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/e632983035b84d8ba8a13e2d0629c37b/00000-4249126713.webp
https://files.tungsten.run/uploads/33dbf03d7eed46d5aa8572d0b9da4b30/00001-4249126714.webp
https://files.tungsten.run/uploads/a770f3f3590340b99200e4d8891f0020/00002-4249126715.webp
This example was created by sparks
Finished in 89.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a close up of a blue alien with glowing eyes and a horned head, realistic alien, ancient alien portrait, a hyper-detailed alien, djinn man male demon, blue face unreal engine, stunning fantasy 3 d render, male djinn man demon hybrid, epic sci - fi character art, epic sci-fi character art, 3 d game art, by Gjon Mil, <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%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:03<02:30, 3.07s/it] 4%|▍ | 2/50 [00:04<01:44, 2.18s/it] 6%|▌ | 3/50 [00:06<01:29, 1.90s/it] 8%|▊ | 4/50 [00:07<01:21, 1.77s/it] 10%|█ | 5/50 [00:09<01:16, 1.71s/it] 12%|█▏ | 6/50 [00:10<01:13, 1.67s/it] 14%|█▍ | 7/50 [00:12<01:10, 1.64s/it] 16%|█▌ | 8/50 [00:14<01:08, 1.63s/it] 18%|█▊ | 9/50 [00:15<01:06, 1.62s/it] 20%|██ | 10/50 [00:17<01:04, 1.62s/it] 22%|██▏ | 11/50 [00:18<01:02, 1.61s/it] 24%|██▍ | 12/50 [00:20<01:01, 1.61s/it] 26%|██▌ | 13/50 [00:22<00:59, 1.61s/it] 28%|██▊ | 14/50 [00:23<00:58, 1.61s/it] 30%|███ | 15/50 [00:25<00:56, 1.61s/it] 32%|███▏ | 16/50 [00:27<00:54, 1.62s/it] 34%|███▍ | 17/50 [00:28<00:53, 1.61s/it] 36%|███▌ | 18/50 [00:30<00:51, 1.61s/it] 38%|███▊ | 19/50 [00:31<00:49, 1.61s/it] 40%|████ | 20/50 [00:33<00:48, 1.61s/it] 42%|████▏ | 21/50 [00:35<00:46, 1.60s/it] 44%|████▍ | 22/50 [00:36<00:44, 1.60s/it] 46%|████▌ | 23/50 [00:38<00:43, 1.59s/it] 48%|████▊ | 24/50 [00:39<00:41, 1.59s/it] 50%|█████ | 25/50 [00:41<00:39, 1.58s/it] 52%|█████▏ | 26/50 [00:42<00:37, 1.58s/it] 54%|█████▍ | 27/50 [00:44<00:36, 1.58s/it] 56%|█████▌ | 28/50 [00:46<00:34, 1.57s/it] 58%|█████▊ | 29/50 [00:47<00:32, 1.57s/it] 60%|██████ | 30/50 [00:49<00:31, 1.57s/it] 62%|██████▏ | 31/50 [00:50<00:29, 1.56s/it] 64%|██████▍ | 32/50 [00:52<00:28, 1.56s/it] 66%|██████▌ | 33/50 [00:53<00:26, 1.56s/it] 68%|██████▊ | 34/50 [00:55<00:24, 1.55s/it] 70%|███████ | 35/50 [00:56<00:23, 1.55s/it] 72%|███████▏ | 36/50 [00:58<00:21, 1.55s/it] 74%|███████▍ | 37/50 [01:00<00:20, 1.55s/it] 76%|███████▌ | 38/50 [01:01<00:18, 1.55s/it] 78%|███████▊ | 39/50 [01:03<00:16, 1.54s/it] 80%|████████ | 40/50 [01:04<00:15, 1.54s/it] 82%|████████▏ | 41/50 [01:06<00:13, 1.54s/it] 84%|████████▍ | 42/50 [01:07<00:12, 1.55s/it] 86%|████████▌ | 43/50 [01:09<00:10, 1.55s/it] 88%|████████▊ | 44/50 [01:10<00:09, 1.55s/it] 90%|█████████ | 45/50 [01:12<00:07, 1.55s/it] 92%|█████████▏| 46/50 [01:13<00:06, 1.55s/it] 94%|█████████▍| 47/50 [01:15<00:04, 1.56s/it] 96%|█████████▌| 48/50 [01:17<00:03, 1.56s/it] 98%|█████████▊| 49/50 [01:18<00:01, 1.56s/it] 100%|██████████| 50/50 [01:20<00:00, 1.56s/it] 100%|██████████| 50/50 [01:20<00:00, 1.60s/it] Decoding latents in cuda:0... done in 2.9s 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/e632983035b84d8ba8a13e2d0629c37b/00000-4249126713.webp
https://files.tungsten.run/uploads/33dbf03d7eed46d5aa8572d0b9da4b30/00001-4249126714.webp
https://files.tungsten.run/uploads/a770f3f3590340b99200e4d8891f0020/00002-4249126715.webp
This example was created by sparks
Finished in 89.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a close up of a blue alien with glowing eyes and a horned head, realistic alien, ancient alien portrait, a hyper-detailed alien, djinn man male demon, blue face unreal engine, stunning fantasy 3 d render, male djinn man demon hybrid, epic sci - fi character art, epic sci-fi character art, 3 d game art, by Gjon Mil, <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%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:03<02:30, 3.07s/it] 4%|▍ | 2/50 [00:04<01:44, 2.18s/it] 6%|▌ | 3/50 [00:06<01:29, 1.90s/it] 8%|▊ | 4/50 [00:07<01:21, 1.77s/it] 10%|█ | 5/50 [00:09<01:16, 1.71s/it] 12%|█▏ | 6/50 [00:10<01:13, 1.67s/it] 14%|█▍ | 7/50 [00:12<01:10, 1.64s/it] 16%|█▌ | 8/50 [00:14<01:08, 1.63s/it] 18%|█▊ | 9/50 [00:15<01:06, 1.62s/it] 20%|██ | 10/50 [00:17<01:04, 1.62s/it] 22%|██▏ | 11/50 [00:18<01:02, 1.61s/it] 24%|██▍ | 12/50 [00:20<01:01, 1.61s/it] 26%|██▌ | 13/50 [00:22<00:59, 1.61s/it] 28%|██▊ | 14/50 [00:23<00:58, 1.61s/it] 30%|███ | 15/50 [00:25<00:56, 1.61s/it] 32%|███▏ | 16/50 [00:27<00:54, 1.62s/it] 34%|███▍ | 17/50 [00:28<00:53, 1.61s/it] 36%|███▌ | 18/50 [00:30<00:51, 1.61s/it] 38%|███▊ | 19/50 [00:31<00:49, 1.61s/it] 40%|████ | 20/50 [00:33<00:48, 1.61s/it] 42%|████▏ | 21/50 [00:35<00:46, 1.60s/it] 44%|████▍ | 22/50 [00:36<00:44, 1.60s/it] 46%|████▌ | 23/50 [00:38<00:43, 1.59s/it] 48%|████▊ | 24/50 [00:39<00:41, 1.59s/it] 50%|█████ | 25/50 [00:41<00:39, 1.58s/it] 52%|█████▏ | 26/50 [00:42<00:37, 1.58s/it] 54%|█████▍ | 27/50 [00:44<00:36, 1.58s/it] 56%|█████▌ | 28/50 [00:46<00:34, 1.57s/it] 58%|█████▊ | 29/50 [00:47<00:32, 1.57s/it] 60%|██████ | 30/50 [00:49<00:31, 1.57s/it] 62%|██████▏ | 31/50 [00:50<00:29, 1.56s/it] 64%|██████▍ | 32/50 [00:52<00:28, 1.56s/it] 66%|██████▌ | 33/50 [00:53<00:26, 1.56s/it] 68%|██████▊ | 34/50 [00:55<00:24, 1.55s/it] 70%|███████ | 35/50 [00:56<00:23, 1.55s/it] 72%|███████▏ | 36/50 [00:58<00:21, 1.55s/it] 74%|███████▍ | 37/50 [01:00<00:20, 1.55s/it] 76%|███████▌ | 38/50 [01:01<00:18, 1.55s/it] 78%|███████▊ | 39/50 [01:03<00:16, 1.54s/it] 80%|████████ | 40/50 [01:04<00:15, 1.54s/it] 82%|████████▏ | 41/50 [01:06<00:13, 1.54s/it] 84%|████████▍ | 42/50 [01:07<00:12, 1.55s/it] 86%|████████▌ | 43/50 [01:09<00:10, 1.55s/it] 88%|████████▊ | 44/50 [01:10<00:09, 1.55s/it] 90%|█████████ | 45/50 [01:12<00:07, 1.55s/it] 92%|█████████▏| 46/50 [01:13<00:06, 1.55s/it] 94%|█████████▍| 47/50 [01:15<00:04, 1.56s/it] 96%|█████████▌| 48/50 [01:17<00:03, 1.56s/it] 98%|█████████▊| 49/50 [01:18<00:01, 1.56s/it] 100%|██████████| 50/50 [01:20<00:00, 1.56s/it] 100%|██████████| 50/50 [01:20<00:00, 1.60s/it] Decoding latents in cuda:0... done in 2.9s Move latents to cpu... done in 0.03s