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/310d34a598ef44d4ae22a2d65fa92d11/00000-4058090395.webp
https://files.tungsten.run/uploads/9373a176fc4645c9a539f0e45e346b7a/00001-4058090396.webp
https://files.tungsten.run/uploads/f2d810978e314afa9233e9277bc027d6/00002-4058090397.webp
This example was created by sparks
Finished in 200.5 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: cute 21-year-old German woman, standing outside a café, attractive face, smiling, blue streaks in hair, beautiful pale blue eyes, eyeliner, mascara, dark eyeshadow, neckless, (t-shirt that reads "Tungsten"), perfect skin, BREAK, professional photography, highest quality photo, dynamic lighting,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: anime, cartoon, watermark, logo, signature, fat, glossy skin, shiny skin, hands, lipstick, (bokeh), blurry, suntan, 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, 5.21s/it] 10%|█ | 4/40 [00:20<03:14, 5.42s/it] 12%|█▎ | 5/40 [00:26<03:13, 5.53s/it] 15%|█▌ | 6/40 [00:32<03:08, 5.54s/it] 18%|█▊ | 7/40 [00:37<03:06, 5.65s/it] 20%|██ | 8/40 [00:43<02:58, 5.58s/it] 22%|██▎ | 9/40 [00:48<02:52, 5.56s/it] 25%|██▌ | 10/40 [00:54<02:46, 5.54s/it] 28%|██▊ | 11/40 [00:59<02:40, 5.52s/it] 30%|███ | 12/40 [01:05<02:36, 5.59s/it] 32%|███▎ | 13/40 [01:11<02:30, 5.57s/it] 35%|███▌ | 14/40 [01:16<02:23, 5.51s/it] 38%|███▊ | 15/40 [01:22<02:18, 5.54s/it] 40%|████ | 16/40 [01:27<02:11, 5.46s/it] 42%|████▎ | 17/40 [01:33<02:06, 5.51s/it] 45%|████▌ | 18/40 [01:38<02:00, 5.49s/it] 48%|████▊ | 19/40 [01:44<01:55, 5.50s/it] 50%|█████ | 20/40 [01:49<01:48, 5.42s/it] 52%|█████▎ | 21/40 [01:53<01:38, 5.21s/it] 55%|█████▌ | 22/40 [01:58<01:28, 4.92s/it] 57%|█████▊ | 23/40 [02:03<01:25, 5.04s/it] 60%|██████ | 24/40 [02:09<01:23, 5.19s/it] 62%|██████▎ | 25/40 [02:13<01:14, 4.95s/it] 65%|██████▌ | 26/40 [02:18<01:09, 4.95s/it] 68%|██████▊ | 27/40 [02:23<01:06, 5.10s/it] 70%|███████ | 28/40 [02:28<01:00, 5.00s/it] 72%|███████▎ | 29/40 [02:33<00:55, 5.02s/it] 75%|███████▌ | 30/40 [02:38<00:50, 5.08s/it] 78%|███████▊ | 31/40 [02:43<00:43, 4.84s/it] 80%|████████ | 32/40 [02:47<00:36, 4.57s/it] 82%|████████▎ | 33/40 [02:51<00:31, 4.53s/it] 85%|████████▌ | 34/40 [02:55<00:26, 4.37s/it] 88%|████████▊ | 35/40 [02:59<00:21, 4.35s/it] 90%|█████████ | 36/40 [03:03<00:16, 4.18s/it] 92%|█████████▎| 37/40 [03:07<00:12, 4.19s/it] 95%|█████████▌| 38/40 [03:12<00:08, 4.23s/it] 98%|█████████▊| 39/40 [03:15<00:04, 4.01s/it] 100%|██████████| 40/40 [03:17<00:00, 3.19s/it] 100%|██████████| 40/40 [03:17<00:00, 4.93s/it] Decoding latents in cuda:0... done in 2.48s 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/310d34a598ef44d4ae22a2d65fa92d11/00000-4058090395.webp
https://files.tungsten.run/uploads/9373a176fc4645c9a539f0e45e346b7a/00001-4058090396.webp
https://files.tungsten.run/uploads/f2d810978e314afa9233e9277bc027d6/00002-4058090397.webp
This example was created by sparks
Finished in 200.5 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: cute 21-year-old German woman, standing outside a café, attractive face, smiling, blue streaks in hair, beautiful pale blue eyes, eyeliner, mascara, dark eyeshadow, neckless, (t-shirt that reads "Tungsten"), perfect skin, BREAK, professional photography, highest quality photo, dynamic lighting,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: anime, cartoon, watermark, logo, signature, fat, glossy skin, shiny skin, hands, lipstick, (bokeh), blurry, suntan, 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, 5.21s/it] 10%|█ | 4/40 [00:20<03:14, 5.42s/it] 12%|█▎ | 5/40 [00:26<03:13, 5.53s/it] 15%|█▌ | 6/40 [00:32<03:08, 5.54s/it] 18%|█▊ | 7/40 [00:37<03:06, 5.65s/it] 20%|██ | 8/40 [00:43<02:58, 5.58s/it] 22%|██▎ | 9/40 [00:48<02:52, 5.56s/it] 25%|██▌ | 10/40 [00:54<02:46, 5.54s/it] 28%|██▊ | 11/40 [00:59<02:40, 5.52s/it] 30%|███ | 12/40 [01:05<02:36, 5.59s/it] 32%|███▎ | 13/40 [01:11<02:30, 5.57s/it] 35%|███▌ | 14/40 [01:16<02:23, 5.51s/it] 38%|███▊ | 15/40 [01:22<02:18, 5.54s/it] 40%|████ | 16/40 [01:27<02:11, 5.46s/it] 42%|████▎ | 17/40 [01:33<02:06, 5.51s/it] 45%|████▌ | 18/40 [01:38<02:00, 5.49s/it] 48%|████▊ | 19/40 [01:44<01:55, 5.50s/it] 50%|█████ | 20/40 [01:49<01:48, 5.42s/it] 52%|█████▎ | 21/40 [01:53<01:38, 5.21s/it] 55%|█████▌ | 22/40 [01:58<01:28, 4.92s/it] 57%|█████▊ | 23/40 [02:03<01:25, 5.04s/it] 60%|██████ | 24/40 [02:09<01:23, 5.19s/it] 62%|██████▎ | 25/40 [02:13<01:14, 4.95s/it] 65%|██████▌ | 26/40 [02:18<01:09, 4.95s/it] 68%|██████▊ | 27/40 [02:23<01:06, 5.10s/it] 70%|███████ | 28/40 [02:28<01:00, 5.00s/it] 72%|███████▎ | 29/40 [02:33<00:55, 5.02s/it] 75%|███████▌ | 30/40 [02:38<00:50, 5.08s/it] 78%|███████▊ | 31/40 [02:43<00:43, 4.84s/it] 80%|████████ | 32/40 [02:47<00:36, 4.57s/it] 82%|████████▎ | 33/40 [02:51<00:31, 4.53s/it] 85%|████████▌ | 34/40 [02:55<00:26, 4.37s/it] 88%|████████▊ | 35/40 [02:59<00:21, 4.35s/it] 90%|█████████ | 36/40 [03:03<00:16, 4.18s/it] 92%|█████████▎| 37/40 [03:07<00:12, 4.19s/it] 95%|█████████▌| 38/40 [03:12<00:08, 4.23s/it] 98%|█████████▊| 39/40 [03:15<00:04, 4.01s/it] 100%|██████████| 40/40 [03:17<00:00, 3.19s/it] 100%|██████████| 40/40 [03:17<00:00, 4.93s/it] Decoding latents in cuda:0... done in 2.48s Move latents to cpu... done in 0.03s