tungsten-logo
Sign In
Graffiti with BI XL
beyondimaginationxl:v0.005
sparks
sparks
·
Feb 29
331
Input
prompt
Specify things to see in the output
<lora:EnvyBetterHiresFixXL01:0.5>, graffiti on a brick wall, a boy with a balloon, Banksy style, masterpiece
negative_prompt
Specify things to not see in the output
(logo:2), (signature:2), (artist name:2), (author name:2), (watermark:2), ugly, bad quality
num_outputs
Number of output images
3
width
Output image width
960
height
Output image height
1280
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
1
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.
3229152439
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++ 3M SDE Karras
samping_steps
Number of denoising steps
50
cfg_scale
Scale for classifier-free guidance
5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
None
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
EnvyBetterHiresFixXL01.safetensors
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/1b4d4db61bce45e6bd016fb5c47591ab/00000-3229152439.webp
https://files.tungsten.run/uploads/b7df9de387104b38a79de67262e476ff/00001-3229152440.webp
https://files.tungsten.run/uploads/e75387df5b1748bdb3cddd34f9c5123a/00002-3229152441.webp
Finished in 163.2 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: <lora:EnvyBetterHiresFixXL01:0.5>, graffiti on a brick wall, a boy with a balloon, Banksy style, masterpiece, <lora:add-detail-xl:1.0> Full negative prompt: (logo:2), (signature:2), (artist name:2), (author name:2), (watermark:2), ugly, bad quality 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:04<03:19, 4.08s/it] 4%|▍ | 2/50 [00:07<02:58, 3.71s/it] 6%|▌ | 3/50 [00:10<02:43, 3.49s/it] 8%|▊ | 4/50 [00:13<02:34, 3.36s/it] 10%|█ | 5/50 [00:17<02:27, 3.27s/it] 12%|█▏ | 6/50 [00:20<02:27, 3.34s/it] 14%|█▍ | 7/50 [00:23<02:20, 3.28s/it] 16%|█▌ | 8/50 [00:27<02:19, 3.31s/it] 18%|█▊ | 9/50 [00:30<02:14, 3.27s/it] 20%|██ | 10/50 [00:33<02:09, 3.25s/it] 22%|██▏ | 11/50 [00:36<02:03, 3.17s/it] 24%|██▍ | 12/50 [00:39<02:02, 3.21s/it] 26%|██▌ | 13/50 [00:42<01:58, 3.19s/it] 28%|██▊ | 14/50 [00:46<01:55, 3.22s/it] 30%|███ | 15/50 [00:49<01:51, 3.18s/it] 32%|███▏ | 16/50 [00:52<01:47, 3.17s/it] 34%|███▍ | 17/50 [00:55<01:45, 3.19s/it] 36%|███▌ | 18/50 [00:58<01:41, 3.17s/it] 38%|███▊ | 19/50 [01:01<01:37, 3.16s/it] 40%|████ | 20/50 [01:05<01:37, 3.26s/it] 42%|████▏ | 21/50 [01:08<01:32, 3.20s/it] 44%|████▍ | 22/50 [01:11<01:29, 3.20s/it] 46%|████▌ | 23/50 [01:14<01:26, 3.19s/it] 48%|████▊ | 24/50 [01:17<01:21, 3.14s/it] 50%|█████ | 25/50 [01:20<01:18, 3.15s/it] 52%|█████▏ | 26/50 [01:25<01:24, 3.51s/it] 54%|█████▍ | 27/50 [01:28<01:17, 3.38s/it] 56%|█████▌ | 28/50 [01:31<01:13, 3.32s/it] 58%|█████▊ | 29/50 [01:34<01:09, 3.32s/it] 60%|██████ | 30/50 [01:38<01:06, 3.33s/it] 62%|██████▏ | 31/50 [01:41<01:01, 3.24s/it] 64%|██████▍ | 32/50 [01:44<00:57, 3.21s/it] 66%|██████▌ | 33/50 [01:47<00:53, 3.17s/it] 68%|██████▊ | 34/50 [01:50<00:49, 3.12s/it] 70%|███████ | 35/50 [01:53<00:45, 3.06s/it] 72%|███████▏ | 36/50 [01:56<00:42, 3.03s/it] 74%|███████▍ | 37/50 [01:59<00:38, 2.96s/it] 76%|███████▌ | 38/50 [02:02<00:36, 3.06s/it] 78%|███████▊ | 39/50 [02:05<00:33, 3.00s/it] 80%|████████ | 40/50 [02:08<00:29, 2.91s/it] 82%|████████▏ | 41/50 [02:11<00:26, 2.96s/it] 84%|████████▍ | 42/50 [02:13<00:22, 2.87s/it] 86%|████████▌ | 43/50 [02:16<00:20, 2.90s/it] 88%|████████▊ | 44/50 [02:19<00:17, 2.88s/it] 90%|█████████ | 45/50 [02:22<00:14, 2.87s/it] 92%|█████████▏| 46/50 [02:25<00:11, 2.93s/it] 94%|█████████▍| 47/50 [02:28<00:08, 2.82s/it] 96%|█████████▌| 48/50 [02:31<00:05, 2.88s/it] 98%|█████████▊| 49/50 [02:32<00:02, 2.56s/it] 100%|██████████| 50/50 [02:34<00:00, 2.25s/it] 100%|██████████| 50/50 [02:34<00:00, 3.09s/it] Decoding latents in cuda:0... done in 2.77s Move latents to cpu... done in 0.03s Uploading outputs... Finished.
prompt
Specify things to see in the output
<lora:EnvyBetterHiresFixXL01:0.5>, graffiti on a brick wall, a boy with a balloon, Banksy style, masterpiece
negative_prompt
Specify things to not see in the output
(logo:2), (signature:2), (artist name:2), (author name:2), (watermark:2), ugly, bad quality
num_outputs
Number of output images
3
width
Output image width
960
height
Output image height
1280
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
1
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.
3229152439
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++ 3M SDE Karras
samping_steps
Number of denoising steps
50
cfg_scale
Scale for classifier-free guidance
5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
None
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
EnvyBetterHiresFixXL01.safetensors
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/1b4d4db61bce45e6bd016fb5c47591ab/00000-3229152439.webp
https://files.tungsten.run/uploads/b7df9de387104b38a79de67262e476ff/00001-3229152440.webp
https://files.tungsten.run/uploads/e75387df5b1748bdb3cddd34f9c5123a/00002-3229152441.webp
Finished in 163.2 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: <lora:EnvyBetterHiresFixXL01:0.5>, graffiti on a brick wall, a boy with a balloon, Banksy style, masterpiece, <lora:add-detail-xl:1.0> Full negative prompt: (logo:2), (signature:2), (artist name:2), (author name:2), (watermark:2), ugly, bad quality 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:04<03:19, 4.08s/it] 4%|▍ | 2/50 [00:07<02:58, 3.71s/it] 6%|▌ | 3/50 [00:10<02:43, 3.49s/it] 8%|▊ | 4/50 [00:13<02:34, 3.36s/it] 10%|█ | 5/50 [00:17<02:27, 3.27s/it] 12%|█▏ | 6/50 [00:20<02:27, 3.34s/it] 14%|█▍ | 7/50 [00:23<02:20, 3.28s/it] 16%|█▌ | 8/50 [00:27<02:19, 3.31s/it] 18%|█▊ | 9/50 [00:30<02:14, 3.27s/it] 20%|██ | 10/50 [00:33<02:09, 3.25s/it] 22%|██▏ | 11/50 [00:36<02:03, 3.17s/it] 24%|██▍ | 12/50 [00:39<02:02, 3.21s/it] 26%|██▌ | 13/50 [00:42<01:58, 3.19s/it] 28%|██▊ | 14/50 [00:46<01:55, 3.22s/it] 30%|███ | 15/50 [00:49<01:51, 3.18s/it] 32%|███▏ | 16/50 [00:52<01:47, 3.17s/it] 34%|███▍ | 17/50 [00:55<01:45, 3.19s/it] 36%|███▌ | 18/50 [00:58<01:41, 3.17s/it] 38%|███▊ | 19/50 [01:01<01:37, 3.16s/it] 40%|████ | 20/50 [01:05<01:37, 3.26s/it] 42%|████▏ | 21/50 [01:08<01:32, 3.20s/it] 44%|████▍ | 22/50 [01:11<01:29, 3.20s/it] 46%|████▌ | 23/50 [01:14<01:26, 3.19s/it] 48%|████▊ | 24/50 [01:17<01:21, 3.14s/it] 50%|█████ | 25/50 [01:20<01:18, 3.15s/it] 52%|█████▏ | 26/50 [01:25<01:24, 3.51s/it] 54%|█████▍ | 27/50 [01:28<01:17, 3.38s/it] 56%|█████▌ | 28/50 [01:31<01:13, 3.32s/it] 58%|█████▊ | 29/50 [01:34<01:09, 3.32s/it] 60%|██████ | 30/50 [01:38<01:06, 3.33s/it] 62%|██████▏ | 31/50 [01:41<01:01, 3.24s/it] 64%|██████▍ | 32/50 [01:44<00:57, 3.21s/it] 66%|██████▌ | 33/50 [01:47<00:53, 3.17s/it] 68%|██████▊ | 34/50 [01:50<00:49, 3.12s/it] 70%|███████ | 35/50 [01:53<00:45, 3.06s/it] 72%|███████▏ | 36/50 [01:56<00:42, 3.03s/it] 74%|███████▍ | 37/50 [01:59<00:38, 2.96s/it] 76%|███████▌ | 38/50 [02:02<00:36, 3.06s/it] 78%|███████▊ | 39/50 [02:05<00:33, 3.00s/it] 80%|████████ | 40/50 [02:08<00:29, 2.91s/it] 82%|████████▏ | 41/50 [02:11<00:26, 2.96s/it] 84%|████████▍ | 42/50 [02:13<00:22, 2.87s/it] 86%|████████▌ | 43/50 [02:16<00:20, 2.90s/it] 88%|████████▊ | 44/50 [02:19<00:17, 2.88s/it] 90%|█████████ | 45/50 [02:22<00:14, 2.87s/it] 92%|█████████▏| 46/50 [02:25<00:11, 2.93s/it] 94%|█████████▍| 47/50 [02:28<00:08, 2.82s/it] 96%|█████████▌| 48/50 [02:31<00:05, 2.88s/it] 98%|█████████▊| 49/50 [02:32<00:02, 2.56s/it] 100%|██████████| 50/50 [02:34<00:00, 2.25s/it] 100%|██████████| 50/50 [02:34<00:00, 3.09s/it] Decoding latents in cuda:0... done in 2.77s Move latents to cpu... done in 0.03s Uploading outputs... Finished.