tungsten-logo
Sign In
Xi
Xi

Xi

5 stars
Version: v1.0
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/6d9de1096d7944edbe70d8ecda0039c5/00000-1855557198.webp
https://files.tungsten.run/uploads/27630a6a5b4a4dbdbfc27f951b2e2c59/00001-1855557199.webp
https://files.tungsten.run/uploads/1a0fda407f2f472f9bfb87df8ad1564f/00002-1855557200.webp
This example was created by sparks
Finished in 125.5 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: it's a professional photo of a woman, sexualization,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: jpeg artifacts, low quality, blurred, noisy, bad anatomy, bad hands, three hands, three legs, bad arms, missing arms, missing fingers, extra fingers, ugly fingers, long fingers, BW 0%| | 0/72 [00:00<?, ?it/s] 1%|▏ | 1/72 [00:02<03:24, 2.89s/it] 3%|▎ | 2/72 [00:04<02:26, 2.09s/it] 4%|▍ | 3/72 [00:05<02:06, 1.84s/it] 6%|▌ | 4/72 [00:07<01:57, 1.73s/it] 7%|▋ | 5/72 [00:09<01:51, 1.67s/it] 8%|▊ | 6/72 [00:10<01:47, 1.63s/it] 10%|▉ | 7/72 [00:12<01:44, 1.61s/it] 11%|█ | 8/72 [00:13<01:42, 1.60s/it] 12%|█▎ | 9/72 [00:15<01:40, 1.59s/it] 14%|█▍ | 10/72 [00:16<01:38, 1.59s/it] 15%|█▌ | 11/72 [00:18<01:36, 1.59s/it] 17%|█▋ | 12/72 [00:20<01:35, 1.58s/it] 18%|█▊ | 13/72 [00:21<01:33, 1.59s/it] 19%|█▉ | 14/72 [00:23<01:32, 1.59s/it] 21%|██ | 15/72 [00:24<01:30, 1.59s/it] 22%|██▏ | 16/72 [00:26<01:29, 1.59s/it] 24%|██▎ | 17/72 [00:28<01:27, 1.60s/it] 25%|██▌ | 18/72 [00:29<01:26, 1.60s/it] 26%|██▋ | 19/72 [00:31<01:24, 1.60s/it] 28%|██▊ | 20/72 [00:32<01:23, 1.61s/it] 29%|██▉ | 21/72 [00:34<01:22, 1.61s/it] 31%|███ | 22/72 [00:36<01:20, 1.61s/it] 32%|███▏ | 23/72 [00:37<01:19, 1.61s/it] 33%|███▎ | 24/72 [00:39<01:17, 1.62s/it] 35%|███▍ | 25/72 [00:41<01:16, 1.62s/it] 36%|███▌ | 26/72 [00:42<01:14, 1.62s/it] 38%|███▊ | 27/72 [00:44<01:13, 1.63s/it] 39%|███▉ | 28/72 [00:45<01:11, 1.63s/it] 40%|████ | 29/72 [00:47<01:10, 1.63s/it] 42%|████▏ | 30/72 [00:49<01:08, 1.63s/it] 43%|████▎ | 31/72 [00:50<01:06, 1.62s/it] 44%|████▍ | 32/72 [00:52<01:04, 1.62s/it] 46%|████▌ | 33/72 [00:54<01:03, 1.62s/it] 47%|████▋ | 34/72 [00:55<01:01, 1.62s/it] 49%|████▊ | 35/72 [00:57<00:59, 1.61s/it] 50%|█████ | 36/72 [00:58<00:58, 1.61s/it] 51%|█████▏ | 37/72 [01:00<00:56, 1.61s/it] 53%|█████▎ | 38/72 [01:02<00:54, 1.61s/it] 54%|█████▍ | 39/72 [01:03<00:53, 1.61s/it] 56%|█████▌ | 40/72 [01:05<00:51, 1.61s/it] 57%|█████▋ | 41/72 [01:06<00:49, 1.60s/it] 58%|█████▊ | 42/72 [01:08<00:48, 1.60s/it] 60%|█████▉ | 43/72 [01:10<00:46, 1.60s/it] 61%|██████ | 44/72 [01:11<00:44, 1.60s/it] 62%|██████▎ | 45/72 [01:13<00:43, 1.59s/it] 64%|██████▍ | 46/72 [01:14<00:41, 1.59s/it] 65%|██████▌ | 47/72 [01:16<00:39, 1.59s/it] 67%|██████▋ | 48/72 [01:17<00:38, 1.59s/it] 68%|██████▊ | 49/72 [01:19<00:36, 1.59s/it] 69%|██████▉ | 50/72 [01:21<00:34, 1.59s/it] 71%|███████ | 51/72 [01:22<00:33, 1.59s/it] 72%|███████▏ | 52/72 [01:24<00:31, 1.58s/it] 74%|███████▎ | 53/72 [01:25<00:30, 1.58s/it] 75%|███████▌ | 54/72 [01:27<00:28, 1.59s/it] 76%|███████▋ | 55/72 [01:29<00:26, 1.59s/it] 78%|███████▊ | 56/72 [01:30<00:25, 1.59s/it] 79%|███████▉ | 57/72 [01:32<00:23, 1.59s/it] 81%|████████ | 58/72 [01:33<00:22, 1.59s/it] 82%|████████▏ | 59/72 [01:35<00:20, 1.59s/it] 83%|████████▎ | 60/72 [01:37<00:19, 1.59s/it] 85%|████████▍ | 61/72 [01:38<00:17, 1.59s/it] 86%|████████▌ | 62/72 [01:40<00:15, 1.60s/it] 88%|████████▊ | 63/72 [01:41<00:14, 1.60s/it] 89%|████████▉ | 64/72 [01:43<00:12, 1.60s/it] 90%|█████████ | 65/72 [01:45<00:11, 1.60s/it] 92%|█████████▏| 66/72 [01:46<00:09, 1.61s/it] 93%|█████████▎| 67/72 [01:48<00:08, 1.61s/it] 94%|█████████▍| 68/72 [01:49<00:06, 1.61s/it] 96%|█████████▌| 69/72 [01:51<00:04, 1.61s/it] 97%|█████████▋| 70/72 [01:53<00:03, 1.62s/it] 99%|█████████▊| 71/72 [01:54<00:01, 1.62s/it] 100%|██████████| 72/72 [01:56<00:00, 1.62s/it] 100%|██████████| 72/72 [01:56<00:00, 1.62s/it] Decoding latents in cuda:0... done in 2.89s Move latents to cpu... done in 0.06s
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/6d9de1096d7944edbe70d8ecda0039c5/00000-1855557198.webp
https://files.tungsten.run/uploads/27630a6a5b4a4dbdbfc27f951b2e2c59/00001-1855557199.webp
https://files.tungsten.run/uploads/1a0fda407f2f472f9bfb87df8ad1564f/00002-1855557200.webp
This example was created by sparks
Finished in 125.5 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: it's a professional photo of a woman, sexualization,, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: jpeg artifacts, low quality, blurred, noisy, bad anatomy, bad hands, three hands, three legs, bad arms, missing arms, missing fingers, extra fingers, ugly fingers, long fingers, BW 0%| | 0/72 [00:00<?, ?it/s] 1%|▏ | 1/72 [00:02<03:24, 2.89s/it] 3%|▎ | 2/72 [00:04<02:26, 2.09s/it] 4%|▍ | 3/72 [00:05<02:06, 1.84s/it] 6%|▌ | 4/72 [00:07<01:57, 1.73s/it] 7%|▋ | 5/72 [00:09<01:51, 1.67s/it] 8%|▊ | 6/72 [00:10<01:47, 1.63s/it] 10%|▉ | 7/72 [00:12<01:44, 1.61s/it] 11%|█ | 8/72 [00:13<01:42, 1.60s/it] 12%|█▎ | 9/72 [00:15<01:40, 1.59s/it] 14%|█▍ | 10/72 [00:16<01:38, 1.59s/it] 15%|█▌ | 11/72 [00:18<01:36, 1.59s/it] 17%|█▋ | 12/72 [00:20<01:35, 1.58s/it] 18%|█▊ | 13/72 [00:21<01:33, 1.59s/it] 19%|█▉ | 14/72 [00:23<01:32, 1.59s/it] 21%|██ | 15/72 [00:24<01:30, 1.59s/it] 22%|██▏ | 16/72 [00:26<01:29, 1.59s/it] 24%|██▎ | 17/72 [00:28<01:27, 1.60s/it] 25%|██▌ | 18/72 [00:29<01:26, 1.60s/it] 26%|██▋ | 19/72 [00:31<01:24, 1.60s/it] 28%|██▊ | 20/72 [00:32<01:23, 1.61s/it] 29%|██▉ | 21/72 [00:34<01:22, 1.61s/it] 31%|███ | 22/72 [00:36<01:20, 1.61s/it] 32%|███▏ | 23/72 [00:37<01:19, 1.61s/it] 33%|███▎ | 24/72 [00:39<01:17, 1.62s/it] 35%|███▍ | 25/72 [00:41<01:16, 1.62s/it] 36%|███▌ | 26/72 [00:42<01:14, 1.62s/it] 38%|███▊ | 27/72 [00:44<01:13, 1.63s/it] 39%|███▉ | 28/72 [00:45<01:11, 1.63s/it] 40%|████ | 29/72 [00:47<01:10, 1.63s/it] 42%|████▏ | 30/72 [00:49<01:08, 1.63s/it] 43%|████▎ | 31/72 [00:50<01:06, 1.62s/it] 44%|████▍ | 32/72 [00:52<01:04, 1.62s/it] 46%|████▌ | 33/72 [00:54<01:03, 1.62s/it] 47%|████▋ | 34/72 [00:55<01:01, 1.62s/it] 49%|████▊ | 35/72 [00:57<00:59, 1.61s/it] 50%|█████ | 36/72 [00:58<00:58, 1.61s/it] 51%|█████▏ | 37/72 [01:00<00:56, 1.61s/it] 53%|█████▎ | 38/72 [01:02<00:54, 1.61s/it] 54%|█████▍ | 39/72 [01:03<00:53, 1.61s/it] 56%|█████▌ | 40/72 [01:05<00:51, 1.61s/it] 57%|█████▋ | 41/72 [01:06<00:49, 1.60s/it] 58%|█████▊ | 42/72 [01:08<00:48, 1.60s/it] 60%|█████▉ | 43/72 [01:10<00:46, 1.60s/it] 61%|██████ | 44/72 [01:11<00:44, 1.60s/it] 62%|██████▎ | 45/72 [01:13<00:43, 1.59s/it] 64%|██████▍ | 46/72 [01:14<00:41, 1.59s/it] 65%|██████▌ | 47/72 [01:16<00:39, 1.59s/it] 67%|██████▋ | 48/72 [01:17<00:38, 1.59s/it] 68%|██████▊ | 49/72 [01:19<00:36, 1.59s/it] 69%|██████▉ | 50/72 [01:21<00:34, 1.59s/it] 71%|███████ | 51/72 [01:22<00:33, 1.59s/it] 72%|███████▏ | 52/72 [01:24<00:31, 1.58s/it] 74%|███████▎ | 53/72 [01:25<00:30, 1.58s/it] 75%|███████▌ | 54/72 [01:27<00:28, 1.59s/it] 76%|███████▋ | 55/72 [01:29<00:26, 1.59s/it] 78%|███████▊ | 56/72 [01:30<00:25, 1.59s/it] 79%|███████▉ | 57/72 [01:32<00:23, 1.59s/it] 81%|████████ | 58/72 [01:33<00:22, 1.59s/it] 82%|████████▏ | 59/72 [01:35<00:20, 1.59s/it] 83%|████████▎ | 60/72 [01:37<00:19, 1.59s/it] 85%|████████▍ | 61/72 [01:38<00:17, 1.59s/it] 86%|████████▌ | 62/72 [01:40<00:15, 1.60s/it] 88%|████████▊ | 63/72 [01:41<00:14, 1.60s/it] 89%|████████▉ | 64/72 [01:43<00:12, 1.60s/it] 90%|█████████ | 65/72 [01:45<00:11, 1.60s/it] 92%|█████████▏| 66/72 [01:46<00:09, 1.61s/it] 93%|█████████▎| 67/72 [01:48<00:08, 1.61s/it] 94%|█████████▍| 68/72 [01:49<00:06, 1.61s/it] 96%|█████████▌| 69/72 [01:51<00:04, 1.61s/it] 97%|█████████▋| 70/72 [01:53<00:03, 1.62s/it] 99%|█████████▊| 71/72 [01:54<00:01, 1.62s/it] 100%|██████████| 72/72 [01:56<00:00, 1.62s/it] 100%|██████████| 72/72 [01:56<00:00, 1.62s/it] Decoding latents in cuda:0... done in 2.89s Move latents to cpu... done in 0.06s