tungsten-logo
Sign In
ArtFusion XL Real
ArtFusion XL Real

ArtFusion XL Real

23 stars
Version: v1.5Lightning
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
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/9ac7c5ae2fbc454b9c9e90905c6e1b6a/00000-4271941379.webp
https://files.tungsten.run/uploads/91f79cd50dc44a78a734fb68b8b7507c/00001-4271941380.webp
https://files.tungsten.run/uploads/55d02f70f54644ecbe295520e18b5893/00002-4271941381.webp
This example was created by sparks
Finished in 197.2 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: attractive 18-year-old American woman walking on the Boardwalk at Ocean City, cute, short blond hair, realistic skin, happy expression, full body view, short shorts, midriff, large breasts, cropped t-shirt, light blue eyes, eyeliner, mascara, sexy ass, summer, beach, BREAK professional photography, highest quality, dynamic lighting, summer, crowded boardwalk, store fronts, pizza, arcade,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: ugly, fat, anime, cartoon, watermark, logo, signature, blurry, glossy skin, shiny skin, lipstick, bokeh, hands, muscular, muscles, NSFW, 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:04<02:40, 4.11s/it] 5%|▌ | 2/40 [00:09<03:00, 4.76s/it] 8%|▊ | 3/40 [00:15<03:12, 5.19s/it] 10%|█ | 4/40 [00:20<03:14, 5.40s/it] 12%|█▎ | 5/40 [00:26<03:12, 5.50s/it] 15%|█▌ | 6/40 [00:31<03:06, 5.50s/it] 18%|█▊ | 7/40 [00:37<03:05, 5.61s/it] 20%|██ | 8/40 [00:43<02:57, 5.55s/it] 22%|██▎ | 9/40 [00:48<02:51, 5.52s/it] 25%|██▌ | 10/40 [00:54<02:44, 5.48s/it] 28%|██▊ | 11/40 [00:59<02:37, 5.44s/it] 30%|███ | 12/40 [01:05<02:33, 5.50s/it] 32%|███▎ | 13/40 [01:10<02:27, 5.47s/it] 35%|███▌ | 14/40 [01:15<02:20, 5.41s/it] 38%|███▊ | 15/40 [01:21<02:16, 5.45s/it] 40%|████ | 16/40 [01:26<02:09, 5.39s/it] 42%|████▎ | 17/40 [01:32<02:05, 5.45s/it] 45%|████▌ | 18/40 [01:37<01:59, 5.44s/it] 48%|████▊ | 19/40 [01:42<01:54, 5.45s/it] 50%|█████ | 20/40 [01:48<01:47, 5.37s/it] 52%|█████▎ | 21/40 [01:52<01:37, 5.15s/it] 55%|█████▌ | 22/40 [01:56<01:27, 4.86s/it] 57%|█████▊ | 23/40 [02:02<01:24, 4.97s/it] 60%|██████ | 24/40 [02:07<01:21, 5.12s/it] 62%|██████▎ | 25/40 [02:11<01:12, 4.86s/it] 65%|██████▌ | 26/40 [02:16<01:07, 4.85s/it] 68%|██████▊ | 27/40 [02:21<01:03, 4.91s/it] 70%|███████ | 28/40 [02:26<00:57, 4.78s/it] 72%|███████▎ | 29/40 [02:31<00:53, 4.82s/it] 75%|███████▌ | 30/40 [02:36<00:49, 4.91s/it] 78%|███████▊ | 31/40 [02:40<00:42, 4.68s/it] 80%|████████ | 32/40 [02:44<00:35, 4.41s/it] 82%|████████▎ | 33/40 [02:48<00:30, 4.39s/it] 85%|████████▌ | 34/40 [02:52<00:25, 4.24s/it] 88%|████████▊ | 35/40 [02:56<00:21, 4.25s/it] 90%|█████████ | 36/40 [03:00<00:16, 4.11s/it] 92%|█████████▎| 37/40 [03:04<00:12, 4.15s/it] 95%|█████████▌| 38/40 [03:08<00:08, 4.14s/it] 98%|█████████▊| 39/40 [03:12<00:03, 3.96s/it] 100%|██████████| 40/40 [03:13<00:00, 3.16s/it] 100%|██████████| 40/40 [03:13<00:00, 4.84s/it] Decoding latents in cuda:0... done in 2.52s Move latents to cpu... done in 0.03s
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
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/9ac7c5ae2fbc454b9c9e90905c6e1b6a/00000-4271941379.webp
https://files.tungsten.run/uploads/91f79cd50dc44a78a734fb68b8b7507c/00001-4271941380.webp
https://files.tungsten.run/uploads/55d02f70f54644ecbe295520e18b5893/00002-4271941381.webp
This example was created by sparks
Finished in 197.2 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: attractive 18-year-old American woman walking on the Boardwalk at Ocean City, cute, short blond hair, realistic skin, happy expression, full body view, short shorts, midriff, large breasts, cropped t-shirt, light blue eyes, eyeliner, mascara, sexy ass, summer, beach, BREAK professional photography, highest quality, dynamic lighting, summer, crowded boardwalk, store fronts, pizza, arcade,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: ugly, fat, anime, cartoon, watermark, logo, signature, blurry, glossy skin, shiny skin, lipstick, bokeh, hands, muscular, muscles, NSFW, 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:04<02:40, 4.11s/it] 5%|▌ | 2/40 [00:09<03:00, 4.76s/it] 8%|▊ | 3/40 [00:15<03:12, 5.19s/it] 10%|█ | 4/40 [00:20<03:14, 5.40s/it] 12%|█▎ | 5/40 [00:26<03:12, 5.50s/it] 15%|█▌ | 6/40 [00:31<03:06, 5.50s/it] 18%|█▊ | 7/40 [00:37<03:05, 5.61s/it] 20%|██ | 8/40 [00:43<02:57, 5.55s/it] 22%|██▎ | 9/40 [00:48<02:51, 5.52s/it] 25%|██▌ | 10/40 [00:54<02:44, 5.48s/it] 28%|██▊ | 11/40 [00:59<02:37, 5.44s/it] 30%|███ | 12/40 [01:05<02:33, 5.50s/it] 32%|███▎ | 13/40 [01:10<02:27, 5.47s/it] 35%|███▌ | 14/40 [01:15<02:20, 5.41s/it] 38%|███▊ | 15/40 [01:21<02:16, 5.45s/it] 40%|████ | 16/40 [01:26<02:09, 5.39s/it] 42%|████▎ | 17/40 [01:32<02:05, 5.45s/it] 45%|████▌ | 18/40 [01:37<01:59, 5.44s/it] 48%|████▊ | 19/40 [01:42<01:54, 5.45s/it] 50%|█████ | 20/40 [01:48<01:47, 5.37s/it] 52%|█████▎ | 21/40 [01:52<01:37, 5.15s/it] 55%|█████▌ | 22/40 [01:56<01:27, 4.86s/it] 57%|█████▊ | 23/40 [02:02<01:24, 4.97s/it] 60%|██████ | 24/40 [02:07<01:21, 5.12s/it] 62%|██████▎ | 25/40 [02:11<01:12, 4.86s/it] 65%|██████▌ | 26/40 [02:16<01:07, 4.85s/it] 68%|██████▊ | 27/40 [02:21<01:03, 4.91s/it] 70%|███████ | 28/40 [02:26<00:57, 4.78s/it] 72%|███████▎ | 29/40 [02:31<00:53, 4.82s/it] 75%|███████▌ | 30/40 [02:36<00:49, 4.91s/it] 78%|███████▊ | 31/40 [02:40<00:42, 4.68s/it] 80%|████████ | 32/40 [02:44<00:35, 4.41s/it] 82%|████████▎ | 33/40 [02:48<00:30, 4.39s/it] 85%|████████▌ | 34/40 [02:52<00:25, 4.24s/it] 88%|████████▊ | 35/40 [02:56<00:21, 4.25s/it] 90%|█████████ | 36/40 [03:00<00:16, 4.11s/it] 92%|█████████▎| 37/40 [03:04<00:12, 4.15s/it] 95%|█████████▌| 38/40 [03:08<00:08, 4.14s/it] 98%|█████████▊| 39/40 [03:12<00:03, 3.96s/it] 100%|██████████| 40/40 [03:13<00:00, 3.16s/it] 100%|██████████| 40/40 [03:13<00:00, 4.84s/it] Decoding latents in cuda:0... done in 2.52s Move latents to cpu... done in 0.03s