tungsten-logo
Sign In
bbb-sdxl
bbb-sdxl

bbb-sdxl

23 stars
Version: v2.0
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/7ad86248456e4ca1aeccc9cc9fd5add9/00000-1041529673.webp
https://files.tungsten.run/uploads/46eee3dbd23b47d99cf9a6524f8f5181/00001-1041529674.webp
https://files.tungsten.run/uploads/75656e02e6ba4ba683077444b3a974ae/00002-1041529675.webp
This example was created by sparks
Finished in 51.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: photo of cute creature, female, big eyes, (freckles), autumn, english garden, cinematic photo flyweight, 35mm photograph, tilt shift, film, professional, 4k, highly detailed, [big breasts], [green eyes:0.2], <lora:add-detail-xl:1.0> Full negative prompt: illustration, bad anatomy, blurry, fuzzy, disfigured, tiling, deformed, mutated, out of frame, cloned, watermark, text, model shooting, nude 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:02<01:05, 2.72s/it] 8%|▊ | 2/25 [00:04<00:48, 2.09s/it] 12%|█▏ | 3/25 [00:06<00:41, 1.90s/it] 16%|█▌ | 4/25 [00:07<00:38, 1.81s/it] 20%|██ | 5/25 [00:09<00:35, 1.76s/it] 24%|██▍ | 6/25 [00:11<00:33, 1.74s/it] 28%|██▊ | 7/25 [00:12<00:31, 1.73s/it] 32%|███▏ | 8/25 [00:14<00:29, 1.72s/it] 36%|███▌ | 9/25 [00:16<00:27, 1.72s/it] 40%|████ | 10/25 [00:17<00:25, 1.71s/it] 44%|████▍ | 11/25 [00:19<00:24, 1.72s/it] 48%|████▊ | 12/25 [00:21<00:22, 1.72s/it] 52%|█████▏ | 13/25 [00:23<00:20, 1.72s/it] 56%|█████▌ | 14/25 [00:24<00:18, 1.72s/it] 60%|██████ | 15/25 [00:26<00:17, 1.72s/it] 64%|██████▍ | 16/25 [00:28<00:15, 1.72s/it] 68%|██████▊ | 17/25 [00:29<00:13, 1.72s/it] 72%|███████▏ | 18/25 [00:31<00:12, 1.72s/it] 76%|███████▌ | 19/25 [00:33<00:10, 1.71s/it] 80%|████████ | 20/25 [00:35<00:08, 1.71s/it] 84%|████████▍ | 21/25 [00:36<00:06, 1.71s/it] 88%|████████▊ | 22/25 [00:38<00:05, 1.70s/it] 92%|█████████▏| 23/25 [00:40<00:03, 1.70s/it] 96%|█████████▌| 24/25 [00:41<00:01, 1.69s/it] 100%|██████████| 25/25 [00:43<00:00, 1.68s/it] 100%|██████████| 25/25 [00:43<00:00, 1.74s/it] Decoding latents in cuda:0... done in 2.86s 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/7ad86248456e4ca1aeccc9cc9fd5add9/00000-1041529673.webp
https://files.tungsten.run/uploads/46eee3dbd23b47d99cf9a6524f8f5181/00001-1041529674.webp
https://files.tungsten.run/uploads/75656e02e6ba4ba683077444b3a974ae/00002-1041529675.webp
This example was created by sparks
Finished in 51.0 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: photo of cute creature, female, big eyes, (freckles), autumn, english garden, cinematic photo flyweight, 35mm photograph, tilt shift, film, professional, 4k, highly detailed, [big breasts], [green eyes:0.2], <lora:add-detail-xl:1.0> Full negative prompt: illustration, bad anatomy, blurry, fuzzy, disfigured, tiling, deformed, mutated, out of frame, cloned, watermark, text, model shooting, nude 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:02<01:05, 2.72s/it] 8%|▊ | 2/25 [00:04<00:48, 2.09s/it] 12%|█▏ | 3/25 [00:06<00:41, 1.90s/it] 16%|█▌ | 4/25 [00:07<00:38, 1.81s/it] 20%|██ | 5/25 [00:09<00:35, 1.76s/it] 24%|██▍ | 6/25 [00:11<00:33, 1.74s/it] 28%|██▊ | 7/25 [00:12<00:31, 1.73s/it] 32%|███▏ | 8/25 [00:14<00:29, 1.72s/it] 36%|███▌ | 9/25 [00:16<00:27, 1.72s/it] 40%|████ | 10/25 [00:17<00:25, 1.71s/it] 44%|████▍ | 11/25 [00:19<00:24, 1.72s/it] 48%|████▊ | 12/25 [00:21<00:22, 1.72s/it] 52%|█████▏ | 13/25 [00:23<00:20, 1.72s/it] 56%|█████▌ | 14/25 [00:24<00:18, 1.72s/it] 60%|██████ | 15/25 [00:26<00:17, 1.72s/it] 64%|██████▍ | 16/25 [00:28<00:15, 1.72s/it] 68%|██████▊ | 17/25 [00:29<00:13, 1.72s/it] 72%|███████▏ | 18/25 [00:31<00:12, 1.72s/it] 76%|███████▌ | 19/25 [00:33<00:10, 1.71s/it] 80%|████████ | 20/25 [00:35<00:08, 1.71s/it] 84%|████████▍ | 21/25 [00:36<00:06, 1.71s/it] 88%|████████▊ | 22/25 [00:38<00:05, 1.70s/it] 92%|█████████▏| 23/25 [00:40<00:03, 1.70s/it] 96%|█████████▌| 24/25 [00:41<00:01, 1.69s/it] 100%|██████████| 25/25 [00:43<00:00, 1.68s/it] 100%|██████████| 25/25 [00:43<00:00, 1.74s/it] Decoding latents in cuda:0... done in 2.86s Move latents to cpu... done in 0.04s Uploading outputs... Finished.