tungsten-logo
Sign In
westmix-realistic
westmix-realistic

westmix-realistic

22 stars
Version: v1.5
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
saturation
Adjust saturation
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/b156003bcd3f4fbc84a106db67d5b7a3/00000-1425640400.webp
https://files.tungsten.run/uploads/8f2c9e99d0f642779396396a93e37c30/00001-1425640401.webp
https://files.tungsten.run/uploads/2187c7c47c734250ba7a67cdf2368762/00002-1425640402.webp
https://files.tungsten.run/uploads/c53f0dbe94a54729a9a26eb4f758991c/00003-1425640403.webp
This example was created by evevalentine2017
Finished in 179.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: beautiful eyes, beautiful girl, high detail skin, high detail eyes, high detail hair, highres, ultra detailed, sharpen picture, highly detailed, masterpiece, best quality, photorealistic, 1girl, short hair, braid, wearing a red summer dress, walking in a small village on the coast, birds, blue sky, smile Full negative prompt: ((negative_hand-neg)), (imperfect anatomy:1), (monochrome), (3 legs), (3 shoes), (imperfect eyes), (ugly eyes), ((nsfw)), ((nipples)), ((nudity)), deformed pupils, deformed iris, hat, teeth, ((asian)), ((holding)), miscolor, odd color, bad color, barefoot, (worst quality:1.4), (low quality:1.4),(monochrome:1.1),bad anatomy, extra limbs, fat, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), bad anatomy, text, error, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, username, blurry, bad feet, poorly drawn face, bad proportions, gross proportions, body merge, (3 legs:1.3), wrong feet side, cat ears, old fashion interior design, asian face, chinese face, japanese face, eurasian face, (3 thighs:1.2), 3 limbs, 3 shins, EasyNegativeV2, ng_deepnegative_v1_75t, 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:02<01:13, 2.53s/it] 7%|▋ | 2/30 [00:06<01:33, 3.33s/it] 10%|█ | 3/30 [00:10<01:34, 3.49s/it] 13%|█▎ | 4/30 [00:13<01:31, 3.52s/it] 17%|█▋ | 5/30 [00:17<01:29, 3.58s/it] 20%|██ | 6/30 [00:20<01:26, 3.59s/it] 23%|██▎ | 7/30 [00:24<01:23, 3.62s/it] 27%|██▋ | 8/30 [00:28<01:18, 3.56s/it] 30%|███ | 9/30 [00:31<01:15, 3.57s/it] 33%|███▎ | 10/30 [00:35<01:11, 3.57s/it] 37%|███▋ | 11/30 [00:38<01:07, 3.55s/it] 40%|████ | 12/30 [00:42<01:02, 3.49s/it] 43%|████▎ | 13/30 [00:45<01:00, 3.54s/it] 47%|████▋ | 14/30 [00:48<00:52, 3.27s/it] 50%|█████ | 15/30 [00:51<00:46, 3.08s/it] 53%|█████▎ | 16/30 [00:53<00:41, 2.99s/it] 57%|█████▋ | 17/30 [00:56<00:37, 2.89s/it] 60%|██████ | 18/30 [00:59<00:35, 2.99s/it] 63%|██████▎ | 19/30 [01:02<00:33, 3.07s/it] 67%|██████▋ | 20/30 [01:05<00:29, 2.99s/it] 70%|███████ | 21/30 [01:09<00:27, 3.10s/it] 73%|███████▎ | 22/30 [01:12<00:25, 3.13s/it] 77%|███████▋ | 23/30 [01:14<00:20, 2.96s/it] 80%|████████ | 24/30 [01:17<00:17, 2.84s/it] 83%|████████▎ | 25/30 [01:20<00:14, 2.96s/it] 87%|████████▋ | 26/30 [01:23<00:11, 2.99s/it] 90%|█████████ | 27/30 [01:26<00:08, 2.94s/it] 93%|█████████▎| 28/30 [01:29<00:05, 2.87s/it] 97%|█████████▋| 29/30 [01:31<00:02, 2.61s/it] 100%|██████████| 30/30 [01:31<00:00, 2.02s/it] 100%|██████████| 30/30 [01:31<00:00, 3.06s/it] Decoding latents in cuda:0... done in 0.98s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.7ms preprocess, 7.8ms inference, 24.5ms 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
saturation
Adjust saturation
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/b156003bcd3f4fbc84a106db67d5b7a3/00000-1425640400.webp
https://files.tungsten.run/uploads/8f2c9e99d0f642779396396a93e37c30/00001-1425640401.webp
https://files.tungsten.run/uploads/2187c7c47c734250ba7a67cdf2368762/00002-1425640402.webp
https://files.tungsten.run/uploads/c53f0dbe94a54729a9a26eb4f758991c/00003-1425640403.webp
This example was created by evevalentine2017
Finished in 179.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: beautiful eyes, beautiful girl, high detail skin, high detail eyes, high detail hair, highres, ultra detailed, sharpen picture, highly detailed, masterpiece, best quality, photorealistic, 1girl, short hair, braid, wearing a red summer dress, walking in a small village on the coast, birds, blue sky, smile Full negative prompt: ((negative_hand-neg)), (imperfect anatomy:1), (monochrome), (3 legs), (3 shoes), (imperfect eyes), (ugly eyes), ((nsfw)), ((nipples)), ((nudity)), deformed pupils, deformed iris, hat, teeth, ((asian)), ((holding)), miscolor, odd color, bad color, barefoot, (worst quality:1.4), (low quality:1.4),(monochrome:1.1),bad anatomy, extra limbs, fat, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, ((monochrome)), ((grayscale)), bad anatomy, text, error, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, username, blurry, bad feet, poorly drawn face, bad proportions, gross proportions, body merge, (3 legs:1.3), wrong feet side, cat ears, old fashion interior design, asian face, chinese face, japanese face, eurasian face, (3 thighs:1.2), 3 limbs, 3 shins, EasyNegativeV2, ng_deepnegative_v1_75t, 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:02<01:13, 2.53s/it] 7%|▋ | 2/30 [00:06<01:33, 3.33s/it] 10%|█ | 3/30 [00:10<01:34, 3.49s/it] 13%|█▎ | 4/30 [00:13<01:31, 3.52s/it] 17%|█▋ | 5/30 [00:17<01:29, 3.58s/it] 20%|██ | 6/30 [00:20<01:26, 3.59s/it] 23%|██▎ | 7/30 [00:24<01:23, 3.62s/it] 27%|██▋ | 8/30 [00:28<01:18, 3.56s/it] 30%|███ | 9/30 [00:31<01:15, 3.57s/it] 33%|███▎ | 10/30 [00:35<01:11, 3.57s/it] 37%|███▋ | 11/30 [00:38<01:07, 3.55s/it] 40%|████ | 12/30 [00:42<01:02, 3.49s/it] 43%|████▎ | 13/30 [00:45<01:00, 3.54s/it] 47%|████▋ | 14/30 [00:48<00:52, 3.27s/it] 50%|█████ | 15/30 [00:51<00:46, 3.08s/it] 53%|█████▎ | 16/30 [00:53<00:41, 2.99s/it] 57%|█████▋ | 17/30 [00:56<00:37, 2.89s/it] 60%|██████ | 18/30 [00:59<00:35, 2.99s/it] 63%|██████▎ | 19/30 [01:02<00:33, 3.07s/it] 67%|██████▋ | 20/30 [01:05<00:29, 2.99s/it] 70%|███████ | 21/30 [01:09<00:27, 3.10s/it] 73%|███████▎ | 22/30 [01:12<00:25, 3.13s/it] 77%|███████▋ | 23/30 [01:14<00:20, 2.96s/it] 80%|████████ | 24/30 [01:17<00:17, 2.84s/it] 83%|████████▎ | 25/30 [01:20<00:14, 2.96s/it] 87%|████████▋ | 26/30 [01:23<00:11, 2.99s/it] 90%|█████████ | 27/30 [01:26<00:08, 2.94s/it] 93%|█████████▎| 28/30 [01:29<00:05, 2.87s/it] 97%|█████████▋| 29/30 [01:31<00:02, 2.61s/it] 100%|██████████| 30/30 [01:31<00:00, 2.02s/it] 100%|██████████| 30/30 [01:31<00:00, 3.06s/it] Decoding latents in cuda:0... done in 0.98s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 3.7ms preprocess, 7.8ms inference, 24.5ms postprocess per image at shape (1, 3, 640, 640)