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/dc34bce5ed75413b8ef781dce4e7f351/00000-985763229.webp
https://files.tungsten.run/uploads/fd9a20e63bac4740ac210433b2bc1cf9/00001-985763230.webp
https://files.tungsten.run/uploads/090a3dc1a1c04fe79fed031d3938f269/00002-985763231.webp
https://files.tungsten.run/uploads/274d1427a0744ba3b1d9bfe18263eed9/00003-985763232.webp
This example was created by evevalentine2017
Finished in 125.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: sculpture of girl, full body, (clay), concept art Full negative prompt: nudity, nipples, nsfw, logo, text, ng_deepnegative_v1_75t, rev2-badprompt, verybadimagenegative_v1.3, mutated hands and fingers, poorly drawn face, extra limb, missing limb, disconnected limbs, malformed hands, ugly, 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:01<00:24, 1.28s/it] 10%|█ | 2/20 [00:03<00:29, 1.61s/it] 15%|█▌ | 3/20 [00:04<00:28, 1.70s/it] 20%|██ | 4/20 [00:06<00:28, 1.77s/it] 25%|██▌ | 5/20 [00:08<00:26, 1.77s/it] 30%|███ | 6/20 [00:10<00:25, 1.79s/it] 35%|███▌ | 7/20 [00:12<00:23, 1.78s/it] 40%|████ | 8/20 [00:13<00:20, 1.73s/it] 45%|████▌ | 9/20 [00:15<00:19, 1.73s/it] 50%|█████ | 10/20 [00:17<00:17, 1.77s/it] 55%|█████▌ | 11/20 [00:19<00:15, 1.73s/it] 60%|██████ | 12/20 [00:20<00:13, 1.69s/it] 65%|██████▌ | 13/20 [00:22<00:11, 1.70s/it] 70%|███████ | 14/20 [00:23<00:09, 1.67s/it] 75%|███████▌ | 15/20 [00:25<00:08, 1.66s/it] 80%|████████ | 16/20 [00:27<00:06, 1.61s/it] 85%|████████▌ | 17/20 [00:28<00:04, 1.59s/it] 90%|█████████ | 18/20 [00:30<00:03, 1.57s/it] 95%|█████████▌| 19/20 [00:31<00:01, 1.38s/it] 100%|██████████| 20/20 [00:31<00:00, 1.16s/it] 100%|██████████| 20/20 [00:31<00:00, 1.59s/it] Decoding latents in cuda:0... done in 0.95s Move latents to cpu... done in 0.01s 0: 640x640 2 faces, 6.0ms Speed: 2.2ms preprocess, 6.0ms inference, 30.6ms 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/dc34bce5ed75413b8ef781dce4e7f351/00000-985763229.webp
https://files.tungsten.run/uploads/fd9a20e63bac4740ac210433b2bc1cf9/00001-985763230.webp
https://files.tungsten.run/uploads/090a3dc1a1c04fe79fed031d3938f269/00002-985763231.webp
https://files.tungsten.run/uploads/274d1427a0744ba3b1d9bfe18263eed9/00003-985763232.webp
This example was created by evevalentine2017
Finished in 125.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: sculpture of girl, full body, (clay), concept art Full negative prompt: nudity, nipples, nsfw, logo, text, ng_deepnegative_v1_75t, rev2-badprompt, verybadimagenegative_v1.3, mutated hands and fingers, poorly drawn face, extra limb, missing limb, disconnected limbs, malformed hands, ugly, 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:01<00:24, 1.28s/it] 10%|█ | 2/20 [00:03<00:29, 1.61s/it] 15%|█▌ | 3/20 [00:04<00:28, 1.70s/it] 20%|██ | 4/20 [00:06<00:28, 1.77s/it] 25%|██▌ | 5/20 [00:08<00:26, 1.77s/it] 30%|███ | 6/20 [00:10<00:25, 1.79s/it] 35%|███▌ | 7/20 [00:12<00:23, 1.78s/it] 40%|████ | 8/20 [00:13<00:20, 1.73s/it] 45%|████▌ | 9/20 [00:15<00:19, 1.73s/it] 50%|█████ | 10/20 [00:17<00:17, 1.77s/it] 55%|█████▌ | 11/20 [00:19<00:15, 1.73s/it] 60%|██████ | 12/20 [00:20<00:13, 1.69s/it] 65%|██████▌ | 13/20 [00:22<00:11, 1.70s/it] 70%|███████ | 14/20 [00:23<00:09, 1.67s/it] 75%|███████▌ | 15/20 [00:25<00:08, 1.66s/it] 80%|████████ | 16/20 [00:27<00:06, 1.61s/it] 85%|████████▌ | 17/20 [00:28<00:04, 1.59s/it] 90%|█████████ | 18/20 [00:30<00:03, 1.57s/it] 95%|█████████▌| 19/20 [00:31<00:01, 1.38s/it] 100%|██████████| 20/20 [00:31<00:00, 1.16s/it] 100%|██████████| 20/20 [00:31<00:00, 1.59s/it] Decoding latents in cuda:0... done in 0.95s Move latents to cpu... done in 0.01s 0: 640x640 2 faces, 6.0ms Speed: 2.2ms preprocess, 6.0ms inference, 30.6ms postprocess per image at shape (1, 3, 640, 640)