Version: v5.0
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
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/b48c2c2d5d1b41f5ba502a32af5a7437/00000-3476920469.webp
https://files.tungsten.run/uploads/5e52096701534826b0ea4cbdaa67b151/00001-3476920470.webp
https://files.tungsten.run/uploads/3cc395d5528a41f0ab28ac8490feceb7/00002-3476920471.webp
This example was created by sparks
Finished in 381.6 seconds
Preparing model sparks/yamers-realistic5:v5.0... v5.0: Pulling from sparks/yamers-realistic5 578acb154839: Already exists ac65017cfc56: Already exists 146269b80f9c: Already exists b51bc62cc3ca: Already exists 4ba34dd48a55: Already exists 2c0d7edf2b4f: Already exists bd3aa092d934: Already exists a2a0b079260c: Already exists 48e8a1cea0b1: Already exists 607175607db9: Already exists 44762e60be28: Already exists 49aa9c9ba08f: Already exists 8915fc22d7d8: Already exists 6ebc9a3b0b34: Already exists 4f4fb700ef54: Already exists 84b14763edf4: Already exists 3c2bd422ca6b: Pull complete 0e2f131f54d1: Pull complete f8ff661fc7d4: Pull complete 3d95ccad48b9: Pull complete Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors Full prompt: by Roger Deakins, cinematic, breathtaking details, dry brush art, canvas of ink, emanating particles, cinder knight, dark souls, disintegrating effect:1.3, knight in black armor, side view, dark, gritty, horror epic photorealistic, art by wlop Yuumei, photography, <lora:add-detail-xl:1.0> Full negative prompt: bad quality, bad anatomy, worst quality, low quality, low resolution, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image, deformation 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:05<06:43, 5.11s/it] 2%|▎ | 2/80 [00:10<06:49, 5.25s/it] 4%|▍ | 3/80 [00:15<06:39, 5.18s/it] 5%|▌ | 4/80 [00:21<06:41, 5.29s/it] 6%|▋ | 5/80 [00:26<06:32, 5.23s/it] 8%|▊ | 6/80 [00:31<06:29, 5.27s/it] 9%|▉ | 7/80 [00:36<06:29, 5.34s/it] 10%|█ | 8/80 [00:42<06:23, 5.33s/it] 11%|█▏ | 9/80 [00:47<06:18, 5.34s/it] 12%|█▎ | 10/80 [00:52<06:06, 5.24s/it] 14%|█▍ | 11/80 [00:57<06:01, 5.23s/it] 15%|█▌ | 12/80 [01:03<05:56, 5.24s/it] 16%|█▋ | 13/80 [01:08<05:54, 5.29s/it] 18%|█▊ | 14/80 [01:13<05:48, 5.28s/it] 19%|█▉ | 15/80 [01:18<05:39, 5.22s/it] 20%|██ | 16/80 [01:23<05:31, 5.18s/it] 21%|██▏ | 17/80 [01:29<05:25, 5.16s/it] 22%|██▎ | 18/80 [01:34<05:24, 5.23s/it] 24%|██▍ | 19/80 [01:39<05:21, 5.28s/it] 25%|██▌ | 20/80 [01:45<05:18, 5.31s/it] 26%|██▋ | 21/80 [01:50<05:14, 5.33s/it] 28%|██▊ | 22/80 [01:55<05:08, 5.31s/it] 29%|██▉ | 23/80 [02:01<04:59, 5.26s/it] 30%|███ | 24/80 [02:06<04:54, 5.26s/it] 31%|███▏ | 25/80 [02:11<04:52, 5.31s/it] 32%|███▎ | 26/80 [02:16<04:44, 5.26s/it] 34%|███▍ | 27/80 [02:21<04:22, 4.95s/it] 35%|███▌ | 28/80 [02:26<04:26, 5.13s/it] 36%|███▋ | 29/80 [02:32<04:26, 5.22s/it] 38%|███▊ | 30/80 [02:37<04:20, 5.20s/it] 39%|███▉ | 31/80 [02:42<04:12, 5.16s/it] 40%|████ | 32/80 [02:46<03:57, 4.95s/it] 41%|████▏ | 33/80 [02:51<03:55, 5.02s/it] 42%|████▎ | 34/80 [02:55<03:34, 4.67s/it] 44%|████▍ | 35/80 [03:01<03:43, 4.97s/it] 45%|████▌ | 36/80 [03:06<03:42, 5.05s/it] 46%|████▋ | 37/80 [03:11<03:30, 4.91s/it] 48%|████▊ | 38/80 [03:15<03:17, 4.69s/it] 49%|████▉ | 39/80 [03:19<03:07, 4.57s/it] 50%|█████ | 40/80 [03:24<03:09, 4.74s/it] 51%|█████▏ | 41/80 [03:29<03:00, 4.63s/it] 52%|█████▎ | 42/80 [03:33<02:50, 4.48s/it] 54%|█████▍ | 43/80 [03:37<02:41, 4.36s/it] 55%|█████▌ | 44/80 [03:42<02:43, 4.55s/it] 56%|█████▋ | 45/80 [03:46<02:37, 4.51s/it] 57%|█████▊ | 46/80 [03:51<02:32, 4.48s/it] 59%|█████▉ | 47/80 [03:55<02:27, 4.46s/it] 60%|██████ | 48/80 [04:00<02:22, 4.45s/it] 61%|██████▏ | 49/80 [04:04<02:16, 4.40s/it] 62%|██████▎ | 50/80 [04:09<02:17, 4.58s/it] 64%|██████▍ | 51/80 [04:13<02:12, 4.56s/it] 65%|██████▌ | 52/80 [04:18<02:10, 4.65s/it] 66%|██████▋ | 53/80 [04:23<02:03, 4.57s/it] 68%|██████▊ | 54/80 [04:28<02:04, 4.77s/it] 69%|██████▉ | 55/80 [04:33<02:04, 4.97s/it] 70%|███████ | 56/80 [04:38<02:00, 5.01s/it] 71%|███████▏ | 57/80 [04:43<01:51, 4.83s/it] 72%|███████▎ | 58/80 [04:48<01:47, 4.86s/it] 74%|███████▍ | 59/80 [04:53<01:43, 4.92s/it] 75%|███████▌ | 60/80 [04:57<01:33, 4.69s/it] 76%|███████▋ | 61/80 [05:01<01:26, 4.56s/it] 78%|███████▊ | 62/80 [05:06<01:23, 4.66s/it] 79%|███████▉ | 63/80 [05:11<01:19, 4.65s/it] 80%|████████ | 64/80 [05:15<01:13, 4.58s/it] 81%|████████▏ | 65/80 [05:19<01:05, 4.37s/it] 82%|████████▎ | 66/80 [05:23<00:59, 4.25s/it] 84%|████████▍ | 67/80 [05:27<00:54, 4.16s/it] 85%|████████▌ | 68/80 [05:31<00:49, 4.12s/it] 86%|████████▋ | 69/80 [05:35<00:45, 4.15s/it] 88%|████████▊ | 70/80 [05:39<00:41, 4.12s/it] 89%|████████▉ | 71/80 [05:44<00:37, 4.19s/it] 90%|█████████ | 72/80 [05:48<00:33, 4.13s/it] 91%|█████████▏| 73/80 [05:51<00:28, 4.03s/it] 92%|█████████▎| 74/80 [05:55<00:23, 3.89s/it] 94%|█████████▍| 75/80 [05:59<00:19, 3.94s/it] 95%|█████████▌| 76/80 [06:03<00:15, 3.90s/it] 96%|█████████▋| 77/80 [06:06<00:11, 3.77s/it] 98%|█████████▊| 78/80 [06:10<00:07, 3.68s/it] 99%|█████████▉| 79/80 [06:13<00:03, 3.51s/it] 100%|██████████| 80/80 [06:14<00:00, 2.85s/it] 100%|██████████| 80/80 [06:14<00:00, 4.68s/it] Decoding latents in cuda:0... done in 2.37s Move latents to cpu... done in 0.03s Uploading outputs... Finished.
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
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/b48c2c2d5d1b41f5ba502a32af5a7437/00000-3476920469.webp
https://files.tungsten.run/uploads/5e52096701534826b0ea4cbdaa67b151/00001-3476920470.webp
https://files.tungsten.run/uploads/3cc395d5528a41f0ab28ac8490feceb7/00002-3476920471.webp
This example was created by sparks
Finished in 381.6 seconds
Preparing model sparks/yamers-realistic5:v5.0... v5.0: Pulling from sparks/yamers-realistic5 578acb154839: Already exists ac65017cfc56: Already exists 146269b80f9c: Already exists b51bc62cc3ca: Already exists 4ba34dd48a55: Already exists 2c0d7edf2b4f: Already exists bd3aa092d934: Already exists a2a0b079260c: Already exists 48e8a1cea0b1: Already exists 607175607db9: Already exists 44762e60be28: Already exists 49aa9c9ba08f: Already exists 8915fc22d7d8: Already exists 6ebc9a3b0b34: Already exists 4f4fb700ef54: Already exists 84b14763edf4: Already exists 3c2bd422ca6b: Pull complete 0e2f131f54d1: Pull complete f8ff661fc7d4: Pull complete 3d95ccad48b9: Pull complete Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors Full prompt: by Roger Deakins, cinematic, breathtaking details, dry brush art, canvas of ink, emanating particles, cinder knight, dark souls, disintegrating effect:1.3, knight in black armor, side view, dark, gritty, horror epic photorealistic, art by wlop Yuumei, photography, <lora:add-detail-xl:1.0> Full negative prompt: bad quality, bad anatomy, worst quality, low quality, low resolution, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image, deformation 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:05<06:43, 5.11s/it] 2%|▎ | 2/80 [00:10<06:49, 5.25s/it] 4%|▍ | 3/80 [00:15<06:39, 5.18s/it] 5%|▌ | 4/80 [00:21<06:41, 5.29s/it] 6%|▋ | 5/80 [00:26<06:32, 5.23s/it] 8%|▊ | 6/80 [00:31<06:29, 5.27s/it] 9%|▉ | 7/80 [00:36<06:29, 5.34s/it] 10%|█ | 8/80 [00:42<06:23, 5.33s/it] 11%|█▏ | 9/80 [00:47<06:18, 5.34s/it] 12%|█▎ | 10/80 [00:52<06:06, 5.24s/it] 14%|█▍ | 11/80 [00:57<06:01, 5.23s/it] 15%|█▌ | 12/80 [01:03<05:56, 5.24s/it] 16%|█▋ | 13/80 [01:08<05:54, 5.29s/it] 18%|█▊ | 14/80 [01:13<05:48, 5.28s/it] 19%|█▉ | 15/80 [01:18<05:39, 5.22s/it] 20%|██ | 16/80 [01:23<05:31, 5.18s/it] 21%|██▏ | 17/80 [01:29<05:25, 5.16s/it] 22%|██▎ | 18/80 [01:34<05:24, 5.23s/it] 24%|██▍ | 19/80 [01:39<05:21, 5.28s/it] 25%|██▌ | 20/80 [01:45<05:18, 5.31s/it] 26%|██▋ | 21/80 [01:50<05:14, 5.33s/it] 28%|██▊ | 22/80 [01:55<05:08, 5.31s/it] 29%|██▉ | 23/80 [02:01<04:59, 5.26s/it] 30%|███ | 24/80 [02:06<04:54, 5.26s/it] 31%|███▏ | 25/80 [02:11<04:52, 5.31s/it] 32%|███▎ | 26/80 [02:16<04:44, 5.26s/it] 34%|███▍ | 27/80 [02:21<04:22, 4.95s/it] 35%|███▌ | 28/80 [02:26<04:26, 5.13s/it] 36%|███▋ | 29/80 [02:32<04:26, 5.22s/it] 38%|███▊ | 30/80 [02:37<04:20, 5.20s/it] 39%|███▉ | 31/80 [02:42<04:12, 5.16s/it] 40%|████ | 32/80 [02:46<03:57, 4.95s/it] 41%|████▏ | 33/80 [02:51<03:55, 5.02s/it] 42%|████▎ | 34/80 [02:55<03:34, 4.67s/it] 44%|████▍ | 35/80 [03:01<03:43, 4.97s/it] 45%|████▌ | 36/80 [03:06<03:42, 5.05s/it] 46%|████▋ | 37/80 [03:11<03:30, 4.91s/it] 48%|████▊ | 38/80 [03:15<03:17, 4.69s/it] 49%|████▉ | 39/80 [03:19<03:07, 4.57s/it] 50%|█████ | 40/80 [03:24<03:09, 4.74s/it] 51%|█████▏ | 41/80 [03:29<03:00, 4.63s/it] 52%|█████▎ | 42/80 [03:33<02:50, 4.48s/it] 54%|█████▍ | 43/80 [03:37<02:41, 4.36s/it] 55%|█████▌ | 44/80 [03:42<02:43, 4.55s/it] 56%|█████▋ | 45/80 [03:46<02:37, 4.51s/it] 57%|█████▊ | 46/80 [03:51<02:32, 4.48s/it] 59%|█████▉ | 47/80 [03:55<02:27, 4.46s/it] 60%|██████ | 48/80 [04:00<02:22, 4.45s/it] 61%|██████▏ | 49/80 [04:04<02:16, 4.40s/it] 62%|██████▎ | 50/80 [04:09<02:17, 4.58s/it] 64%|██████▍ | 51/80 [04:13<02:12, 4.56s/it] 65%|██████▌ | 52/80 [04:18<02:10, 4.65s/it] 66%|██████▋ | 53/80 [04:23<02:03, 4.57s/it] 68%|██████▊ | 54/80 [04:28<02:04, 4.77s/it] 69%|██████▉ | 55/80 [04:33<02:04, 4.97s/it] 70%|███████ | 56/80 [04:38<02:00, 5.01s/it] 71%|███████▏ | 57/80 [04:43<01:51, 4.83s/it] 72%|███████▎ | 58/80 [04:48<01:47, 4.86s/it] 74%|███████▍ | 59/80 [04:53<01:43, 4.92s/it] 75%|███████▌ | 60/80 [04:57<01:33, 4.69s/it] 76%|███████▋ | 61/80 [05:01<01:26, 4.56s/it] 78%|███████▊ | 62/80 [05:06<01:23, 4.66s/it] 79%|███████▉ | 63/80 [05:11<01:19, 4.65s/it] 80%|████████ | 64/80 [05:15<01:13, 4.58s/it] 81%|████████▏ | 65/80 [05:19<01:05, 4.37s/it] 82%|████████▎ | 66/80 [05:23<00:59, 4.25s/it] 84%|████████▍ | 67/80 [05:27<00:54, 4.16s/it] 85%|████████▌ | 68/80 [05:31<00:49, 4.12s/it] 86%|████████▋ | 69/80 [05:35<00:45, 4.15s/it] 88%|████████▊ | 70/80 [05:39<00:41, 4.12s/it] 89%|████████▉ | 71/80 [05:44<00:37, 4.19s/it] 90%|█████████ | 72/80 [05:48<00:33, 4.13s/it] 91%|█████████▏| 73/80 [05:51<00:28, 4.03s/it] 92%|█████████▎| 74/80 [05:55<00:23, 3.89s/it] 94%|█████████▍| 75/80 [05:59<00:19, 3.94s/it] 95%|█████████▌| 76/80 [06:03<00:15, 3.90s/it] 96%|█████████▋| 77/80 [06:06<00:11, 3.77s/it] 98%|█████████▊| 78/80 [06:10<00:07, 3.68s/it] 99%|█████████▉| 79/80 [06:13<00:03, 3.51s/it] 100%|██████████| 80/80 [06:14<00:00, 2.85s/it] 100%|██████████| 80/80 [06:14<00:00, 4.68s/it] Decoding latents in cuda:0... done in 2.37s Move latents to cpu... done in 0.03s Uploading outputs... Finished.