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/1fae50eb6107455c93bab22d079acd69/00000-4030100647.webp
https://files.tungsten.run/uploads/cd23d42de67048219d7fb75bd9e75ee6/00001-4030100648.webp
https://files.tungsten.run/uploads/5c04403e7bbd4de083b770236eee4139/00002-4030100649.webp
This example was created by sparks
Finished in 162.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Role-playing game (RPG) style fantasy Gothic style a woman in a corset sitting on a couch in a room with a mirror and a gold framed mirror, Ayami Kojima, by Guo Pei,victorian, a sculpture, gothic art, 1girl, blonde hair, breasts, cleavage, corset, garter straps, jewelry, leg garter, lips, looking at viewer, medium breasts, realistic, solo, thigh strap . Dark, mysterious, haunting, dramatic, ornate, detailed . Detailed, vibrant, immersive, reminiscent of high fantasy RPG games,, <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 [00:04<03:17, 4.03s/it] 4%|▍ | 2/50 [00:07<02:54, 3.63s/it] 6%|▌ | 3/50 [00:10<02:40, 3.41s/it] 8%|▊ | 4/50 [00:13<02:30, 3.27s/it] 10%|█ | 5/50 [00:16<02:23, 3.19s/it] 12%|█▏ | 6/50 [00:21<02:38, 3.59s/it] 14%|█▍ | 7/50 [00:24<02:27, 3.43s/it] 16%|█▌ | 8/50 [00:27<02:23, 3.41s/it] 18%|█▊ | 9/50 [00:30<02:16, 3.34s/it] 20%|██ | 10/50 [00:33<02:11, 3.29s/it] 22%|██▏ | 11/50 [00:36<02:04, 3.19s/it] 24%|██▍ | 12/50 [00:40<02:09, 3.42s/it] 26%|██▌ | 13/50 [00:43<02:02, 3.32s/it] 28%|██▊ | 14/50 [00:47<01:58, 3.31s/it] 30%|███ | 15/50 [00:50<01:51, 3.19s/it] 32%|███▏ | 16/50 [00:53<01:50, 3.24s/it] 34%|███▍ | 17/50 [00:56<01:46, 3.23s/it] 36%|███▌ | 18/50 [00:59<01:41, 3.17s/it] 38%|███▊ | 19/50 [01:02<01:37, 3.13s/it] 40%|████ | 20/50 [01:06<01:36, 3.23s/it] 42%|████▏ | 21/50 [01:09<01:31, 3.17s/it] 44%|████▍ | 22/50 [01:12<01:28, 3.16s/it] 46%|████▌ | 23/50 [01:15<01:24, 3.15s/it] 48%|████▊ | 24/50 [01:18<01:20, 3.10s/it] 50%|█████ | 25/50 [01:21<01:17, 3.10s/it] 52%|█████▏ | 26/50 [01:24<01:15, 3.13s/it] 54%|█████▍ | 27/50 [01:27<01:11, 3.10s/it] 56%|█████▌ | 28/50 [01:30<01:08, 3.12s/it] 58%|█████▊ | 29/50 [01:34<01:06, 3.15s/it] 60%|██████ | 30/50 [01:37<01:04, 3.20s/it] 62%|██████▏ | 31/50 [01:40<01:00, 3.19s/it] 64%|██████▍ | 32/50 [01:43<00:56, 3.16s/it] 66%|██████▌ | 33/50 [01:46<00:53, 3.12s/it] 68%|██████▊ | 34/50 [01:49<00:49, 3.06s/it] 70%|███████ | 35/50 [01:52<00:45, 3.00s/it] 72%|███████▏ | 36/50 [01:55<00:41, 2.97s/it] 74%|███████▍ | 37/50 [01:58<00:37, 2.91s/it] 76%|███████▌ | 38/50 [02:02<00:38, 3.19s/it] 78%|███████▊ | 39/50 [02:04<00:33, 3.08s/it] 80%|████████ | 40/50 [02:07<00:29, 2.95s/it] 82%|████████▏ | 41/50 [02:10<00:26, 2.96s/it] 84%|████████▍ | 42/50 [02:13<00:22, 2.86s/it] 86%|████████▌ | 43/50 [02:15<00:20, 2.87s/it] 88%|████████▊ | 44/50 [02:18<00:17, 2.84s/it] 90%|█████████ | 45/50 [02:21<00:14, 2.83s/it] 92%|█████████▏| 46/50 [02:24<00:11, 2.87s/it] 94%|█████████▍| 47/50 [02:27<00:08, 2.76s/it] 96%|█████████▌| 48/50 [02:30<00:05, 2.82s/it] 98%|█████████▊| 49/50 [02:31<00:02, 2.51s/it] 100%|██████████| 50/50 [02:33<00:00, 2.21s/it] 100%|██████████| 50/50 [02:33<00:00, 3.07s/it] Decoding latents in cuda:0... done in 2.86s 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/1fae50eb6107455c93bab22d079acd69/00000-4030100647.webp
https://files.tungsten.run/uploads/cd23d42de67048219d7fb75bd9e75ee6/00001-4030100648.webp
https://files.tungsten.run/uploads/5c04403e7bbd4de083b770236eee4139/00002-4030100649.webp
This example was created by sparks
Finished in 162.1 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Role-playing game (RPG) style fantasy Gothic style a woman in a corset sitting on a couch in a room with a mirror and a gold framed mirror, Ayami Kojima, by Guo Pei,victorian, a sculpture, gothic art, 1girl, blonde hair, breasts, cleavage, corset, garter straps, jewelry, leg garter, lips, looking at viewer, medium breasts, realistic, solo, thigh strap . Dark, mysterious, haunting, dramatic, ornate, detailed . Detailed, vibrant, immersive, reminiscent of high fantasy RPG games,, <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 [00:04<03:17, 4.03s/it] 4%|▍ | 2/50 [00:07<02:54, 3.63s/it] 6%|▌ | 3/50 [00:10<02:40, 3.41s/it] 8%|▊ | 4/50 [00:13<02:30, 3.27s/it] 10%|█ | 5/50 [00:16<02:23, 3.19s/it] 12%|█▏ | 6/50 [00:21<02:38, 3.59s/it] 14%|█▍ | 7/50 [00:24<02:27, 3.43s/it] 16%|█▌ | 8/50 [00:27<02:23, 3.41s/it] 18%|█▊ | 9/50 [00:30<02:16, 3.34s/it] 20%|██ | 10/50 [00:33<02:11, 3.29s/it] 22%|██▏ | 11/50 [00:36<02:04, 3.19s/it] 24%|██▍ | 12/50 [00:40<02:09, 3.42s/it] 26%|██▌ | 13/50 [00:43<02:02, 3.32s/it] 28%|██▊ | 14/50 [00:47<01:58, 3.31s/it] 30%|███ | 15/50 [00:50<01:51, 3.19s/it] 32%|███▏ | 16/50 [00:53<01:50, 3.24s/it] 34%|███▍ | 17/50 [00:56<01:46, 3.23s/it] 36%|███▌ | 18/50 [00:59<01:41, 3.17s/it] 38%|███▊ | 19/50 [01:02<01:37, 3.13s/it] 40%|████ | 20/50 [01:06<01:36, 3.23s/it] 42%|████▏ | 21/50 [01:09<01:31, 3.17s/it] 44%|████▍ | 22/50 [01:12<01:28, 3.16s/it] 46%|████▌ | 23/50 [01:15<01:24, 3.15s/it] 48%|████▊ | 24/50 [01:18<01:20, 3.10s/it] 50%|█████ | 25/50 [01:21<01:17, 3.10s/it] 52%|█████▏ | 26/50 [01:24<01:15, 3.13s/it] 54%|█████▍ | 27/50 [01:27<01:11, 3.10s/it] 56%|█████▌ | 28/50 [01:30<01:08, 3.12s/it] 58%|█████▊ | 29/50 [01:34<01:06, 3.15s/it] 60%|██████ | 30/50 [01:37<01:04, 3.20s/it] 62%|██████▏ | 31/50 [01:40<01:00, 3.19s/it] 64%|██████▍ | 32/50 [01:43<00:56, 3.16s/it] 66%|██████▌ | 33/50 [01:46<00:53, 3.12s/it] 68%|██████▊ | 34/50 [01:49<00:49, 3.06s/it] 70%|███████ | 35/50 [01:52<00:45, 3.00s/it] 72%|███████▏ | 36/50 [01:55<00:41, 2.97s/it] 74%|███████▍ | 37/50 [01:58<00:37, 2.91s/it] 76%|███████▌ | 38/50 [02:02<00:38, 3.19s/it] 78%|███████▊ | 39/50 [02:04<00:33, 3.08s/it] 80%|████████ | 40/50 [02:07<00:29, 2.95s/it] 82%|████████▏ | 41/50 [02:10<00:26, 2.96s/it] 84%|████████▍ | 42/50 [02:13<00:22, 2.86s/it] 86%|████████▌ | 43/50 [02:15<00:20, 2.87s/it] 88%|████████▊ | 44/50 [02:18<00:17, 2.84s/it] 90%|█████████ | 45/50 [02:21<00:14, 2.83s/it] 92%|█████████▏| 46/50 [02:24<00:11, 2.87s/it] 94%|█████████▍| 47/50 [02:27<00:08, 2.76s/it] 96%|█████████▌| 48/50 [02:30<00:05, 2.82s/it] 98%|█████████▊| 49/50 [02:31<00:02, 2.51s/it] 100%|██████████| 50/50 [02:33<00:00, 2.21s/it] 100%|██████████| 50/50 [02:33<00:00, 3.07s/it] Decoding latents in cuda:0... done in 2.86s Move latents to cpu... done in 0.04s