Version: v3.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
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
num_outputs
Number of output images
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
width
Output image width
height
Output image height
reference_image
Image that the output should be similar to
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/3f4c502404d541d0b69740857eecbde3/00000-3129443255.png
https://files.tungsten.run/uploads/b19b7be30a4c4e7da44b6da01fbc0881/00001-3129443256.png
This example was created by wwwbookafficionado
Finished in 46.3 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/vae-ft-mse-840000-ema-pruned_fp16.safetensors Full prompt: extra extra extra plus-size busty blonde woman, sitting in a bright white french style restaurant, ash blue dress, large protrusive inappropriate cleavage. Restaurant has huge floor to ceiling windows and you can see through them, windows take up the entire wall, through the window you can see extravagant french gardens,, Realistic, (masterpiece:1.5), (top quality:1.5), (real life photo:1.5), (ultra detailed:1.5), <lora:add_detail:1.0> Full negative prompt: large breasts, big breasts, (deformed iris, deformed pupils, semi-realistic, cgi, 3d, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, BadDream, badhandv4, easynegative, clone, clones, watermark, oversaturated, low quality, pixelated, morphing, morph, morphed, big tits, huge tits, monochrome, asian, (EasyNegative:1.2),(worst quality:2),(low quality:2),(normal quality:1.6),(ng_deepnegative_v1_75t),monochrome,(watermark:1.4),artist name,(character name:1.2),text,bad anatomy,sketch,duplicate,(negative_hand-neg:1.2),bad_pictures,FastNegativeV2, 0%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:00<00:32, 1.13it/s] 5%|▌ | 2/38 [00:01<00:25, 1.40it/s] 8%|▊ | 3/38 [00:02<00:22, 1.53it/s] 11%|█ | 4/38 [00:02<00:21, 1.61it/s] 13%|█▎ | 5/38 [00:03<00:20, 1.63it/s] 16%|█▌ | 6/38 [00:03<00:19, 1.64it/s] 18%|█▊ | 7/38 [00:04<00:18, 1.63it/s] 21%|██ | 8/38 [00:05<00:18, 1.66it/s] 24%|██▎ | 9/38 [00:05<00:17, 1.68it/s] 26%|██▋ | 10/38 [00:06<00:16, 1.72it/s] 29%|██▉ | 11/38 [00:06<00:15, 1.71it/s] 32%|███▏ | 12/38 [00:07<00:15, 1.72it/s] 34%|███▍ | 13/38 [00:07<00:14, 1.73it/s] 37%|███▋ | 14/38 [00:08<00:13, 1.77it/s] 39%|███▉ | 15/38 [00:09<00:13, 1.75it/s] 42%|████▏ | 16/38 [00:09<00:12, 1.77it/s] 45%|████▍ | 17/38 [00:10<00:12, 1.73it/s] 47%|████▋ | 18/38 [00:10<00:11, 1.77it/s] 50%|█████ | 19/38 [00:11<00:10, 1.80it/s] 53%|█████▎ | 20/38 [00:11<00:10, 1.79it/s] 55%|█████▌ | 21/38 [00:12<00:09, 1.79it/s] 58%|█████▊ | 22/38 [00:12<00:09, 1.77it/s] 61%|██████ | 23/38 [00:13<00:08, 1.85it/s] 63%|██████▎ | 24/38 [00:14<00:07, 1.81it/s] 66%|██████▌ | 25/38 [00:14<00:07, 1.86it/s] 68%|██████▊ | 26/38 [00:15<00:06, 1.88it/s] 71%|███████ | 27/38 [00:15<00:05, 1.84it/s] 74%|███████▎ | 28/38 [00:16<00:05, 1.83it/s] 76%|███████▋ | 29/38 [00:16<00:04, 1.85it/s] 79%|███████▉ | 30/38 [00:17<00:04, 1.88it/s] 82%|████████▏ | 31/38 [00:17<00:03, 1.88it/s] 84%|████████▍ | 32/38 [00:18<00:03, 1.86it/s] 87%|████████▋ | 33/38 [00:18<00:02, 1.84it/s] 89%|████████▉ | 34/38 [00:19<00:02, 1.81it/s] 92%|█████████▏| 35/38 [00:19<00:01, 1.84it/s] 95%|█████████▍| 36/38 [00:20<00:01, 1.80it/s] 97%|█████████▋| 37/38 [00:20<00:00, 2.03it/s] 100%|██████████| 38/38 [00:21<00:00, 2.49it/s] 100%|██████████| 38/38 [00:21<00:00, 1.81it/s] Decoding latents in cuda:0... done in 0.31s Move latents to cpu... done in 0.01s 0: 640x448 1 face, 164.9ms Speed: 2.0ms preprocess, 164.9ms inference, 23.1ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/21 [00:00<?, ?it/s] 5%|▍ | 1/21 [00:00<00:11, 1.78it/s] 10%|▉ | 2/21 [00:00<00:08, 2.28it/s] 14%|█▍ | 3/21 [00:01<00:07, 2.48it/s] 19%|█▉ | 4/21 [00:01<00:06, 2.59it/s] 24%|██▍ | 5/21 [00:02<00:06, 2.63it/s] 29%|██▊ | 6/21 [00:02<00:05, 2.78it/s] 33%|███▎ | 7/21 [00:02<00:05, 2.77it/s] 38%|███▊ | 8/21 [00:03<00:04, 2.85it/s] 43%|████▎ | 9/21 [00:03<00:04, 2.87it/s] 48%|████▊ | 10/21 [00:03<00:03, 2.82it/s] 52%|█████▏ | 11/21 [00:04<00:03, 2.83it/s] 57%|█████▋ | 12/21 [00:04<00:03, 2.84it/s] 62%|██████▏ | 13/21 [00:04<00:02, 2.89it/s] 67%|██████▋ | 14/21 [00:05<00:02, 2.90it/s] 71%|███████▏ | 15/21 [00:05<00:02, 2.85it/s] 76%|███████▌ | 16/21 [00:05<00:01, 2.82it/s] 81%|████████ | 17/21 [00:06<00:01, 2.76it/s] 86%|████████▌ | 18/21 [00:06<00:01, 2.79it/s] 90%|█████████ | 19/21 [00:06<00:00, 2.64it/s] 95%|█████████▌| 20/21 [00:07<00:00, 2.93it/s] 100%|██████████| 21/21 [00:07<00:00, 3.38it/s] 100%|██████████| 21/21 [00:07<00:00, 2.83it/s] Decoding latents in cuda:0... done in 0.15s Move latents to cpu... done in 0.0s 0: 640x448 1 face, 7.6ms Speed: 1.9ms preprocess, 7.6ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/21 [00:00<?, ?it/s] 5%|▍ | 1/21 [00:00<00:07, 2.77it/s] 10%|▉ | 2/21 [00:00<00:06, 2.82it/s] 14%|█▍ | 3/21 [00:01<00:06, 2.78it/s] 19%|█▉ | 4/21 [00:01<00:06, 2.66it/s] 24%|██▍ | 5/21 [00:01<00:06, 2.64it/s] 29%|██▊ | 6/21 [00:02<00:05, 2.74it/s] 33%|███▎ | 7/21 [00:02<00:05, 2.73it/s] 38%|███▊ | 8/21 [00:02<00:04, 2.78it/s] 43%|████▎ | 9/21 [00:03<00:04, 2.78it/s] 48%|████▊ | 10/21 [00:03<00:04, 2.69it/s] 52%|█████▏ | 11/21 [00:04<00:03, 2.67it/s] 57%|█████▋ | 12/21 [00:04<00:03, 2.69it/s] 62%|██████▏ | 13/21 [00:04<00:02, 2.72it/s] 67%|██████▋ | 14/21 [00:05<00:02, 2.73it/s] 71%|███████▏ | 15/21 [00:05<00:02, 2.74it/s] 76%|███████▌ | 16/21 [00:05<00:01, 2.73it/s] 81%|████████ | 17/21 [00:06<00:01, 2.69it/s] 86%|████████▌ | 18/21 [00:06<00:01, 2.75it/s] 90%|█████████ | 19/21 [00:06<00:00, 2.73it/s] 95%|█████████▌| 20/21 [00:07<00:00, 2.99it/s] 100%|██████████| 21/21 [00:07<00:00, 3.45it/s] 100%|██████████| 21/21 [00:07<00:00, 2.83it/s] Decoding latents in cuda:0... done in 0.14s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
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
num_outputs
Number of output images
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
width
Output image width
height
Output image height
reference_image
Image that the output should be similar to
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/3f4c502404d541d0b69740857eecbde3/00000-3129443255.png
https://files.tungsten.run/uploads/b19b7be30a4c4e7da44b6da01fbc0881/00001-3129443256.png
This example was created by wwwbookafficionado
Finished in 46.3 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/vae-ft-mse-840000-ema-pruned_fp16.safetensors Full prompt: extra extra extra plus-size busty blonde woman, sitting in a bright white french style restaurant, ash blue dress, large protrusive inappropriate cleavage. Restaurant has huge floor to ceiling windows and you can see through them, windows take up the entire wall, through the window you can see extravagant french gardens,, Realistic, (masterpiece:1.5), (top quality:1.5), (real life photo:1.5), (ultra detailed:1.5), <lora:add_detail:1.0> Full negative prompt: large breasts, big breasts, (deformed iris, deformed pupils, semi-realistic, cgi, 3d, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, BadDream, badhandv4, easynegative, clone, clones, watermark, oversaturated, low quality, pixelated, morphing, morph, morphed, big tits, huge tits, monochrome, asian, (EasyNegative:1.2),(worst quality:2),(low quality:2),(normal quality:1.6),(ng_deepnegative_v1_75t),monochrome,(watermark:1.4),artist name,(character name:1.2),text,bad anatomy,sketch,duplicate,(negative_hand-neg:1.2),bad_pictures,FastNegativeV2, 0%| | 0/38 [00:00<?, ?it/s] 3%|▎ | 1/38 [00:00<00:32, 1.13it/s] 5%|▌ | 2/38 [00:01<00:25, 1.40it/s] 8%|▊ | 3/38 [00:02<00:22, 1.53it/s] 11%|█ | 4/38 [00:02<00:21, 1.61it/s] 13%|█▎ | 5/38 [00:03<00:20, 1.63it/s] 16%|█▌ | 6/38 [00:03<00:19, 1.64it/s] 18%|█▊ | 7/38 [00:04<00:18, 1.63it/s] 21%|██ | 8/38 [00:05<00:18, 1.66it/s] 24%|██▎ | 9/38 [00:05<00:17, 1.68it/s] 26%|██▋ | 10/38 [00:06<00:16, 1.72it/s] 29%|██▉ | 11/38 [00:06<00:15, 1.71it/s] 32%|███▏ | 12/38 [00:07<00:15, 1.72it/s] 34%|███▍ | 13/38 [00:07<00:14, 1.73it/s] 37%|███▋ | 14/38 [00:08<00:13, 1.77it/s] 39%|███▉ | 15/38 [00:09<00:13, 1.75it/s] 42%|████▏ | 16/38 [00:09<00:12, 1.77it/s] 45%|████▍ | 17/38 [00:10<00:12, 1.73it/s] 47%|████▋ | 18/38 [00:10<00:11, 1.77it/s] 50%|█████ | 19/38 [00:11<00:10, 1.80it/s] 53%|█████▎ | 20/38 [00:11<00:10, 1.79it/s] 55%|█████▌ | 21/38 [00:12<00:09, 1.79it/s] 58%|█████▊ | 22/38 [00:12<00:09, 1.77it/s] 61%|██████ | 23/38 [00:13<00:08, 1.85it/s] 63%|██████▎ | 24/38 [00:14<00:07, 1.81it/s] 66%|██████▌ | 25/38 [00:14<00:07, 1.86it/s] 68%|██████▊ | 26/38 [00:15<00:06, 1.88it/s] 71%|███████ | 27/38 [00:15<00:05, 1.84it/s] 74%|███████▎ | 28/38 [00:16<00:05, 1.83it/s] 76%|███████▋ | 29/38 [00:16<00:04, 1.85it/s] 79%|███████▉ | 30/38 [00:17<00:04, 1.88it/s] 82%|████████▏ | 31/38 [00:17<00:03, 1.88it/s] 84%|████████▍ | 32/38 [00:18<00:03, 1.86it/s] 87%|████████▋ | 33/38 [00:18<00:02, 1.84it/s] 89%|████████▉ | 34/38 [00:19<00:02, 1.81it/s] 92%|█████████▏| 35/38 [00:19<00:01, 1.84it/s] 95%|█████████▍| 36/38 [00:20<00:01, 1.80it/s] 97%|█████████▋| 37/38 [00:20<00:00, 2.03it/s] 100%|██████████| 38/38 [00:21<00:00, 2.49it/s] 100%|██████████| 38/38 [00:21<00:00, 1.81it/s] Decoding latents in cuda:0... done in 0.31s Move latents to cpu... done in 0.01s 0: 640x448 1 face, 164.9ms Speed: 2.0ms preprocess, 164.9ms inference, 23.1ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/21 [00:00<?, ?it/s] 5%|▍ | 1/21 [00:00<00:11, 1.78it/s] 10%|▉ | 2/21 [00:00<00:08, 2.28it/s] 14%|█▍ | 3/21 [00:01<00:07, 2.48it/s] 19%|█▉ | 4/21 [00:01<00:06, 2.59it/s] 24%|██▍ | 5/21 [00:02<00:06, 2.63it/s] 29%|██▊ | 6/21 [00:02<00:05, 2.78it/s] 33%|███▎ | 7/21 [00:02<00:05, 2.77it/s] 38%|███▊ | 8/21 [00:03<00:04, 2.85it/s] 43%|████▎ | 9/21 [00:03<00:04, 2.87it/s] 48%|████▊ | 10/21 [00:03<00:03, 2.82it/s] 52%|█████▏ | 11/21 [00:04<00:03, 2.83it/s] 57%|█████▋ | 12/21 [00:04<00:03, 2.84it/s] 62%|██████▏ | 13/21 [00:04<00:02, 2.89it/s] 67%|██████▋ | 14/21 [00:05<00:02, 2.90it/s] 71%|███████▏ | 15/21 [00:05<00:02, 2.85it/s] 76%|███████▌ | 16/21 [00:05<00:01, 2.82it/s] 81%|████████ | 17/21 [00:06<00:01, 2.76it/s] 86%|████████▌ | 18/21 [00:06<00:01, 2.79it/s] 90%|█████████ | 19/21 [00:06<00:00, 2.64it/s] 95%|█████████▌| 20/21 [00:07<00:00, 2.93it/s] 100%|██████████| 21/21 [00:07<00:00, 3.38it/s] 100%|██████████| 21/21 [00:07<00:00, 2.83it/s] Decoding latents in cuda:0... done in 0.15s Move latents to cpu... done in 0.0s 0: 640x448 1 face, 7.6ms Speed: 1.9ms preprocess, 7.6ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/21 [00:00<?, ?it/s] 5%|▍ | 1/21 [00:00<00:07, 2.77it/s] 10%|▉ | 2/21 [00:00<00:06, 2.82it/s] 14%|█▍ | 3/21 [00:01<00:06, 2.78it/s] 19%|█▉ | 4/21 [00:01<00:06, 2.66it/s] 24%|██▍ | 5/21 [00:01<00:06, 2.64it/s] 29%|██▊ | 6/21 [00:02<00:05, 2.74it/s] 33%|███▎ | 7/21 [00:02<00:05, 2.73it/s] 38%|███▊ | 8/21 [00:02<00:04, 2.78it/s] 43%|████▎ | 9/21 [00:03<00:04, 2.78it/s] 48%|████▊ | 10/21 [00:03<00:04, 2.69it/s] 52%|█████▏ | 11/21 [00:04<00:03, 2.67it/s] 57%|█████▋ | 12/21 [00:04<00:03, 2.69it/s] 62%|██████▏ | 13/21 [00:04<00:02, 2.72it/s] 67%|██████▋ | 14/21 [00:05<00:02, 2.73it/s] 71%|███████▏ | 15/21 [00:05<00:02, 2.74it/s] 76%|███████▌ | 16/21 [00:05<00:01, 2.73it/s] 81%|████████ | 17/21 [00:06<00:01, 2.69it/s] 86%|████████▌ | 18/21 [00:06<00:01, 2.75it/s] 90%|█████████ | 19/21 [00:06<00:00, 2.73it/s] 95%|█████████▌| 20/21 [00:07<00:00, 2.99it/s] 100%|██████████| 21/21 [00:07<00:00, 3.45it/s] 100%|██████████| 21/21 [00:07<00:00, 2.83it/s] Decoding latents in cuda:0... done in 0.14s Move latents to cpu... done in 0.0s Uploading outputs... Finished.