tungsten-logo
Sign In
yamers-realistic5
yamers-realistic5

yamers-realistic5

6 stars
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/a81965589d214601be27d4006730eb22/00000-2803491274.webp
https://files.tungsten.run/uploads/431579ba3bbf411e979249519c01ebbc/00001-2803491275.webp
https://files.tungsten.run/uploads/3305c22e6cb04bb298417e6f3c2384df/00002-2803491276.webp
This example was created by sparks
Finished in 382.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors Full prompt: extreme close up on the helmet of the doom slayer, broken doom slayer helmet, photorealistic, doom slayer, doom eternal, raging face of the doom slayer, <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<06:45, 5.13s/it] 2%|▎ | 2/80 [00:10<06:52, 5.29s/it] 4%|▍ | 3/80 [00:15<06:43, 5.24s/it] 5%|▌ | 4/80 [00:21<06:44, 5.32s/it] 6%|▋ | 5/80 [00:26<06:42, 5.37s/it] 8%|▊ | 6/80 [00:32<06:41, 5.42s/it] 9%|▉ | 7/80 [00:37<06:36, 5.43s/it] 10%|█ | 8/80 [00:42<06:28, 5.40s/it] 11%|█▏ | 9/80 [00:48<06:21, 5.38s/it] 12%|█▎ | 10/80 [00:53<06:11, 5.31s/it] 14%|█▍ | 11/80 [00:58<06:05, 5.30s/it] 15%|█▌ | 12/80 [01:05<06:27, 5.70s/it] 16%|█▋ | 13/80 [01:10<06:14, 5.59s/it] 18%|█▊ | 14/80 [01:15<06:03, 5.51s/it] 19%|█▉ | 15/80 [01:21<05:54, 5.46s/it] 20%|██ | 16/80 [01:26<05:47, 5.43s/it] 21%|██▏ | 17/80 [01:32<05:40, 5.41s/it] 22%|██▎ | 18/80 [01:37<05:35, 5.42s/it] 24%|██▍ | 19/80 [01:42<05:30, 5.42s/it] 25%|██▌ | 20/80 [01:48<05:25, 5.42s/it] 26%|██▋ | 21/80 [01:53<05:19, 5.42s/it] 28%|██▊ | 22/80 [01:59<05:13, 5.40s/it] 29%|██▉ | 23/80 [02:04<05:03, 5.32s/it] 30%|███ | 24/80 [02:09<04:57, 5.31s/it] 31%|███▏ | 25/80 [02:14<04:54, 5.36s/it] 32%|███▎ | 26/80 [02:20<04:46, 5.30s/it] 34%|███▍ | 27/80 [02:24<04:24, 5.00s/it] 35%|███▌ | 28/80 [02:30<04:29, 5.18s/it] 36%|███▋ | 29/80 [02:35<04:27, 5.24s/it] 38%|███▊ | 30/80 [02:40<04:21, 5.23s/it] 39%|███▉ | 31/80 [02:45<04:12, 5.16s/it] 40%|████ | 32/80 [02:50<03:58, 4.97s/it] 41%|████▏ | 33/80 [02:55<03:57, 5.06s/it] 42%|████▎ | 34/80 [02:59<03:36, 4.71s/it] 44%|████▍ | 35/80 [03:05<03:46, 5.04s/it] 45%|████▌ | 36/80 [03:10<03:43, 5.09s/it] 46%|████▋ | 37/80 [03:14<03:32, 4.95s/it] 48%|████▊ | 38/80 [03:19<03:18, 4.73s/it] 49%|████▉ | 39/80 [03:23<03:11, 4.66s/it] 50%|█████ | 40/80 [03:28<03:13, 4.84s/it] 51%|█████▏ | 41/80 [03:33<03:03, 4.72s/it] 52%|█████▎ | 42/80 [03:37<02:52, 4.53s/it] 54%|█████▍ | 43/80 [03:41<02:42, 4.40s/it] 55%|█████▌ | 44/80 [03:46<02:45, 4.61s/it] 56%|█████▋ | 45/80 [03:51<02:40, 4.58s/it] 57%|█████▊ | 46/80 [03:55<02:34, 4.54s/it] 59%|█████▉ | 47/80 [04:00<02:28, 4.50s/it] 60%|██████ | 48/80 [04:04<02:22, 4.46s/it] 61%|██████▏ | 49/80 [04:08<02:16, 4.39s/it] 62%|██████▎ | 50/80 [04:13<02:17, 4.60s/it] 64%|██████▍ | 51/80 [04:18<02:12, 4.58s/it] 65%|██████▌ | 52/80 [04:23<02:11, 4.68s/it] 66%|██████▋ | 53/80 [04:27<02:02, 4.52s/it] 68%|██████▊ | 54/80 [04:31<01:56, 4.47s/it] 69%|██████▉ | 55/80 [04:36<01:54, 4.57s/it] 70%|███████ | 56/80 [04:41<01:54, 4.76s/it] 71%|███████▏ | 57/80 [04:46<01:47, 4.69s/it] 72%|███████▎ | 58/80 [04:51<01:45, 4.78s/it] 74%|███████▍ | 59/80 [04:56<01:42, 4.86s/it] 75%|███████▌ | 60/80 [05:00<01:32, 4.65s/it] 76%|███████▋ | 61/80 [05:04<01:26, 4.54s/it] 78%|███████▊ | 62/80 [05:09<01:22, 4.58s/it] 79%|███████▉ | 63/80 [05:13<01:14, 4.41s/it] 80%|████████ | 64/80 [05:17<01:10, 4.40s/it] 81%|████████▏ | 65/80 [05:21<01:03, 4.24s/it] 82%|████████▎ | 66/80 [05:25<00:57, 4.13s/it] 84%|████████▍ | 67/80 [05:29<00:52, 4.06s/it] 85%|████████▌ | 68/80 [05:33<00:48, 4.04s/it] 86%|████████▋ | 69/80 [05:37<00:44, 4.09s/it] 88%|████████▊ | 70/80 [05:41<00:40, 4.06s/it] 89%|████████▉ | 71/80 [05:45<00:36, 4.02s/it] 90%|█████████ | 72/80 [05:49<00:31, 3.96s/it] 91%|█████████▏| 73/80 [05:53<00:27, 3.91s/it] 92%|█████████▎| 74/80 [05:56<00:22, 3.81s/it] 94%|█████████▍| 75/80 [06:00<00:19, 3.89s/it] 95%|█████████▌| 76/80 [06:04<00:15, 3.88s/it] 96%|█████████▋| 77/80 [06:08<00:11, 3.76s/it] 98%|█████████▊| 78/80 [06:11<00:07, 3.68s/it] 99%|█████████▉| 79/80 [06:14<00:03, 3.52s/it] 100%|██████████| 80/80 [06:16<00:00, 2.85s/it] 100%|██████████| 80/80 [06:16<00:00, 4.70s/it] Decoding latents in cuda:0... done in 2.35s 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/a81965589d214601be27d4006730eb22/00000-2803491274.webp
https://files.tungsten.run/uploads/431579ba3bbf411e979249519c01ebbc/00001-2803491275.webp
https://files.tungsten.run/uploads/3305c22e6cb04bb298417e6f3c2384df/00002-2803491276.webp
This example was created by sparks
Finished in 382.9 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors Full prompt: extreme close up on the helmet of the doom slayer, broken doom slayer helmet, photorealistic, doom slayer, doom eternal, raging face of the doom slayer, <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<06:45, 5.13s/it] 2%|▎ | 2/80 [00:10<06:52, 5.29s/it] 4%|▍ | 3/80 [00:15<06:43, 5.24s/it] 5%|▌ | 4/80 [00:21<06:44, 5.32s/it] 6%|▋ | 5/80 [00:26<06:42, 5.37s/it] 8%|▊ | 6/80 [00:32<06:41, 5.42s/it] 9%|▉ | 7/80 [00:37<06:36, 5.43s/it] 10%|█ | 8/80 [00:42<06:28, 5.40s/it] 11%|█▏ | 9/80 [00:48<06:21, 5.38s/it] 12%|█▎ | 10/80 [00:53<06:11, 5.31s/it] 14%|█▍ | 11/80 [00:58<06:05, 5.30s/it] 15%|█▌ | 12/80 [01:05<06:27, 5.70s/it] 16%|█▋ | 13/80 [01:10<06:14, 5.59s/it] 18%|█▊ | 14/80 [01:15<06:03, 5.51s/it] 19%|█▉ | 15/80 [01:21<05:54, 5.46s/it] 20%|██ | 16/80 [01:26<05:47, 5.43s/it] 21%|██▏ | 17/80 [01:32<05:40, 5.41s/it] 22%|██▎ | 18/80 [01:37<05:35, 5.42s/it] 24%|██▍ | 19/80 [01:42<05:30, 5.42s/it] 25%|██▌ | 20/80 [01:48<05:25, 5.42s/it] 26%|██▋ | 21/80 [01:53<05:19, 5.42s/it] 28%|██▊ | 22/80 [01:59<05:13, 5.40s/it] 29%|██▉ | 23/80 [02:04<05:03, 5.32s/it] 30%|███ | 24/80 [02:09<04:57, 5.31s/it] 31%|███▏ | 25/80 [02:14<04:54, 5.36s/it] 32%|███▎ | 26/80 [02:20<04:46, 5.30s/it] 34%|███▍ | 27/80 [02:24<04:24, 5.00s/it] 35%|███▌ | 28/80 [02:30<04:29, 5.18s/it] 36%|███▋ | 29/80 [02:35<04:27, 5.24s/it] 38%|███▊ | 30/80 [02:40<04:21, 5.23s/it] 39%|███▉ | 31/80 [02:45<04:12, 5.16s/it] 40%|████ | 32/80 [02:50<03:58, 4.97s/it] 41%|████▏ | 33/80 [02:55<03:57, 5.06s/it] 42%|████▎ | 34/80 [02:59<03:36, 4.71s/it] 44%|████▍ | 35/80 [03:05<03:46, 5.04s/it] 45%|████▌ | 36/80 [03:10<03:43, 5.09s/it] 46%|████▋ | 37/80 [03:14<03:32, 4.95s/it] 48%|████▊ | 38/80 [03:19<03:18, 4.73s/it] 49%|████▉ | 39/80 [03:23<03:11, 4.66s/it] 50%|█████ | 40/80 [03:28<03:13, 4.84s/it] 51%|█████▏ | 41/80 [03:33<03:03, 4.72s/it] 52%|█████▎ | 42/80 [03:37<02:52, 4.53s/it] 54%|█████▍ | 43/80 [03:41<02:42, 4.40s/it] 55%|█████▌ | 44/80 [03:46<02:45, 4.61s/it] 56%|█████▋ | 45/80 [03:51<02:40, 4.58s/it] 57%|█████▊ | 46/80 [03:55<02:34, 4.54s/it] 59%|█████▉ | 47/80 [04:00<02:28, 4.50s/it] 60%|██████ | 48/80 [04:04<02:22, 4.46s/it] 61%|██████▏ | 49/80 [04:08<02:16, 4.39s/it] 62%|██████▎ | 50/80 [04:13<02:17, 4.60s/it] 64%|██████▍ | 51/80 [04:18<02:12, 4.58s/it] 65%|██████▌ | 52/80 [04:23<02:11, 4.68s/it] 66%|██████▋ | 53/80 [04:27<02:02, 4.52s/it] 68%|██████▊ | 54/80 [04:31<01:56, 4.47s/it] 69%|██████▉ | 55/80 [04:36<01:54, 4.57s/it] 70%|███████ | 56/80 [04:41<01:54, 4.76s/it] 71%|███████▏ | 57/80 [04:46<01:47, 4.69s/it] 72%|███████▎ | 58/80 [04:51<01:45, 4.78s/it] 74%|███████▍ | 59/80 [04:56<01:42, 4.86s/it] 75%|███████▌ | 60/80 [05:00<01:32, 4.65s/it] 76%|███████▋ | 61/80 [05:04<01:26, 4.54s/it] 78%|███████▊ | 62/80 [05:09<01:22, 4.58s/it] 79%|███████▉ | 63/80 [05:13<01:14, 4.41s/it] 80%|████████ | 64/80 [05:17<01:10, 4.40s/it] 81%|████████▏ | 65/80 [05:21<01:03, 4.24s/it] 82%|████████▎ | 66/80 [05:25<00:57, 4.13s/it] 84%|████████▍ | 67/80 [05:29<00:52, 4.06s/it] 85%|████████▌ | 68/80 [05:33<00:48, 4.04s/it] 86%|████████▋ | 69/80 [05:37<00:44, 4.09s/it] 88%|████████▊ | 70/80 [05:41<00:40, 4.06s/it] 89%|████████▉ | 71/80 [05:45<00:36, 4.02s/it] 90%|█████████ | 72/80 [05:49<00:31, 3.96s/it] 91%|█████████▏| 73/80 [05:53<00:27, 3.91s/it] 92%|█████████▎| 74/80 [05:56<00:22, 3.81s/it] 94%|█████████▍| 75/80 [06:00<00:19, 3.89s/it] 95%|█████████▌| 76/80 [06:04<00:15, 3.88s/it] 96%|█████████▋| 77/80 [06:08<00:11, 3.76s/it] 98%|█████████▊| 78/80 [06:11<00:07, 3.68s/it] 99%|█████████▉| 79/80 [06:14<00:03, 3.52s/it] 100%|██████████| 80/80 [06:16<00:00, 2.85s/it] 100%|██████████| 80/80 [06:16<00:00, 4.70s/it] Decoding latents in cuda:0... done in 2.35s Move latents to cpu... done in 0.03s Uploading outputs... Finished.