tungsten-logo
Sign In
perfectRSBmix
perfectRSBmix

perfectRSBmix

53 stars
Version: v7.1
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
Detailer
Detailer
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/de6929a739bd4aee8a4d53e072571a1e/output-cdf3ae72006442e4b0c379c5b59a39d9-00000-3868859098.webp
https://files.tungsten.run/uploads/3f999c6a55274bb2826df18e45a8f2f4/output-0eace576f78940968df7488a7a024da2-00001-3868859099.webp
https://files.tungsten.run/uploads/f020a6a2c1904379b3cc3695ebc76a3a/output-b5b798d53daf42cb8fe227c5146e3e9f-00002-3868859100.webp
This example was created by zennerhenric
Finished in 59.0 seconds
Using seed 3868859098 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Shogun Raiden, on knees, tongue out, blush, Full negative prompt: (negativeXL_D):0.75, (negative_hand-neg-SDXL):0.3, (ImgFixerPre0.3:0.2), unaestheticXL_bp5, (worst quality, low quality, normal quality):1.3, (monochrome, grayscale):1.2, (mutated, deformed):1.3, (bad anatomy):1.2, (watermark, text, username):1.2, mutated hands, bad hands, mutated feet, bad feet, missing fingers, extra digit, fewer digits, 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:00<00:21, 1.10it/s] 8%|▊ | 2/24 [00:01<00:20, 1.10it/s] 12%|█▎ | 3/24 [00:02<00:19, 1.10it/s] 17%|█▋ | 4/24 [00:03<00:18, 1.09it/s] 21%|██ | 5/24 [00:04<00:17, 1.09it/s] 25%|██▌ | 6/24 [00:05<00:16, 1.09it/s] 29%|██▉ | 7/24 [00:06<00:15, 1.09it/s] 33%|███▎ | 8/24 [00:07<00:14, 1.09it/s] 38%|███▊ | 9/24 [00:08<00:13, 1.09it/s] 42%|████▏ | 10/24 [00:09<00:14, 1.02s/it] 46%|████▌ | 11/24 [00:10<00:12, 1.01it/s] 50%|█████ | 12/24 [00:11<00:11, 1.03it/s] 54%|█████▍ | 13/24 [00:12<00:10, 1.04it/s] 58%|█████▊ | 14/24 [00:13<00:09, 1.06it/s] 62%|██████▎ | 15/24 [00:14<00:08, 1.06it/s] 67%|██████▋ | 16/24 [00:15<00:07, 1.07it/s] 71%|███████ | 17/24 [00:15<00:06, 1.07it/s] 75%|███████▌ | 18/24 [00:16<00:05, 1.07it/s] 79%|███████▉ | 19/24 [00:17<00:04, 1.07it/s] 83%|████████▎ | 20/24 [00:18<00:03, 1.07it/s] 88%|████████▊ | 21/24 [00:19<00:02, 1.07it/s] 92%|█████████▏| 22/24 [00:20<00:01, 1.07it/s] 96%|█████████▌| 23/24 [00:21<00:00, 1.07it/s] 100%|██████████| 24/24 [00:22<00:00, 1.06it/s] 100%|██████████| 24/24 [00:22<00:00, 1.06it/s] Decoding latents in cuda:0... done in 1.8s Move latents to cpu... done in 0.03s 0: 640x480 1 face, 158.3ms Speed: 2.6ms preprocess, 158.3ms inference, 29.9ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:07, 1.35it/s] 18%|█▊ | 2/11 [00:01<00:06, 1.50it/s] 27%|██▋ | 3/11 [00:01<00:05, 1.57it/s] 36%|███▋ | 4/11 [00:02<00:04, 1.61it/s] 45%|████▌ | 5/11 [00:03<00:03, 1.63it/s] 55%|█████▍ | 6/11 [00:03<00:03, 1.64it/s] 64%|██████▎ | 7/11 [00:04<00:02, 1.65it/s] 73%|███████▎ | 8/11 [00:04<00:01, 1.64it/s] 82%|████████▏ | 9/11 [00:05<00:01, 1.63it/s] 91%|█████████ | 10/11 [00:06<00:00, 1.64it/s] 100%|██████████| 11/11 [00:06<00:00, 1.66it/s] 100%|██████████| 11/11 [00:06<00:00, 1.62it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.4ms Speed: 2.4ms preprocess, 8.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:05, 1.67it/s] 18%|█▊ | 2/11 [00:01<00:05, 1.68it/s] 27%|██▋ | 3/11 [00:01<00:04, 1.67it/s] 36%|███▋ | 4/11 [00:02<00:04, 1.66it/s] 45%|████▌ | 5/11 [00:02<00:03, 1.67it/s] 55%|█████▍ | 6/11 [00:03<00:02, 1.67it/s] 64%|██████▎ | 7/11 [00:04<00:02, 1.67it/s] 73%|███████▎ | 8/11 [00:04<00:01, 1.67it/s] 82%|████████▏ | 9/11 [00:05<00:01, 1.67it/s] 91%|█████████ | 10/11 [00:05<00:00, 1.67it/s] 100%|██████████| 11/11 [00:06<00:00, 1.67it/s] 100%|██████████| 11/11 [00:06<00:00, 1.67it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 7.9ms Speed: 2.2ms preprocess, 7.9ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:06, 1.61it/s] 18%|█▊ | 2/11 [00:01<00:05, 1.64it/s] 27%|██▋ | 3/11 [00:01<00:04, 1.66it/s] 36%|███▋ | 4/11 [00:02<00:04, 1.68it/s] 45%|████▌ | 5/11 [00:02<00:03, 1.67it/s] 55%|█████▍ | 6/11 [00:03<00:02, 1.67it/s] 64%|██████▎ | 7/11 [00:04<00:02, 1.67it/s] 73%|███████▎ | 8/11 [00:04<00:01, 1.67it/s] 82%|████████▏ | 9/11 [00:05<00:01, 1.67it/s] 91%|█████████ | 10/11 [00:05<00:00, 1.67it/s] 100%|██████████| 11/11 [00:06<00:00, 1.67it/s] 100%|██████████| 11/11 [00:06<00:00, 1.67it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s Uploading files.. Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
Detailer
Detailer
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/de6929a739bd4aee8a4d53e072571a1e/output-cdf3ae72006442e4b0c379c5b59a39d9-00000-3868859098.webp
https://files.tungsten.run/uploads/3f999c6a55274bb2826df18e45a8f2f4/output-0eace576f78940968df7488a7a024da2-00001-3868859099.webp
https://files.tungsten.run/uploads/f020a6a2c1904379b3cc3695ebc76a3a/output-b5b798d53daf42cb8fe227c5146e3e9f-00002-3868859100.webp
This example was created by zennerhenric
Finished in 59.0 seconds
Using seed 3868859098 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Shogun Raiden, on knees, tongue out, blush, Full negative prompt: (negativeXL_D):0.75, (negative_hand-neg-SDXL):0.3, (ImgFixerPre0.3:0.2), unaestheticXL_bp5, (worst quality, low quality, normal quality):1.3, (monochrome, grayscale):1.2, (mutated, deformed):1.3, (bad anatomy):1.2, (watermark, text, username):1.2, mutated hands, bad hands, mutated feet, bad feet, missing fingers, extra digit, fewer digits, 0%| | 0/24 [00:00<?, ?it/s] 4%|▍ | 1/24 [00:00<00:21, 1.10it/s] 8%|▊ | 2/24 [00:01<00:20, 1.10it/s] 12%|█▎ | 3/24 [00:02<00:19, 1.10it/s] 17%|█▋ | 4/24 [00:03<00:18, 1.09it/s] 21%|██ | 5/24 [00:04<00:17, 1.09it/s] 25%|██▌ | 6/24 [00:05<00:16, 1.09it/s] 29%|██▉ | 7/24 [00:06<00:15, 1.09it/s] 33%|███▎ | 8/24 [00:07<00:14, 1.09it/s] 38%|███▊ | 9/24 [00:08<00:13, 1.09it/s] 42%|████▏ | 10/24 [00:09<00:14, 1.02s/it] 46%|████▌ | 11/24 [00:10<00:12, 1.01it/s] 50%|█████ | 12/24 [00:11<00:11, 1.03it/s] 54%|█████▍ | 13/24 [00:12<00:10, 1.04it/s] 58%|█████▊ | 14/24 [00:13<00:09, 1.06it/s] 62%|██████▎ | 15/24 [00:14<00:08, 1.06it/s] 67%|██████▋ | 16/24 [00:15<00:07, 1.07it/s] 71%|███████ | 17/24 [00:15<00:06, 1.07it/s] 75%|███████▌ | 18/24 [00:16<00:05, 1.07it/s] 79%|███████▉ | 19/24 [00:17<00:04, 1.07it/s] 83%|████████▎ | 20/24 [00:18<00:03, 1.07it/s] 88%|████████▊ | 21/24 [00:19<00:02, 1.07it/s] 92%|█████████▏| 22/24 [00:20<00:01, 1.07it/s] 96%|█████████▌| 23/24 [00:21<00:00, 1.07it/s] 100%|██████████| 24/24 [00:22<00:00, 1.06it/s] 100%|██████████| 24/24 [00:22<00:00, 1.06it/s] Decoding latents in cuda:0... done in 1.8s Move latents to cpu... done in 0.03s 0: 640x480 1 face, 158.3ms Speed: 2.6ms preprocess, 158.3ms inference, 29.9ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:07, 1.35it/s] 18%|█▊ | 2/11 [00:01<00:06, 1.50it/s] 27%|██▋ | 3/11 [00:01<00:05, 1.57it/s] 36%|███▋ | 4/11 [00:02<00:04, 1.61it/s] 45%|████▌ | 5/11 [00:03<00:03, 1.63it/s] 55%|█████▍ | 6/11 [00:03<00:03, 1.64it/s] 64%|██████▎ | 7/11 [00:04<00:02, 1.65it/s] 73%|███████▎ | 8/11 [00:04<00:01, 1.64it/s] 82%|████████▏ | 9/11 [00:05<00:01, 1.63it/s] 91%|█████████ | 10/11 [00:06<00:00, 1.64it/s] 100%|██████████| 11/11 [00:06<00:00, 1.66it/s] 100%|██████████| 11/11 [00:06<00:00, 1.62it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.4ms Speed: 2.4ms preprocess, 8.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:05, 1.67it/s] 18%|█▊ | 2/11 [00:01<00:05, 1.68it/s] 27%|██▋ | 3/11 [00:01<00:04, 1.67it/s] 36%|███▋ | 4/11 [00:02<00:04, 1.66it/s] 45%|████▌ | 5/11 [00:02<00:03, 1.67it/s] 55%|█████▍ | 6/11 [00:03<00:02, 1.67it/s] 64%|██████▎ | 7/11 [00:04<00:02, 1.67it/s] 73%|███████▎ | 8/11 [00:04<00:01, 1.67it/s] 82%|████████▏ | 9/11 [00:05<00:01, 1.67it/s] 91%|█████████ | 10/11 [00:05<00:00, 1.67it/s] 100%|██████████| 11/11 [00:06<00:00, 1.67it/s] 100%|██████████| 11/11 [00:06<00:00, 1.67it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 7.9ms Speed: 2.2ms preprocess, 7.9ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/11 [00:00<?, ?it/s] 9%|▉ | 1/11 [00:00<00:06, 1.61it/s] 18%|█▊ | 2/11 [00:01<00:05, 1.64it/s] 27%|██▋ | 3/11 [00:01<00:04, 1.66it/s] 36%|███▋ | 4/11 [00:02<00:04, 1.68it/s] 45%|████▌ | 5/11 [00:02<00:03, 1.67it/s] 55%|█████▍ | 6/11 [00:03<00:02, 1.67it/s] 64%|██████▎ | 7/11 [00:04<00:02, 1.67it/s] 73%|███████▎ | 8/11 [00:04<00:01, 1.67it/s] 82%|████████▏ | 9/11 [00:05<00:01, 1.67it/s] 91%|█████████ | 10/11 [00:05<00:00, 1.67it/s] 100%|██████████| 11/11 [00:06<00:00, 1.67it/s] 100%|██████████| 11/11 [00:06<00:00, 1.67it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s Uploading files.. Finished.