tungsten-logo
Sign In
Pony photo real merge x3
Pony photo real merge x3

Pony photo real merge x3

42 stars
Version: v1.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
PonyDetail_V20
Pony Detail V20
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/d48c0731de1f433896ea6b695845b07c/output-b89d1c4fa37d4469b27f695f90a582f1-00000-1536911961.webp
https://files.tungsten.run/uploads/fff1c874ae34473e823281663fed733a/output-5a97f5db6857423dbaff8cda0afb949f-00001-1536911962.webp
https://files.tungsten.run/uploads/eb93102930a94419923d4361b77f08dd/output-bce80c68626f40f088f769ff1abc2fd7-00002-1536911963.webp
This example was created by sparks
Finished in 91.0 seconds
Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_photo, source_real, 1girl, big breasts, upper body, black long hair, looking at the viewer, Long sleeve sweater, front lighting, living room,, <lora:Pony_DetailV2.0:1.0> Full negative prompt: 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:03<01:41, 3.37s/it] 6%|▋ | 2/31 [00:04<01:07, 2.32s/it] 10%|▉ | 3/31 [00:06<00:55, 1.98s/it] 13%|█▎ | 4/31 [00:08<00:49, 1.83s/it] 16%|█▌ | 5/31 [00:09<00:45, 1.74s/it] 19%|█▉ | 6/31 [00:11<00:42, 1.69s/it] 23%|██▎ | 7/31 [00:12<00:39, 1.66s/it] 26%|██▌ | 8/31 [00:14<00:37, 1.64s/it] 29%|██▉ | 9/31 [00:16<00:35, 1.63s/it] 32%|███▏ | 10/31 [00:17<00:34, 1.62s/it] 35%|███▌ | 11/31 [00:19<00:32, 1.62s/it] 39%|███▊ | 12/31 [00:20<00:30, 1.62s/it] 42%|████▏ | 13/31 [00:22<00:29, 1.62s/it] 45%|████▌ | 14/31 [00:24<00:27, 1.62s/it] 48%|████▊ | 15/31 [00:25<00:25, 1.62s/it] 52%|█████▏ | 16/31 [00:27<00:24, 1.62s/it] 55%|█████▍ | 17/31 [00:29<00:22, 1.62s/it] 58%|█████▊ | 18/31 [00:30<00:21, 1.63s/it] 61%|██████▏ | 19/31 [00:32<00:19, 1.63s/it] 65%|██████▍ | 20/31 [00:33<00:17, 1.63s/it] 68%|██████▊ | 21/31 [00:35<00:16, 1.64s/it] 71%|███████ | 22/31 [00:37<00:14, 1.64s/it] 74%|███████▍ | 23/31 [00:38<00:13, 1.64s/it] 77%|███████▋ | 24/31 [00:40<00:11, 1.64s/it] 81%|████████ | 25/31 [00:42<00:09, 1.65s/it] 84%|████████▍ | 26/31 [00:43<00:08, 1.65s/it] 87%|████████▋ | 27/31 [00:45<00:06, 1.65s/it] 90%|█████████ | 28/31 [00:47<00:04, 1.65s/it] 94%|█████████▎| 29/31 [00:48<00:03, 1.65s/it] 97%|█████████▋| 30/31 [00:50<00:01, 1.66s/it] 100%|██████████| 31/31 [00:52<00:00, 1.65s/it] 100%|██████████| 31/31 [00:52<00:00, 1.68s/it] Decoding latents in cuda:0... done in 2.93s Move latents to cpu... done in 0.03s 0: 640x480 1 face, 159.9ms Speed: 2.6ms preprocess, 159.9ms inference, 31.1ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.01it/s] 15%|█▌ | 2/13 [00:00<00:05, 2.04it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.04it/s] 31%|███ | 4/13 [00:01<00:04, 2.04it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.03it/s] 46%|████▌ | 6/13 [00:02<00:03, 2.04it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.03it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.04it/s] 69%|██████▉ | 9/13 [00:04<00:01, 2.03it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.04it/s] 85%|████████▍ | 11/13 [00:05<00:00, 2.02it/s] 92%|█████████▏| 12/13 [00:05<00:00, 2.03it/s] 100%|██████████| 13/13 [00:06<00:00, 2.04it/s] 100%|██████████| 13/13 [00:06<00:00, 2.03it/s] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.1ms Speed: 1.9ms preprocess, 8.1ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.13it/s] 15%|█▌ | 2/13 [00:00<00:05, 2.09it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.04it/s] 31%|███ | 4/13 [00:01<00:04, 2.05it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.03it/s] 46%|████▌ | 6/13 [00:02<00:03, 2.04it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.03it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.03it/s] 69%|██████▉ | 9/13 [00:04<00:01, 2.02it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.03it/s] 85%|████████▍ | 11/13 [00:05<00:00, 2.03it/s] 92%|█████████▏| 12/13 [00:05<00:00, 2.02it/s] 100%|██████████| 13/13 [00:06<00:00, 2.03it/s] 100%|██████████| 13/13 [00:06<00:00, 2.04it/s] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.6ms Speed: 2.2ms preprocess, 8.6ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.12it/s] 15%|█▌ | 2/13 [00:00<00:05, 2.08it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.03it/s] 31%|███ | 4/13 [00:01<00:04, 2.04it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.02it/s] 46%|████▌ | 6/13 [00:02<00:03, 2.03it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.01it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.02it/s] 69%|██████▉ | 9/13 [00:04<00:01, 2.01it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.02it/s] 85%|████████▍ | 11/13 [00:05<00:00, 2.01it/s] 92%|█████████▏| 12/13 [00:05<00:00, 2.02it/s] 100%|██████████| 13/13 [00:06<00:00, 2.03it/s] 100%|██████████| 13/13 [00:06<00:00, 2.03it/s] Decoding latents in cuda:0... done in 0.97s 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
PonyDetail_V20
Pony Detail V20
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/d48c0731de1f433896ea6b695845b07c/output-b89d1c4fa37d4469b27f695f90a582f1-00000-1536911961.webp
https://files.tungsten.run/uploads/fff1c874ae34473e823281663fed733a/output-5a97f5db6857423dbaff8cda0afb949f-00001-1536911962.webp
https://files.tungsten.run/uploads/eb93102930a94419923d4361b77f08dd/output-bce80c68626f40f088f769ff1abc2fd7-00002-1536911963.webp
This example was created by sparks
Finished in 91.0 seconds
Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_photo, source_real, 1girl, big breasts, upper body, black long hair, looking at the viewer, Long sleeve sweater, front lighting, living room,, <lora:Pony_DetailV2.0:1.0> Full negative prompt: 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:03<01:41, 3.37s/it] 6%|▋ | 2/31 [00:04<01:07, 2.32s/it] 10%|▉ | 3/31 [00:06<00:55, 1.98s/it] 13%|█▎ | 4/31 [00:08<00:49, 1.83s/it] 16%|█▌ | 5/31 [00:09<00:45, 1.74s/it] 19%|█▉ | 6/31 [00:11<00:42, 1.69s/it] 23%|██▎ | 7/31 [00:12<00:39, 1.66s/it] 26%|██▌ | 8/31 [00:14<00:37, 1.64s/it] 29%|██▉ | 9/31 [00:16<00:35, 1.63s/it] 32%|███▏ | 10/31 [00:17<00:34, 1.62s/it] 35%|███▌ | 11/31 [00:19<00:32, 1.62s/it] 39%|███▊ | 12/31 [00:20<00:30, 1.62s/it] 42%|████▏ | 13/31 [00:22<00:29, 1.62s/it] 45%|████▌ | 14/31 [00:24<00:27, 1.62s/it] 48%|████▊ | 15/31 [00:25<00:25, 1.62s/it] 52%|█████▏ | 16/31 [00:27<00:24, 1.62s/it] 55%|█████▍ | 17/31 [00:29<00:22, 1.62s/it] 58%|█████▊ | 18/31 [00:30<00:21, 1.63s/it] 61%|██████▏ | 19/31 [00:32<00:19, 1.63s/it] 65%|██████▍ | 20/31 [00:33<00:17, 1.63s/it] 68%|██████▊ | 21/31 [00:35<00:16, 1.64s/it] 71%|███████ | 22/31 [00:37<00:14, 1.64s/it] 74%|███████▍ | 23/31 [00:38<00:13, 1.64s/it] 77%|███████▋ | 24/31 [00:40<00:11, 1.64s/it] 81%|████████ | 25/31 [00:42<00:09, 1.65s/it] 84%|████████▍ | 26/31 [00:43<00:08, 1.65s/it] 87%|████████▋ | 27/31 [00:45<00:06, 1.65s/it] 90%|█████████ | 28/31 [00:47<00:04, 1.65s/it] 94%|█████████▎| 29/31 [00:48<00:03, 1.65s/it] 97%|█████████▋| 30/31 [00:50<00:01, 1.66s/it] 100%|██████████| 31/31 [00:52<00:00, 1.65s/it] 100%|██████████| 31/31 [00:52<00:00, 1.68s/it] Decoding latents in cuda:0... done in 2.93s Move latents to cpu... done in 0.03s 0: 640x480 1 face, 159.9ms Speed: 2.6ms preprocess, 159.9ms inference, 31.1ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.01it/s] 15%|█▌ | 2/13 [00:00<00:05, 2.04it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.04it/s] 31%|███ | 4/13 [00:01<00:04, 2.04it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.03it/s] 46%|████▌ | 6/13 [00:02<00:03, 2.04it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.03it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.04it/s] 69%|██████▉ | 9/13 [00:04<00:01, 2.03it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.04it/s] 85%|████████▍ | 11/13 [00:05<00:00, 2.02it/s] 92%|█████████▏| 12/13 [00:05<00:00, 2.03it/s] 100%|██████████| 13/13 [00:06<00:00, 2.04it/s] 100%|██████████| 13/13 [00:06<00:00, 2.03it/s] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.1ms Speed: 1.9ms preprocess, 8.1ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.13it/s] 15%|█▌ | 2/13 [00:00<00:05, 2.09it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.04it/s] 31%|███ | 4/13 [00:01<00:04, 2.05it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.03it/s] 46%|████▌ | 6/13 [00:02<00:03, 2.04it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.03it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.03it/s] 69%|██████▉ | 9/13 [00:04<00:01, 2.02it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.03it/s] 85%|████████▍ | 11/13 [00:05<00:00, 2.03it/s] 92%|█████████▏| 12/13 [00:05<00:00, 2.02it/s] 100%|██████████| 13/13 [00:06<00:00, 2.03it/s] 100%|██████████| 13/13 [00:06<00:00, 2.04it/s] Decoding latents in cuda:0... done in 0.96s Move latents to cpu... done in 0.0s 0: 640x480 1 face, 8.6ms Speed: 2.2ms preprocess, 8.6ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:05, 2.12it/s] 15%|█▌ | 2/13 [00:00<00:05, 2.08it/s] 23%|██▎ | 3/13 [00:01<00:04, 2.03it/s] 31%|███ | 4/13 [00:01<00:04, 2.04it/s] 38%|███▊ | 5/13 [00:02<00:03, 2.02it/s] 46%|████▌ | 6/13 [00:02<00:03, 2.03it/s] 54%|█████▍ | 7/13 [00:03<00:02, 2.01it/s] 62%|██████▏ | 8/13 [00:03<00:02, 2.02it/s] 69%|██████▉ | 9/13 [00:04<00:01, 2.01it/s] 77%|███████▋ | 10/13 [00:04<00:01, 2.02it/s] 85%|████████▍ | 11/13 [00:05<00:00, 2.01it/s] 92%|█████████▏| 12/13 [00:05<00:00, 2.02it/s] 100%|██████████| 13/13 [00:06<00:00, 2.03it/s] 100%|██████████| 13/13 [00:06<00:00, 2.03it/s] Decoding latents in cuda:0... done in 0.97s Move latents to cpu... done in 0.0s Uploading files.. Finished.