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/5f0a404fd02240d8857d24341c5a1f5c/00000-1.webp
https://files.tungsten.run/uploads/fc3c092d59e94f4599723f65ed36650a/00001-2.webp
https://files.tungsten.run/uploads/f7b252ff8fcd411abd97cce3b6e533cb/00002-3.webp
This example was created by sparks
Finished in 332.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: great photo a girl, Accent Lighting, Global Illumination. Extremely high-resolution details, photographic, realism pushed to extreme, fine texture, incredibly lifelike, <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%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:06<05:41, 6.32s/it] 4%|▎ | 2/55 [00:13<05:51, 6.63s/it] 5%|▌ | 3/55 [00:19<05:47, 6.68s/it] 7%|▋ | 4/55 [00:26<05:43, 6.73s/it] 9%|▉ | 5/55 [00:33<05:36, 6.72s/it] 11%|█ | 6/55 [00:40<05:29, 6.73s/it] 13%|█▎ | 7/55 [00:46<05:19, 6.67s/it] 15%|█▍ | 8/55 [00:53<05:09, 6.59s/it] 16%|█▋ | 9/55 [01:00<05:09, 6.73s/it] 18%|█▊ | 10/55 [01:06<05:00, 6.68s/it] 20%|██ | 11/55 [01:13<04:56, 6.73s/it] 22%|██▏ | 12/55 [01:20<04:48, 6.71s/it] 24%|██▎ | 13/55 [01:26<04:38, 6.64s/it] 25%|██▌ | 14/55 [01:33<04:28, 6.54s/it] 27%|██▋ | 15/55 [01:39<04:24, 6.62s/it] 29%|██▉ | 16/55 [01:46<04:13, 6.50s/it] 31%|███ | 17/55 [01:52<04:11, 6.61s/it] 33%|███▎ | 18/55 [01:59<04:04, 6.62s/it] 35%|███▍ | 19/55 [02:06<03:57, 6.61s/it] 36%|███▋ | 20/55 [02:12<03:50, 6.59s/it] 38%|███▊ | 21/55 [02:19<03:44, 6.60s/it] 40%|████ | 22/55 [02:25<03:37, 6.60s/it] 42%|████▏ | 23/55 [02:31<03:25, 6.43s/it] 44%|████▎ | 24/55 [02:38<03:16, 6.34s/it] 45%|████▌ | 25/55 [02:44<03:09, 6.32s/it] 47%|████▋ | 26/55 [02:50<03:02, 6.28s/it] 49%|████▉ | 27/55 [02:56<02:56, 6.30s/it] 51%|█████ | 28/55 [03:03<02:51, 6.37s/it] 53%|█████▎ | 29/55 [03:09<02:45, 6.35s/it] 55%|█████▍ | 30/55 [03:16<02:39, 6.36s/it] 56%|█████▋ | 31/55 [03:21<02:25, 6.07s/it] 58%|█████▊ | 32/55 [03:27<02:16, 5.95s/it] 60%|██████ | 33/55 [03:32<02:07, 5.79s/it] 62%|██████▏ | 34/55 [03:37<01:56, 5.55s/it] 64%|██████▎ | 35/55 [03:42<01:46, 5.31s/it] 65%|██████▌ | 36/55 [03:48<01:46, 5.61s/it] 67%|██████▋ | 37/55 [03:54<01:44, 5.80s/it] 69%|██████▉ | 38/55 [04:00<01:36, 5.66s/it] 71%|███████ | 39/55 [04:05<01:30, 5.64s/it] 73%|███████▎ | 40/55 [04:10<01:22, 5.51s/it] 75%|███████▍ | 41/55 [04:16<01:16, 5.43s/it] 76%|███████▋ | 42/55 [04:21<01:08, 5.29s/it] 78%|███████▊ | 43/55 [04:26<01:02, 5.20s/it] 80%|████████ | 44/55 [04:31<00:57, 5.23s/it] 82%|████████▏ | 45/55 [04:37<00:55, 5.57s/it] 84%|████████▎ | 46/55 [04:43<00:49, 5.48s/it] 85%|████████▌ | 47/55 [04:48<00:43, 5.39s/it] 87%|████████▋ | 48/55 [04:53<00:36, 5.23s/it] 89%|████████▉ | 49/55 [04:58<00:31, 5.27s/it] 91%|█████████ | 50/55 [05:03<00:25, 5.20s/it] 93%|█████████▎| 51/55 [05:08<00:20, 5.16s/it] 95%|█████████▍| 52/55 [05:13<00:15, 5.17s/it] 96%|█████████▋| 53/55 [05:17<00:09, 4.87s/it] 98%|█████████▊| 54/55 [05:21<00:04, 4.54s/it] 100%|██████████| 55/55 [05:23<00:00, 3.67s/it] 100%|██████████| 55/55 [05:23<00:00, 5.88s/it] Decoding latents in cuda:0... done in 2.91s Move latents to cpu... done in 0.04s
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/5f0a404fd02240d8857d24341c5a1f5c/00000-1.webp
https://files.tungsten.run/uploads/fc3c092d59e94f4599723f65ed36650a/00001-2.webp
https://files.tungsten.run/uploads/f7b252ff8fcd411abd97cce3b6e533cb/00002-3.webp
This example was created by sparks
Finished in 332.2 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: great photo a girl, Accent Lighting, Global Illumination. Extremely high-resolution details, photographic, realism pushed to extreme, fine texture, incredibly lifelike, <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%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:06<05:41, 6.32s/it] 4%|▎ | 2/55 [00:13<05:51, 6.63s/it] 5%|▌ | 3/55 [00:19<05:47, 6.68s/it] 7%|▋ | 4/55 [00:26<05:43, 6.73s/it] 9%|▉ | 5/55 [00:33<05:36, 6.72s/it] 11%|█ | 6/55 [00:40<05:29, 6.73s/it] 13%|█▎ | 7/55 [00:46<05:19, 6.67s/it] 15%|█▍ | 8/55 [00:53<05:09, 6.59s/it] 16%|█▋ | 9/55 [01:00<05:09, 6.73s/it] 18%|█▊ | 10/55 [01:06<05:00, 6.68s/it] 20%|██ | 11/55 [01:13<04:56, 6.73s/it] 22%|██▏ | 12/55 [01:20<04:48, 6.71s/it] 24%|██▎ | 13/55 [01:26<04:38, 6.64s/it] 25%|██▌ | 14/55 [01:33<04:28, 6.54s/it] 27%|██▋ | 15/55 [01:39<04:24, 6.62s/it] 29%|██▉ | 16/55 [01:46<04:13, 6.50s/it] 31%|███ | 17/55 [01:52<04:11, 6.61s/it] 33%|███▎ | 18/55 [01:59<04:04, 6.62s/it] 35%|███▍ | 19/55 [02:06<03:57, 6.61s/it] 36%|███▋ | 20/55 [02:12<03:50, 6.59s/it] 38%|███▊ | 21/55 [02:19<03:44, 6.60s/it] 40%|████ | 22/55 [02:25<03:37, 6.60s/it] 42%|████▏ | 23/55 [02:31<03:25, 6.43s/it] 44%|████▎ | 24/55 [02:38<03:16, 6.34s/it] 45%|████▌ | 25/55 [02:44<03:09, 6.32s/it] 47%|████▋ | 26/55 [02:50<03:02, 6.28s/it] 49%|████▉ | 27/55 [02:56<02:56, 6.30s/it] 51%|█████ | 28/55 [03:03<02:51, 6.37s/it] 53%|█████▎ | 29/55 [03:09<02:45, 6.35s/it] 55%|█████▍ | 30/55 [03:16<02:39, 6.36s/it] 56%|█████▋ | 31/55 [03:21<02:25, 6.07s/it] 58%|█████▊ | 32/55 [03:27<02:16, 5.95s/it] 60%|██████ | 33/55 [03:32<02:07, 5.79s/it] 62%|██████▏ | 34/55 [03:37<01:56, 5.55s/it] 64%|██████▎ | 35/55 [03:42<01:46, 5.31s/it] 65%|██████▌ | 36/55 [03:48<01:46, 5.61s/it] 67%|██████▋ | 37/55 [03:54<01:44, 5.80s/it] 69%|██████▉ | 38/55 [04:00<01:36, 5.66s/it] 71%|███████ | 39/55 [04:05<01:30, 5.64s/it] 73%|███████▎ | 40/55 [04:10<01:22, 5.51s/it] 75%|███████▍ | 41/55 [04:16<01:16, 5.43s/it] 76%|███████▋ | 42/55 [04:21<01:08, 5.29s/it] 78%|███████▊ | 43/55 [04:26<01:02, 5.20s/it] 80%|████████ | 44/55 [04:31<00:57, 5.23s/it] 82%|████████▏ | 45/55 [04:37<00:55, 5.57s/it] 84%|████████▎ | 46/55 [04:43<00:49, 5.48s/it] 85%|████████▌ | 47/55 [04:48<00:43, 5.39s/it] 87%|████████▋ | 48/55 [04:53<00:36, 5.23s/it] 89%|████████▉ | 49/55 [04:58<00:31, 5.27s/it] 91%|█████████ | 50/55 [05:03<00:25, 5.20s/it] 93%|█████████▎| 51/55 [05:08<00:20, 5.16s/it] 95%|█████████▍| 52/55 [05:13<00:15, 5.17s/it] 96%|█████████▋| 53/55 [05:17<00:09, 4.87s/it] 98%|█████████▊| 54/55 [05:21<00:04, 4.54s/it] 100%|██████████| 55/55 [05:23<00:00, 3.67s/it] 100%|██████████| 55/55 [05:23<00:00, 5.88s/it] Decoding latents in cuda:0... done in 2.91s Move latents to cpu... done in 0.04s