, 1.30it/s] 21%|██ | 4/19 [00:03<00:11, 1.31it/s] 26%|██▋ | 5/19 [00:03<00:10, 1.31it/s] 32%|███▏ | 6/19 [00:04<00:09, 1.31it/s] 37%|███▋ | 7/19 [00:05<00:09, 1.30it/s] 42%|████▏ | 8/19 [00:06<00:08, 1.30it/s] 47%|████▋ | 9/19 [00:06<00:07, 1.30it/s] 53%|█████▎ | 10/19 [00:07<00:06, 1.30it/s] 58%|█████▊ | 11/19 [00:08<00:06, 1.30it/s] 63%|██████▎ | 12/19 [00:09<00:05, 1.29it/s] 68%|██████▊ | 13/19 [00:10<00:04, 1.29it/s] 74%|███████▎ | 14/19 [00:10<00:03, 1.29it/s] 79%|███████▉ | 15/19 [00:11<00:03, 1.29it/s] 84%|████████▍ | 16/19 [00:12<00:02, 1.28it/s] 89%|████████▉ | 17/19 [00:13<00:01, 1.28it/s] 95%|█████████▍| 18/19 [00:13<00:00, 1.28it/s] 100%|██████████| 19/19 [00:14<00:00, 1.28it/s] 100%|██████████| 19/19 [00:14<00:00, 1.29it/s] Decoding latents in cuda:0... done in 1.48s Move latents to cpu... done in 0.02s 0: 640x640 (no detections), 7.2ms Speed: 3.6ms preprocess, 7.2ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:13, 1.35it/s] 11%|█ | 2/19 [00:01<00:12, 1.32it/s] 16%|█▌ | 3/19 [00:02<00:12, 1.31it/s] 21%|██ | 4/19 [00:03<00:11, 1.31it/s] 26%|██▋ | 5/19 [00:03<00:10, 1.32it/s] 32%|███▏ | 6/19 [00:04<00:09, 1.31it/s] 37%|███▋ | 7/19 [00:05<00:09, 1.31it/s] 42%|████▏ | 8/19 [00:06<00:08, 1.31it/s] 47%|████▋ | 9/19 [00:06<00:07, 1.32it/s] 53%|█████▎ | 10/19 [00:07<00:06, 1.32it/s] 58%|█████▊ | 11/19 [00:08<00:06, 1.32it/s] 63%|██████▎ | 12/19 [00:09<00:05, 1.32it/s] 68%|██████▊ | 13/19 [00:09<00:04, 1.32it/s] 74%|███████▎ | 14/19 [00:10<00:03, 1.32it/s] 79%|███████▉ | 15/19 [00:11<00:03, 1.32it/s] 84%|████████▍ | 16/19 [00:12<00:02, 1.32it/s] 89%|████████▉ | 17/19 [00:12<00:01, 1.32it/s] 95%|█████████▍| 18/19 [00:13<00:00, 1.33it/s] 100%|██████████| 19/19 [00:14<00:00, 1.33it/s] 100%|██████████| 19/19 [00:14<00:00, 1.32it/s] Decoding latents in cuda:0... done in 1.46s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.1ms Speed: 3.4ms preprocess, 7.1ms inference, 0.8ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:13, 1.37it/s] 11%|█ | 2/19 [00:01<00:12, 1.33it/s] 16%|█▌ | 3/19 [00:02<00:12, 1.32it/s] 21%|██ | 4/19 [00:03<00:11, 1.33it/s] 26%|██▋ | 5/19 [00:03<00:10, 1.33it/s] 32%|███▏ | 6/19 [00:04<00:09, 1.33it/s] 37%|███▋ | 7/19 [00:05<00:09, 1.33it/s] 42%|████▏ | 8/19 [00:06<00:08, 1.32it/s] 47%|████▋ | 9/19 [00:06<00:07, 1.32it/s] 53%|█████▎ | 10/19 [00:07<00:06, 1.32it/s] 58%|█████▊ | 11/19 [00:08<00:06, 1.31it/s] 63%|██████▎ | 12/19 [00:09<00:05, 1.31it/s] 68%|██████▊ | 13/19 [00:09<00:04, 1.31it/s] 74%|███████▎ | 14/19 [00:10<00:03, 1.31it/s] 79%|███████▉ | 15/19 [00:11<00:03, 1.31it/s] 84%|████████▍ | 16/19 [00:12<00:02, 1.31it/s] 89%|████████▉ | 17/19 [00:12<00:01, 1.31it/s] 95%|█████████▍| 18/19 [00:13<00:00, 1.31it/s] 100%|██████████| 19/19 [00:14<00:00, 1.32it/s] 100%|██████████| 19/19 [00:14<00:00, 1.32it/s] Decoding latents in cuda:0... done in 1.45s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.5ms Speed: 3.6ms preprocess, 7.5ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.