tungsten-logo
Sign In
opendalle
opendalle

opendalle

13 stars
Version: v1.1
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/3558116e3f384a0c89ec21f57fe7b63a/00000-2229996417.webp
https://files.tungsten.run/uploads/f0d5eb304ced41b4ba89f446308a884f/00001-2229996418.webp
https://files.tungsten.run/uploads/6be540e5062c46b995ed39bcab791c46/00002-2229996419.webp
This example was created by sparks
Finished in 128.8 seconds
Setting up the model... Preparing inputs... Processing... Using seed 2229996417 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: A tactical Navy Seal (Pepe the Frog:1.2) emerging from water in the middle of the night, equipped with night vision goggles and armed, with a dark, stealthy background, capturing the essence of a covert military operation. The scene is wide, showcasing the vastness of the night sea and sky, enhancing the atmosphere of secrecy and danger, pepe_frog, <lora:EnvyBetterHiresFixXL01:0.4>, <lora:add-detail-xl:1.0> Full negative prompt: NSFW, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:04<02:21, 4.17s/it] 6%|▌ | 2/35 [00:07<02:04, 3.77s/it] 9%|▊ | 3/35 [00:11<01:56, 3.64s/it] 11%|█▏ | 4/35 [00:14<01:52, 3.63s/it] 14%|█▍ | 5/35 [00:18<01:48, 3.61s/it] 17%|█▋ | 6/35 [00:22<01:47, 3.71s/it] 20%|██ | 7/35 [00:25<01:43, 3.69s/it] 23%|██▎ | 8/35 [00:29<01:38, 3.66s/it] 26%|██▌ | 9/35 [00:33<01:34, 3.65s/it] 29%|██▊ | 10/35 [00:36<01:28, 3.55s/it] 31%|███▏ | 11/35 [00:39<01:24, 3.54s/it] 34%|███▍ | 12/35 [00:43<01:21, 3.56s/it] 37%|███▋ | 13/35 [00:47<01:18, 3.57s/it] 40%|████ | 14/35 [00:50<01:16, 3.62s/it] 43%|████▎ | 15/35 [00:55<01:16, 3.82s/it] 46%|████▌ | 16/35 [00:59<01:17, 4.06s/it] 49%|████▊ | 17/35 [01:03<01:10, 3.93s/it] 51%|█████▏ | 18/35 [01:06<01:02, 3.71s/it] 54%|█████▍ | 19/35 [01:10<00:58, 3.65s/it] 57%|█████▋ | 20/35 [01:13<00:54, 3.66s/it] 60%|██████ | 21/35 [01:17<00:50, 3.57s/it] 63%|██████▎ | 22/35 [01:19<00:43, 3.32s/it] 66%|██████▌ | 23/35 [01:22<00:38, 3.21s/it] 69%|██████▊ | 24/35 [01:25<00:35, 3.19s/it] 71%|███████▏ | 25/35 [01:29<00:32, 3.29s/it] 74%|███████▍ | 26/35 [01:33<00:30, 3.38s/it] 77%|███████▋ | 27/35 [01:36<00:26, 3.36s/it] 80%|████████ | 28/35 [01:39<00:23, 3.31s/it] 83%|████████▎ | 29/35 [01:42<00:19, 3.23s/it] 86%|████████▌ | 30/35 [01:45<00:15, 3.19s/it] 89%|████████▊ | 31/35 [01:49<00:12, 3.22s/it] 91%|█████████▏| 32/35 [01:52<00:09, 3.18s/it] 94%|█████████▍| 33/35 [01:55<00:06, 3.23s/it] 97%|█████████▋| 34/35 [01:57<00:02, 2.87s/it] 100%|██████████| 35/35 [01:59<00:00, 2.53s/it] 100%|██████████| 35/35 [01:59<00:00, 3.41s/it] Decoding latents in cuda:0... done in 3.15s Move latents to cpu... done in 0.04s 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/3558116e3f384a0c89ec21f57fe7b63a/00000-2229996417.webp
https://files.tungsten.run/uploads/f0d5eb304ced41b4ba89f446308a884f/00001-2229996418.webp
https://files.tungsten.run/uploads/6be540e5062c46b995ed39bcab791c46/00002-2229996419.webp
This example was created by sparks
Finished in 128.8 seconds
Setting up the model... Preparing inputs... Processing... Using seed 2229996417 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: A tactical Navy Seal (Pepe the Frog:1.2) emerging from water in the middle of the night, equipped with night vision goggles and armed, with a dark, stealthy background, capturing the essence of a covert military operation. The scene is wide, showcasing the vastness of the night sea and sky, enhancing the atmosphere of secrecy and danger, pepe_frog, <lora:EnvyBetterHiresFixXL01:0.4>, <lora:add-detail-xl:1.0> Full negative prompt: NSFW, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:04<02:21, 4.17s/it] 6%|▌ | 2/35 [00:07<02:04, 3.77s/it] 9%|▊ | 3/35 [00:11<01:56, 3.64s/it] 11%|█▏ | 4/35 [00:14<01:52, 3.63s/it] 14%|█▍ | 5/35 [00:18<01:48, 3.61s/it] 17%|█▋ | 6/35 [00:22<01:47, 3.71s/it] 20%|██ | 7/35 [00:25<01:43, 3.69s/it] 23%|██▎ | 8/35 [00:29<01:38, 3.66s/it] 26%|██▌ | 9/35 [00:33<01:34, 3.65s/it] 29%|██▊ | 10/35 [00:36<01:28, 3.55s/it] 31%|███▏ | 11/35 [00:39<01:24, 3.54s/it] 34%|███▍ | 12/35 [00:43<01:21, 3.56s/it] 37%|███▋ | 13/35 [00:47<01:18, 3.57s/it] 40%|████ | 14/35 [00:50<01:16, 3.62s/it] 43%|████▎ | 15/35 [00:55<01:16, 3.82s/it] 46%|████▌ | 16/35 [00:59<01:17, 4.06s/it] 49%|████▊ | 17/35 [01:03<01:10, 3.93s/it] 51%|█████▏ | 18/35 [01:06<01:02, 3.71s/it] 54%|█████▍ | 19/35 [01:10<00:58, 3.65s/it] 57%|█████▋ | 20/35 [01:13<00:54, 3.66s/it] 60%|██████ | 21/35 [01:17<00:50, 3.57s/it] 63%|██████▎ | 22/35 [01:19<00:43, 3.32s/it] 66%|██████▌ | 23/35 [01:22<00:38, 3.21s/it] 69%|██████▊ | 24/35 [01:25<00:35, 3.19s/it] 71%|███████▏ | 25/35 [01:29<00:32, 3.29s/it] 74%|███████▍ | 26/35 [01:33<00:30, 3.38s/it] 77%|███████▋ | 27/35 [01:36<00:26, 3.36s/it] 80%|████████ | 28/35 [01:39<00:23, 3.31s/it] 83%|████████▎ | 29/35 [01:42<00:19, 3.23s/it] 86%|████████▌ | 30/35 [01:45<00:15, 3.19s/it] 89%|████████▊ | 31/35 [01:49<00:12, 3.22s/it] 91%|█████████▏| 32/35 [01:52<00:09, 3.18s/it] 94%|█████████▍| 33/35 [01:55<00:06, 3.23s/it] 97%|█████████▋| 34/35 [01:57<00:02, 2.87s/it] 100%|██████████| 35/35 [01:59<00:00, 2.53s/it] 100%|██████████| 35/35 [01:59<00:00, 3.41s/it] Decoding latents in cuda:0... done in 3.15s Move latents to cpu... done in 0.04s Uploading outputs... Finished.