tungsten-logo
Sign In
semi-real-anime-mix
semi-real-anime-mix

semi-real-anime-mix

5 stars
Version: v1.0
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/dd3b0c8e2e03456b9c98756212e714cd/00000-3520698549.webp
https://files.tungsten.run/uploads/2faa798162474faeb02677211f0f3b21/00001-3520698550.webp
https://files.tungsten.run/uploads/6381d34989d441bb80b9de1e38b03f35/00002-3520698551.webp
https://files.tungsten.run/uploads/78e6b3d7352543c38d8f3a470388ce13/00003-3520698552.webp
This example was created by evevalentine2017
Finished in 52.4 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/kl-f8-anime2_fp16.safetensors Full prompt: (masterpiece, best quality), 1girl, blonde messy hair, choker, big smile, pajamas, see-through, glasses Full negative prompt: 3 legs, (worst quality, low quality:1.4), watermark, EasyNegative 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:12, 1.51it/s] 10%|█ | 2/20 [00:01<00:12, 1.48it/s] 15%|█▌ | 3/20 [00:02<00:11, 1.49it/s] 20%|██ | 4/20 [00:02<00:10, 1.49it/s] 25%|██▌ | 5/20 [00:03<00:10, 1.48it/s] 30%|███ | 6/20 [00:04<00:09, 1.48it/s] 35%|███▌ | 7/20 [00:04<00:08, 1.48it/s] 40%|████ | 8/20 [00:05<00:08, 1.48it/s] 45%|████▌ | 9/20 [00:06<00:07, 1.48it/s] 50%|█████ | 10/20 [00:06<00:06, 1.48it/s] 55%|█████▌ | 11/20 [00:07<00:06, 1.48it/s] 60%|██████ | 12/20 [00:08<00:05, 1.48it/s] 65%|██████▌ | 13/20 [00:08<00:04, 1.48it/s] 70%|███████ | 14/20 [00:09<00:04, 1.48it/s] 75%|███████▌ | 15/20 [00:10<00:03, 1.48it/s] 80%|████████ | 16/20 [00:10<00:02, 1.49it/s] 85%|████████▌ | 17/20 [00:11<00:02, 1.48it/s] 90%|█████████ | 18/20 [00:12<00:01, 1.48it/s] 95%|█████████▌| 19/20 [00:12<00:00, 1.48it/s] 100%|██████████| 20/20 [00:13<00:00, 1.48it/s] 100%|██████████| 20/20 [00:13<00:00, 1.48it/s] Decoding latents in cuda:0... done in 0.98s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.7ms Speed: 3.2ms preprocess, 7.7ms inference, 31.8ms 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/dd3b0c8e2e03456b9c98756212e714cd/00000-3520698549.webp
https://files.tungsten.run/uploads/2faa798162474faeb02677211f0f3b21/00001-3520698550.webp
https://files.tungsten.run/uploads/6381d34989d441bb80b9de1e38b03f35/00002-3520698551.webp
https://files.tungsten.run/uploads/78e6b3d7352543c38d8f3a470388ce13/00003-3520698552.webp
This example was created by evevalentine2017
Finished in 52.4 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/kl-f8-anime2_fp16.safetensors Full prompt: (masterpiece, best quality), 1girl, blonde messy hair, choker, big smile, pajamas, see-through, glasses Full negative prompt: 3 legs, (worst quality, low quality:1.4), watermark, EasyNegative 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:12, 1.51it/s] 10%|█ | 2/20 [00:01<00:12, 1.48it/s] 15%|█▌ | 3/20 [00:02<00:11, 1.49it/s] 20%|██ | 4/20 [00:02<00:10, 1.49it/s] 25%|██▌ | 5/20 [00:03<00:10, 1.48it/s] 30%|███ | 6/20 [00:04<00:09, 1.48it/s] 35%|███▌ | 7/20 [00:04<00:08, 1.48it/s] 40%|████ | 8/20 [00:05<00:08, 1.48it/s] 45%|████▌ | 9/20 [00:06<00:07, 1.48it/s] 50%|█████ | 10/20 [00:06<00:06, 1.48it/s] 55%|█████▌ | 11/20 [00:07<00:06, 1.48it/s] 60%|██████ | 12/20 [00:08<00:05, 1.48it/s] 65%|██████▌ | 13/20 [00:08<00:04, 1.48it/s] 70%|███████ | 14/20 [00:09<00:04, 1.48it/s] 75%|███████▌ | 15/20 [00:10<00:03, 1.48it/s] 80%|████████ | 16/20 [00:10<00:02, 1.49it/s] 85%|████████▌ | 17/20 [00:11<00:02, 1.48it/s] 90%|█████████ | 18/20 [00:12<00:01, 1.48it/s] 95%|█████████▌| 19/20 [00:12<00:00, 1.48it/s] 100%|██████████| 20/20 [00:13<00:00, 1.48it/s] 100%|██████████| 20/20 [00:13<00:00, 1.48it/s] Decoding latents in cuda:0... done in 0.98s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.7ms Speed: 3.2ms preprocess, 7.7ms inference, 31.8ms postprocess per image at shape (1, 3, 640, 640)