tungsten-logo
Sign In
Caravaggio with Interdiffusion XL
interdiffusion-xl:v3.0
evevalentine2017
evevalentine2017
·
Mar 30
175
Input
prompt
Specify things to see in the output
a Caravaggio masterpiece
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
-1
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2S a Karras
samping_steps
Number of denoising steps
20
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
sdxl_vae.safetensors
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.
false
Output
https://files.tungsten.run/uploads/5332125a5ca6437e9dca0f15f609ce9a/00000-2593723654.webp
https://files.tungsten.run/uploads/adeae906e57747af83bbc7d5c061e71d/00001-2593723655.webp
https://files.tungsten.run/uploads/7959e036dc2c4c9fb8f7a4cd92fd7729/00002-2593723656.webp
Finished in 103.7 seconds
Setting up the model... Preparing inputs... Processing... Using seed 2593723654 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a Caravaggio masterpiece Full negative prompt: 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:02<00:53, 2.83s/it] 10%|█ | 2/20 [00:05<00:51, 2.85s/it] 15%|█▌ | 3/20 [00:08<00:48, 2.85s/it] 20%|██ | 4/20 [00:11<00:45, 2.85s/it] 25%|██▌ | 5/20 [00:14<00:42, 2.85s/it] 30%|███ | 6/20 [00:17<00:39, 2.84s/it] 35%|███▌ | 7/20 [00:19<00:36, 2.84s/it] 40%|████ | 8/20 [00:22<00:33, 2.83s/it] 45%|████▌ | 9/20 [00:25<00:31, 2.82s/it] 50%|█████ | 10/20 [00:28<00:28, 2.82s/it] 55%|█████▌ | 11/20 [00:31<00:25, 2.82s/it] 60%|██████ | 12/20 [00:33<00:22, 2.81s/it] 65%|██████▌ | 13/20 [00:36<00:19, 2.80s/it] 70%|███████ | 14/20 [00:39<00:16, 2.78s/it] 75%|███████▌ | 15/20 [00:42<00:13, 2.77s/it] 80%|████████ | 16/20 [00:44<00:11, 2.77s/it] 85%|████████▌ | 17/20 [00:47<00:08, 2.77s/it] 90%|█████████ | 18/20 [00:50<00:05, 2.76s/it] 95%|█████████▌| 19/20 [00:53<00:02, 2.75s/it] 100%|██████████| 20/20 [00:54<00:00, 2.33s/it] 100%|██████████| 20/20 [00:54<00:00, 2.73s/it] Decoding latents in cuda:0... done in 2.41s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.8ms Speed: 3.4ms preprocess, 7.8ms inference, 34.6ms postprocess per image at shape (1, 3, 640, 640)
prompt
Specify things to see in the output
a Caravaggio masterpiece
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
3
width
Output image width
1024
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
-1
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2S a Karras
samping_steps
Number of denoising steps
20
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
1
vae
Select VAE
sdxl_vae.safetensors
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.
false
https://files.tungsten.run/uploads/5332125a5ca6437e9dca0f15f609ce9a/00000-2593723654.webp
https://files.tungsten.run/uploads/adeae906e57747af83bbc7d5c061e71d/00001-2593723655.webp
https://files.tungsten.run/uploads/7959e036dc2c4c9fb8f7a4cd92fd7729/00002-2593723656.webp
Finished in 103.7 seconds
Setting up the model... Preparing inputs... Processing... Using seed 2593723654 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a Caravaggio masterpiece Full negative prompt: 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:02<00:53, 2.83s/it] 10%|█ | 2/20 [00:05<00:51, 2.85s/it] 15%|█▌ | 3/20 [00:08<00:48, 2.85s/it] 20%|██ | 4/20 [00:11<00:45, 2.85s/it] 25%|██▌ | 5/20 [00:14<00:42, 2.85s/it] 30%|███ | 6/20 [00:17<00:39, 2.84s/it] 35%|███▌ | 7/20 [00:19<00:36, 2.84s/it] 40%|████ | 8/20 [00:22<00:33, 2.83s/it] 45%|████▌ | 9/20 [00:25<00:31, 2.82s/it] 50%|█████ | 10/20 [00:28<00:28, 2.82s/it] 55%|█████▌ | 11/20 [00:31<00:25, 2.82s/it] 60%|██████ | 12/20 [00:33<00:22, 2.81s/it] 65%|██████▌ | 13/20 [00:36<00:19, 2.80s/it] 70%|███████ | 14/20 [00:39<00:16, 2.78s/it] 75%|███████▌ | 15/20 [00:42<00:13, 2.77s/it] 80%|████████ | 16/20 [00:44<00:11, 2.77s/it] 85%|████████▌ | 17/20 [00:47<00:08, 2.77s/it] 90%|█████████ | 18/20 [00:50<00:05, 2.76s/it] 95%|█████████▌| 19/20 [00:53<00:02, 2.75s/it] 100%|██████████| 20/20 [00:54<00:00, 2.33s/it] 100%|██████████| 20/20 [00:54<00:00, 2.73s/it] Decoding latents in cuda:0... done in 2.41s Move latents to cpu... done in 0.03s 0: 640x640 1 face, 7.8ms Speed: 3.4ms preprocess, 7.8ms inference, 34.6ms postprocess per image at shape (1, 3, 640, 640)