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/589b006c6aa9404da1190caa2cb9d4d0/output-fbf5aa5bf27a494d86bfc6c584da310f-00000-1335517905.webp
https://files.tungsten.run/uploads/4d4d5d09efbe4cc2ad408fc633e153ca/output-67d4439d955146d2b544f19daf95eb04-00001-1335517906.webp
https://files.tungsten.run/uploads/34345fe23e1b4313a8f7cad8726cf7b1/output-026279c063614e6b9f5f4e4f129477b9-00002-1335517907.webp
This example was created by sparks
Finished in 85.0 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, solo, hime cut hair, looking at viewer, black hair, green eyes, bare shoulders, upper body, off shoulder, blurry, sweater, red lips, watermark, web address, realistic, <lora:Pony_DetailV2.0:1.0> Full negative prompt: 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:02<01:13, 2.47s/it] 6%|▋ | 2/31 [00:03<00:49, 1.72s/it] 10%|▉ | 3/31 [00:04<00:41, 1.47s/it] 13%|█▎ | 4/31 [00:06<00:36, 1.36s/it] 16%|█▌ | 5/31 [00:07<00:33, 1.30s/it] 19%|█▉ | 6/31 [00:08<00:31, 1.26s/it] 23%|██▎ | 7/31 [00:09<00:29, 1.24s/it] 26%|██▌ | 8/31 [00:10<00:28, 1.23s/it] 29%|██▉ | 9/31 [00:12<00:26, 1.22s/it] 32%|███▏ | 10/31 [00:13<00:25, 1.21s/it] 35%|███▌ | 11/31 [00:14<00:24, 1.21s/it] 39%|███▊ | 12/31 [00:15<00:23, 1.21s/it] 42%|████▏ | 13/31 [00:16<00:21, 1.21s/it] 45%|████▌ | 14/31 [00:18<00:20, 1.21s/it] 48%|████▊ | 15/31 [00:19<00:19, 1.20s/it] 52%|█████▏ | 16/31 [00:20<00:18, 1.21s/it] 55%|█████▍ | 17/31 [00:21<00:16, 1.20s/it] 58%|█████▊ | 18/31 [00:22<00:15, 1.20s/it] 61%|██████▏ | 19/31 [00:24<00:14, 1.20s/it] 65%|██████▍ | 20/31 [00:25<00:13, 1.20s/it] 68%|██████▊ | 21/31 [00:26<00:12, 1.20s/it] 71%|███████ | 22/31 [00:27<00:10, 1.21s/it] 74%|███████▍ | 23/31 [00:28<00:09, 1.21s/it] 77%|███████▋ | 24/31 [00:30<00:08, 1.21s/it] 81%|████████ | 25/31 [00:31<00:07, 1.21s/it] 84%|████████▍ | 26/31 [00:32<00:06, 1.21s/it] 87%|████████▋ | 27/31 [00:33<00:04, 1.21s/it] 90%|█████████ | 28/31 [00:34<00:03, 1.21s/it] 94%|█████████▎| 29/31 [00:36<00:02, 1.21s/it] 97%|█████████▋| 30/31 [00:37<00:01, 1.22s/it] 100%|██████████| 31/31 [00:38<00:00, 1.21s/it] 100%|██████████| 31/31 [00:38<00:00, 1.24s/it] Decoding latents in cuda:0... done in 2.34s Move latents to cpu... done in 0.03s 0: 640x448 1 face, 328.6ms Speed: 4.6ms preprocess, 328.6ms inference, 60.0ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:01<00:20, 1.73s/it] 15%|█▌ | 2/13 [00:03<00:17, 1.61s/it] 23%|██▎ | 3/13 [00:04<00:15, 1.54s/it] 31%|███ | 4/13 [00:05<00:10, 1.19s/it] 38%|███▊ | 5/13 [00:05<00:07, 1.02it/s] 46%|████▌ | 6/13 [00:07<00:07, 1.04s/it] 54%|█████▍ | 7/13 [00:07<00:05, 1.11it/s] 62%|██████▏ | 8/13 [00:08<00:04, 1.23it/s] 69%|██████▉ | 9/13 [00:08<00:03, 1.33it/s] 77%|███████▋ | 10/13 [00:09<00:02, 1.40it/s] 85%|████████▍ | 11/13 [00:10<00:01, 1.46it/s] 92%|█████████▏| 12/13 [00:10<00:00, 1.51it/s] 100%|██████████| 13/13 [00:11<00:00, 1.55it/s] 100%|██████████| 13/13 [00:11<00:00, 1.13it/s] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x448 1 face, 8.1ms Speed: 2.4ms preprocess, 8.1ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:07, 1.63it/s] 15%|█▌ | 2/13 [00:01<00:06, 1.60it/s] 23%|██▎ | 3/13 [00:01<00:06, 1.61it/s] 31%|███ | 4/13 [00:02<00:05, 1.62it/s] 38%|███▊ | 5/13 [00:03<00:04, 1.62it/s] 46%|████▌ | 6/13 [00:03<00:04, 1.58it/s] 54%|█████▍ | 7/13 [00:04<00:03, 1.59it/s] 62%|██████▏ | 8/13 [00:04<00:03, 1.60it/s] 69%|██████▉ | 9/13 [00:05<00:02, 1.62it/s] 77%|███████▋ | 10/13 [00:06<00:01, 1.58it/s] 85%|████████▍ | 11/13 [00:06<00:01, 1.57it/s] 92%|█████████▏| 12/13 [00:07<00:00, 1.59it/s] 100%|██████████| 13/13 [00:08<00:00, 1.59it/s] 100%|██████████| 13/13 [00:08<00:00, 1.60it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x448 1 face, 9.6ms Speed: 2.4ms preprocess, 9.6ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:07, 1.59it/s] 15%|█▌ | 2/13 [00:01<00:07, 1.52it/s] 23%|██▎ | 3/13 [00:01<00:06, 1.52it/s] 31%|███ | 4/13 [00:02<00:05, 1.56it/s] 38%|███▊ | 5/13 [00:03<00:05, 1.57it/s] 46%|████▌ | 6/13 [00:03<00:04, 1.59it/s] 54%|█████▍ | 7/13 [00:04<00:03, 1.61it/s] 62%|██████▏ | 8/13 [00:05<00:03, 1.62it/s] 69%|██████▉ | 9/13 [00:05<00:02, 1.62it/s] 77%|███████▋ | 10/13 [00:06<00:01, 1.62it/s] 85%|████████▍ | 11/13 [00:06<00:01, 1.63it/s] 92%|█████████▏| 12/13 [00:07<00:00, 1.63it/s] 100%|██████████| 13/13 [00:08<00:00, 1.63it/s] 100%|██████████| 13/13 [00:08<00:00, 1.60it/s] Decoding latents in cuda:0... done in 0.8s 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/589b006c6aa9404da1190caa2cb9d4d0/output-fbf5aa5bf27a494d86bfc6c584da310f-00000-1335517905.webp
https://files.tungsten.run/uploads/4d4d5d09efbe4cc2ad408fc633e153ca/output-67d4439d955146d2b544f19daf95eb04-00001-1335517906.webp
https://files.tungsten.run/uploads/34345fe23e1b4313a8f7cad8726cf7b1/output-026279c063614e6b9f5f4e4f129477b9-00002-1335517907.webp
This example was created by sparks
Finished in 85.0 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, solo, hime cut hair, looking at viewer, black hair, green eyes, bare shoulders, upper body, off shoulder, blurry, sweater, red lips, watermark, web address, realistic, <lora:Pony_DetailV2.0:1.0> Full negative prompt: 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:02<01:13, 2.47s/it] 6%|▋ | 2/31 [00:03<00:49, 1.72s/it] 10%|▉ | 3/31 [00:04<00:41, 1.47s/it] 13%|█▎ | 4/31 [00:06<00:36, 1.36s/it] 16%|█▌ | 5/31 [00:07<00:33, 1.30s/it] 19%|█▉ | 6/31 [00:08<00:31, 1.26s/it] 23%|██▎ | 7/31 [00:09<00:29, 1.24s/it] 26%|██▌ | 8/31 [00:10<00:28, 1.23s/it] 29%|██▉ | 9/31 [00:12<00:26, 1.22s/it] 32%|███▏ | 10/31 [00:13<00:25, 1.21s/it] 35%|███▌ | 11/31 [00:14<00:24, 1.21s/it] 39%|███▊ | 12/31 [00:15<00:23, 1.21s/it] 42%|████▏ | 13/31 [00:16<00:21, 1.21s/it] 45%|████▌ | 14/31 [00:18<00:20, 1.21s/it] 48%|████▊ | 15/31 [00:19<00:19, 1.20s/it] 52%|█████▏ | 16/31 [00:20<00:18, 1.21s/it] 55%|█████▍ | 17/31 [00:21<00:16, 1.20s/it] 58%|█████▊ | 18/31 [00:22<00:15, 1.20s/it] 61%|██████▏ | 19/31 [00:24<00:14, 1.20s/it] 65%|██████▍ | 20/31 [00:25<00:13, 1.20s/it] 68%|██████▊ | 21/31 [00:26<00:12, 1.20s/it] 71%|███████ | 22/31 [00:27<00:10, 1.21s/it] 74%|███████▍ | 23/31 [00:28<00:09, 1.21s/it] 77%|███████▋ | 24/31 [00:30<00:08, 1.21s/it] 81%|████████ | 25/31 [00:31<00:07, 1.21s/it] 84%|████████▍ | 26/31 [00:32<00:06, 1.21s/it] 87%|████████▋ | 27/31 [00:33<00:04, 1.21s/it] 90%|█████████ | 28/31 [00:34<00:03, 1.21s/it] 94%|█████████▎| 29/31 [00:36<00:02, 1.21s/it] 97%|█████████▋| 30/31 [00:37<00:01, 1.22s/it] 100%|██████████| 31/31 [00:38<00:00, 1.21s/it] 100%|██████████| 31/31 [00:38<00:00, 1.24s/it] Decoding latents in cuda:0... done in 2.34s Move latents to cpu... done in 0.03s 0: 640x448 1 face, 328.6ms Speed: 4.6ms preprocess, 328.6ms inference, 60.0ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:01<00:20, 1.73s/it] 15%|█▌ | 2/13 [00:03<00:17, 1.61s/it] 23%|██▎ | 3/13 [00:04<00:15, 1.54s/it] 31%|███ | 4/13 [00:05<00:10, 1.19s/it] 38%|███▊ | 5/13 [00:05<00:07, 1.02it/s] 46%|████▌ | 6/13 [00:07<00:07, 1.04s/it] 54%|█████▍ | 7/13 [00:07<00:05, 1.11it/s] 62%|██████▏ | 8/13 [00:08<00:04, 1.23it/s] 69%|██████▉ | 9/13 [00:08<00:03, 1.33it/s] 77%|███████▋ | 10/13 [00:09<00:02, 1.40it/s] 85%|████████▍ | 11/13 [00:10<00:01, 1.46it/s] 92%|█████████▏| 12/13 [00:10<00:00, 1.51it/s] 100%|██████████| 13/13 [00:11<00:00, 1.55it/s] 100%|██████████| 13/13 [00:11<00:00, 1.13it/s] Decoding latents in cuda:0... done in 0.77s Move latents to cpu... done in 0.0s 0: 640x448 1 face, 8.1ms Speed: 2.4ms preprocess, 8.1ms inference, 1.8ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:07, 1.63it/s] 15%|█▌ | 2/13 [00:01<00:06, 1.60it/s] 23%|██▎ | 3/13 [00:01<00:06, 1.61it/s] 31%|███ | 4/13 [00:02<00:05, 1.62it/s] 38%|███▊ | 5/13 [00:03<00:04, 1.62it/s] 46%|████▌ | 6/13 [00:03<00:04, 1.58it/s] 54%|█████▍ | 7/13 [00:04<00:03, 1.59it/s] 62%|██████▏ | 8/13 [00:04<00:03, 1.60it/s] 69%|██████▉ | 9/13 [00:05<00:02, 1.62it/s] 77%|███████▋ | 10/13 [00:06<00:01, 1.58it/s] 85%|████████▍ | 11/13 [00:06<00:01, 1.57it/s] 92%|█████████▏| 12/13 [00:07<00:00, 1.59it/s] 100%|██████████| 13/13 [00:08<00:00, 1.59it/s] 100%|██████████| 13/13 [00:08<00:00, 1.60it/s] Decoding latents in cuda:0... done in 0.78s Move latents to cpu... done in 0.0s 0: 640x448 1 face, 9.6ms Speed: 2.4ms preprocess, 9.6ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 448) 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:07, 1.59it/s] 15%|█▌ | 2/13 [00:01<00:07, 1.52it/s] 23%|██▎ | 3/13 [00:01<00:06, 1.52it/s] 31%|███ | 4/13 [00:02<00:05, 1.56it/s] 38%|███▊ | 5/13 [00:03<00:05, 1.57it/s] 46%|████▌ | 6/13 [00:03<00:04, 1.59it/s] 54%|█████▍ | 7/13 [00:04<00:03, 1.61it/s] 62%|██████▏ | 8/13 [00:05<00:03, 1.62it/s] 69%|██████▉ | 9/13 [00:05<00:02, 1.62it/s] 77%|███████▋ | 10/13 [00:06<00:01, 1.62it/s] 85%|████████▍ | 11/13 [00:06<00:01, 1.63it/s] 92%|█████████▏| 12/13 [00:07<00:00, 1.63it/s] 100%|██████████| 13/13 [00:08<00:00, 1.63it/s] 100%|██████████| 13/13 [00:08<00:00, 1.60it/s] Decoding latents in cuda:0... done in 0.8s Move latents to cpu... done in 0.0s Uploading files.. Finished.