tungsten-logo
Sign In
photopedia-xl
photopedia-xl

photopedia-xl

23 stars
1 running now
Version: v4.5
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/d104ac77f5f3451594d5b6252ef6e233/00000-1777179944.webp
https://files.tungsten.run/uploads/c94c6c3c0d2046e98a048219af4403b9/00001-1777179945.webp
https://files.tungsten.run/uploads/0a44d41084e048ad95365137b7fc8dd3/00002-1777179946.webp
This example was created by evevalentine2017
Finished in 115.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Yoda, Star Wars, holding a wooden sign "I love Tungsten", spaceship background Full negative prompt: desaturated, unrealistic, blurry, unsharp, deformed, bad anatomy, poorly drawn face, mutated, extra limb, poorly drawn hands, missing limb, missing fingers, cropped, low quality, low resolution, abnormal eye proportion, oversaturated, undersaturated 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:01<01:15, 1.93s/it] 5%|▌ | 2/40 [00:03<01:13, 1.94s/it] 8%|▊ | 3/40 [00:05<01:11, 1.94s/it] 10%|█ | 4/40 [00:07<01:09, 1.94s/it] 12%|█▎ | 5/40 [00:09<01:07, 1.94s/it] 15%|█▌ | 6/40 [00:11<01:06, 1.95s/it] 18%|█▊ | 7/40 [00:13<01:04, 1.95s/it] 20%|██ | 8/40 [00:15<01:02, 1.96s/it] 22%|██▎ | 9/40 [00:17<01:00, 1.96s/it] 25%|██▌ | 10/40 [00:19<00:59, 1.97s/it] 28%|██▊ | 11/40 [00:21<00:57, 1.97s/it] 30%|███ | 12/40 [00:23<00:55, 1.98s/it] 32%|███▎ | 13/40 [00:25<00:53, 1.99s/it] 35%|███▌ | 14/40 [00:27<00:51, 1.99s/it] 38%|███▊ | 15/40 [00:29<00:49, 2.00s/it] 40%|████ | 16/40 [00:31<00:47, 1.99s/it] 42%|████▎ | 17/40 [00:33<00:45, 1.99s/it] 45%|████▌ | 18/40 [00:35<00:43, 1.99s/it] 48%|████▊ | 19/40 [00:37<00:41, 1.99s/it] 50%|█████ | 20/40 [00:39<00:39, 1.98s/it] 52%|█████▎ | 21/40 [00:41<00:37, 1.98s/it] 55%|█████▌ | 22/40 [00:43<00:35, 1.97s/it] 57%|█████▊ | 23/40 [00:45<00:33, 1.97s/it] 60%|██████ | 24/40 [00:47<00:31, 1.96s/it] 62%|██████▎ | 25/40 [00:49<00:29, 1.96s/it] 65%|██████▌ | 26/40 [00:51<00:27, 1.95s/it] 68%|██████▊ | 27/40 [00:53<00:25, 1.95s/it] 70%|███████ | 28/40 [00:55<00:23, 1.95s/it] 72%|███████▎ | 29/40 [00:57<00:21, 1.95s/it] 75%|███████▌ | 30/40 [00:58<00:19, 1.95s/it] 78%|███████▊ | 31/40 [01:00<00:17, 1.95s/it] 80%|████████ | 32/40 [01:02<00:15, 1.95s/it] 82%|████████▎ | 33/40 [01:04<00:13, 1.95s/it] 85%|████████▌ | 34/40 [01:06<00:11, 1.95s/it] 88%|████████▊ | 35/40 [01:08<00:09, 1.95s/it] 90%|█████████ | 36/40 [01:10<00:07, 1.94s/it] 92%|█████████▎| 37/40 [01:12<00:05, 1.94s/it] 95%|█████████▌| 38/40 [01:14<00:03, 1.94s/it] 98%|█████████▊| 39/40 [01:16<00:01, 1.94s/it] 100%|██████████| 40/40 [01:17<00:00, 1.64s/it] 100%|██████████| 40/40 [01:17<00:00, 1.94s/it] Decoding latents in cuda:0... done in 1.73s Move latents to cpu... done in 0.02s 0: 480x640 1 face, 162.5ms Speed: 2.9ms preprocess, 162.5ms inference, 29.5ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:14, 1.24it/s] 11%|█ | 2/19 [00:01<00:12, 1.37it/s] 16%|█▌ | 3/19 [00:02<00:11, 1.43it/s] 21%|██ | 4/19 [00:02<00:10, 1.46it/s] 26%|██▋ | 5/19 [00:03<00:09, 1.47it/s] 32%|███▏ | 6/19 [00:04<00:08, 1.48it/s] 37%|███▋ | 7/19 [00:04<00:08, 1.49it/s] 42%|████▏ | 8/19 [00:05<00:07, 1.50it/s] 47%|████▋ | 9/19 [00:06<00:06, 1.51it/s] 53%|█████▎ | 10/19 [00:06<00:05, 1.52it/s] 58%|█████▊ | 11/19 [00:07<00:05, 1.52it/s] 63%|██████▎ | 12/19 [00:08<00:04, 1.52it/s] 68%|██████▊ | 13/19 [00:08<00:03, 1.51it/s] 74%|███████▎ | 14/19 [00:09<00:03, 1.50it/s] 79%|███████▉ | 15/19 [00:10<00:02, 1.50it/s] 84%|████████▍ | 16/19 [00:10<00:01, 1.51it/s] 89%|████████▉ | 17/19 [00:11<00:01, 1.51it/s] 95%|█████████▍| 18/19 [00:12<00:00, 1.51it/s] 100%|██████████| 19/19 [00:12<00:00, 1.79it/s] 100%|██████████| 19/19 [00:12<00:00, 1.53it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 480x640 1 face, 8.0ms Speed: 2.5ms preprocess, 8.0ms inference, 1.5ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:12, 1.48it/s] 11%|█ | 2/19 [00:01<00:11, 1.50it/s] 16%|█▌ | 3/19 [00:01<00:10, 1.51it/s] 21%|██ | 4/19 [00:02<00:09, 1.52it/s] 26%|██▋ | 5/19 [00:03<00:09, 1.52it/s] 32%|███▏ | 6/19 [00:03<00:08, 1.51it/s] 37%|███▋ | 7/19 [00:04<00:07, 1.50it/s] 42%|████▏ | 8/19 [00:05<00:07, 1.51it/s] 47%|████▋ | 9/19 [00:05<00:06, 1.51it/s] 53%|█████▎ | 10/19 [00:06<00:06, 1.49it/s] 58%|█████▊ | 11/19 [00:07<00:05, 1.50it/s] 63%|██████▎ | 12/19 [00:07<00:04, 1.50it/s] 68%|██████▊ | 13/19 [00:08<00:04, 1.50it/s] 74%|███████▎ | 14/19 [00:09<00:03, 1.49it/s] 79%|███████▉ | 15/19 [00:09<00:02, 1.49it/s] 84%|████████▍ | 16/19 [00:10<00:02, 1.48it/s] 89%|████████▉ | 17/19 [00:11<00:01, 1.49it/s] 95%|█████████▍| 18/19 [00:12<00:00, 1.49it/s] 100%|██████████| 19/19 [00:12<00:00, 1.76it/s] 100%|██████████| 19/19 [00:12<00:00, 1.54it/s] Decoding latents in cuda:0... done in 0.59s Move latents to cpu... done in 0.0s 0: 480x640 (no detections), 8.4ms Speed: 2.3ms preprocess, 8.4ms inference, 0.7ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. 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/d104ac77f5f3451594d5b6252ef6e233/00000-1777179944.webp
https://files.tungsten.run/uploads/c94c6c3c0d2046e98a048219af4403b9/00001-1777179945.webp
https://files.tungsten.run/uploads/0a44d41084e048ad95365137b7fc8dd3/00002-1777179946.webp
This example was created by evevalentine2017
Finished in 115.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Yoda, Star Wars, holding a wooden sign "I love Tungsten", spaceship background Full negative prompt: desaturated, unrealistic, blurry, unsharp, deformed, bad anatomy, poorly drawn face, mutated, extra limb, poorly drawn hands, missing limb, missing fingers, cropped, low quality, low resolution, abnormal eye proportion, oversaturated, undersaturated 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:01<01:15, 1.93s/it] 5%|▌ | 2/40 [00:03<01:13, 1.94s/it] 8%|▊ | 3/40 [00:05<01:11, 1.94s/it] 10%|█ | 4/40 [00:07<01:09, 1.94s/it] 12%|█▎ | 5/40 [00:09<01:07, 1.94s/it] 15%|█▌ | 6/40 [00:11<01:06, 1.95s/it] 18%|█▊ | 7/40 [00:13<01:04, 1.95s/it] 20%|██ | 8/40 [00:15<01:02, 1.96s/it] 22%|██▎ | 9/40 [00:17<01:00, 1.96s/it] 25%|██▌ | 10/40 [00:19<00:59, 1.97s/it] 28%|██▊ | 11/40 [00:21<00:57, 1.97s/it] 30%|███ | 12/40 [00:23<00:55, 1.98s/it] 32%|███▎ | 13/40 [00:25<00:53, 1.99s/it] 35%|███▌ | 14/40 [00:27<00:51, 1.99s/it] 38%|███▊ | 15/40 [00:29<00:49, 2.00s/it] 40%|████ | 16/40 [00:31<00:47, 1.99s/it] 42%|████▎ | 17/40 [00:33<00:45, 1.99s/it] 45%|████▌ | 18/40 [00:35<00:43, 1.99s/it] 48%|████▊ | 19/40 [00:37<00:41, 1.99s/it] 50%|█████ | 20/40 [00:39<00:39, 1.98s/it] 52%|█████▎ | 21/40 [00:41<00:37, 1.98s/it] 55%|█████▌ | 22/40 [00:43<00:35, 1.97s/it] 57%|█████▊ | 23/40 [00:45<00:33, 1.97s/it] 60%|██████ | 24/40 [00:47<00:31, 1.96s/it] 62%|██████▎ | 25/40 [00:49<00:29, 1.96s/it] 65%|██████▌ | 26/40 [00:51<00:27, 1.95s/it] 68%|██████▊ | 27/40 [00:53<00:25, 1.95s/it] 70%|███████ | 28/40 [00:55<00:23, 1.95s/it] 72%|███████▎ | 29/40 [00:57<00:21, 1.95s/it] 75%|███████▌ | 30/40 [00:58<00:19, 1.95s/it] 78%|███████▊ | 31/40 [01:00<00:17, 1.95s/it] 80%|████████ | 32/40 [01:02<00:15, 1.95s/it] 82%|████████▎ | 33/40 [01:04<00:13, 1.95s/it] 85%|████████▌ | 34/40 [01:06<00:11, 1.95s/it] 88%|████████▊ | 35/40 [01:08<00:09, 1.95s/it] 90%|█████████ | 36/40 [01:10<00:07, 1.94s/it] 92%|█████████▎| 37/40 [01:12<00:05, 1.94s/it] 95%|█████████▌| 38/40 [01:14<00:03, 1.94s/it] 98%|█████████▊| 39/40 [01:16<00:01, 1.94s/it] 100%|██████████| 40/40 [01:17<00:00, 1.64s/it] 100%|██████████| 40/40 [01:17<00:00, 1.94s/it] Decoding latents in cuda:0... done in 1.73s Move latents to cpu... done in 0.02s 0: 480x640 1 face, 162.5ms Speed: 2.9ms preprocess, 162.5ms inference, 29.5ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:14, 1.24it/s] 11%|█ | 2/19 [00:01<00:12, 1.37it/s] 16%|█▌ | 3/19 [00:02<00:11, 1.43it/s] 21%|██ | 4/19 [00:02<00:10, 1.46it/s] 26%|██▋ | 5/19 [00:03<00:09, 1.47it/s] 32%|███▏ | 6/19 [00:04<00:08, 1.48it/s] 37%|███▋ | 7/19 [00:04<00:08, 1.49it/s] 42%|████▏ | 8/19 [00:05<00:07, 1.50it/s] 47%|████▋ | 9/19 [00:06<00:06, 1.51it/s] 53%|█████▎ | 10/19 [00:06<00:05, 1.52it/s] 58%|█████▊ | 11/19 [00:07<00:05, 1.52it/s] 63%|██████▎ | 12/19 [00:08<00:04, 1.52it/s] 68%|██████▊ | 13/19 [00:08<00:03, 1.51it/s] 74%|███████▎ | 14/19 [00:09<00:03, 1.50it/s] 79%|███████▉ | 15/19 [00:10<00:02, 1.50it/s] 84%|████████▍ | 16/19 [00:10<00:01, 1.51it/s] 89%|████████▉ | 17/19 [00:11<00:01, 1.51it/s] 95%|█████████▍| 18/19 [00:12<00:00, 1.51it/s] 100%|██████████| 19/19 [00:12<00:00, 1.79it/s] 100%|██████████| 19/19 [00:12<00:00, 1.53it/s] Decoding latents in cuda:0... done in 0.57s Move latents to cpu... done in 0.0s 0: 480x640 1 face, 8.0ms Speed: 2.5ms preprocess, 8.0ms inference, 1.5ms postprocess per image at shape (1, 3, 480, 640) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:12, 1.48it/s] 11%|█ | 2/19 [00:01<00:11, 1.50it/s] 16%|█▌ | 3/19 [00:01<00:10, 1.51it/s] 21%|██ | 4/19 [00:02<00:09, 1.52it/s] 26%|██▋ | 5/19 [00:03<00:09, 1.52it/s] 32%|███▏ | 6/19 [00:03<00:08, 1.51it/s] 37%|███▋ | 7/19 [00:04<00:07, 1.50it/s] 42%|████▏ | 8/19 [00:05<00:07, 1.51it/s] 47%|████▋ | 9/19 [00:05<00:06, 1.51it/s] 53%|█████▎ | 10/19 [00:06<00:06, 1.49it/s] 58%|█████▊ | 11/19 [00:07<00:05, 1.50it/s] 63%|██████▎ | 12/19 [00:07<00:04, 1.50it/s] 68%|██████▊ | 13/19 [00:08<00:04, 1.50it/s] 74%|███████▎ | 14/19 [00:09<00:03, 1.49it/s] 79%|███████▉ | 15/19 [00:09<00:02, 1.49it/s] 84%|████████▍ | 16/19 [00:10<00:02, 1.48it/s] 89%|████████▉ | 17/19 [00:11<00:01, 1.49it/s] 95%|█████████▍| 18/19 [00:12<00:00, 1.49it/s] 100%|██████████| 19/19 [00:12<00:00, 1.76it/s] 100%|██████████| 19/19 [00:12<00:00, 1.54it/s] Decoding latents in cuda:0... done in 0.59s Move latents to cpu... done in 0.0s 0: 480x640 (no detections), 8.4ms Speed: 2.3ms preprocess, 8.4ms inference, 0.7ms postprocess per image at shape (1, 3, 480, 640) [-] ADetailer: nothing detected on image 3 with 1st settings. Uploading outputs... Finished.