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/0a25b724c0fb4108aa7e10b2e511779e/00000-4284884149.webp
https://files.tungsten.run/uploads/0cc1c7f1342b4754bca1efbc18912a18/00001-4284884150.webp
https://files.tungsten.run/uploads/19a92ea97dfe44ada7b8cbe87dd1096c/00002-4284884151.webp
This example was created by sparks
Finished in 163.8 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Hyperrealistic art fantasy forest landscape, a magic portal in the forest, a detailed matte painting by Mike Winkelmann AND by Alan Lee, cgsociety, fantasy art, forest portal, cgsociety 9, 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: doors, 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%| | 0/64 [00:00<?, ?it/s] 2%|▏ | 1/64 [00:02<02:31, 2.40s/it] 3%|▎ | 2/64 [00:04<02:30, 2.42s/it] 5%|▍ | 3/64 [00:07<02:28, 2.43s/it] 6%|▋ | 4/64 [00:09<02:26, 2.44s/it] 8%|▊ | 5/64 [00:12<02:24, 2.45s/it] 9%|▉ | 6/64 [00:14<02:22, 2.45s/it] 11%|█ | 7/64 [00:17<02:20, 2.46s/it] 12%|█▎ | 8/64 [00:19<02:18, 2.47s/it] 14%|█▍ | 9/64 [00:22<02:15, 2.47s/it] 16%|█▌ | 10/64 [00:24<02:13, 2.48s/it] 17%|█▋ | 11/64 [00:27<02:11, 2.48s/it] 19%|█▉ | 12/64 [00:29<02:08, 2.48s/it] 20%|██ | 13/64 [00:32<02:06, 2.48s/it] 22%|██▏ | 14/64 [00:34<02:03, 2.48s/it] 23%|██▎ | 15/64 [00:36<02:01, 2.48s/it] 25%|██▌ | 16/64 [00:39<01:58, 2.48s/it] 27%|██▋ | 17/64 [00:41<01:56, 2.47s/it] 28%|██▊ | 18/64 [00:44<01:53, 2.47s/it] 30%|██▉ | 19/64 [00:46<01:51, 2.47s/it] 31%|███▏ | 20/64 [00:49<01:48, 2.47s/it] 33%|███▎ | 21/64 [00:51<01:45, 2.46s/it] 34%|███▍ | 22/64 [00:54<01:43, 2.46s/it] 36%|███▌ | 23/64 [00:56<01:40, 2.46s/it] 38%|███▊ | 24/64 [00:59<01:38, 2.46s/it] 39%|███▉ | 25/64 [01:01<01:35, 2.46s/it] 41%|████ | 26/64 [01:04<01:33, 2.46s/it] 42%|████▏ | 27/64 [01:06<01:30, 2.46s/it] 44%|████▍ | 28/64 [01:08<01:28, 2.46s/it] 45%|████▌ | 29/64 [01:11<01:26, 2.46s/it] 47%|████▋ | 30/64 [01:13<01:23, 2.46s/it] 48%|████▊ | 31/64 [01:16<01:21, 2.47s/it] 50%|█████ | 32/64 [01:18<01:19, 2.47s/it] 52%|█████▏ | 33/64 [01:21<01:16, 2.48s/it] 53%|█████▎ | 34/64 [01:23<01:14, 2.49s/it] 55%|█████▍ | 35/64 [01:26<01:12, 2.50s/it] 56%|█████▋ | 36/64 [01:28<01:10, 2.50s/it] 58%|█████▊ | 37/64 [01:31<01:07, 2.51s/it] 59%|█████▉ | 38/64 [01:33<01:05, 2.52s/it] 61%|██████ | 39/64 [01:36<01:03, 2.52s/it] 62%|██████▎ | 40/64 [01:39<01:00, 2.53s/it] 64%|██████▍ | 41/64 [01:41<00:58, 2.54s/it] 66%|██████▌ | 42/64 [01:44<00:56, 2.55s/it] 67%|██████▋ | 43/64 [01:46<00:53, 2.56s/it] 69%|██████▉ | 44/64 [01:49<00:51, 2.56s/it] 70%|███████ | 45/64 [01:51<00:48, 2.56s/it] 72%|███████▏ | 46/64 [01:54<00:45, 2.56s/it] 73%|███████▎ | 47/64 [01:56<00:43, 2.55s/it] 75%|███████▌ | 48/64 [01:59<00:40, 2.55s/it] 77%|███████▋ | 49/64 [02:02<00:38, 2.54s/it] 78%|███████▊ | 50/64 [02:04<00:35, 2.53s/it] 80%|███████▉ | 51/64 [02:07<00:32, 2.53s/it] 81%|████████▏ | 52/64 [02:09<00:30, 2.52s/it] 83%|████████▎ | 53/64 [02:12<00:27, 2.52s/it] 84%|████████▍ | 54/64 [02:14<00:25, 2.53s/it] 86%|████████▌ | 55/64 [02:17<00:22, 2.53s/it] 88%|████████▊ | 56/64 [02:19<00:20, 2.52s/it] 89%|████████▉ | 57/64 [02:22<00:17, 2.52s/it] 91%|█████████ | 58/64 [02:24<00:15, 2.52s/it] 92%|█████████▏| 59/64 [02:27<00:12, 2.52s/it] 94%|█████████▍| 60/64 [02:29<00:10, 2.52s/it] 95%|█████████▌| 61/64 [02:32<00:07, 2.52s/it] 97%|█████████▋| 62/64 [02:34<00:05, 2.51s/it] 98%|█████████▊| 63/64 [02:37<00:02, 2.51s/it] 100%|██████████| 64/64 [02:39<00:00, 2.52s/it] 100%|██████████| 64/64 [02:39<00:00, 2.50s/it] Decoding latents in cuda:0... done in 2.86s 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/0a25b724c0fb4108aa7e10b2e511779e/00000-4284884149.webp
https://files.tungsten.run/uploads/0cc1c7f1342b4754bca1efbc18912a18/00001-4284884150.webp
https://files.tungsten.run/uploads/19a92ea97dfe44ada7b8cbe87dd1096c/00002-4284884151.webp
This example was created by sparks
Finished in 163.8 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: Hyperrealistic art fantasy forest landscape, a magic portal in the forest, a detailed matte painting by Mike Winkelmann AND by Alan Lee, cgsociety, fantasy art, forest portal, cgsociety 9, 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: doors, 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%| | 0/64 [00:00<?, ?it/s] 2%|▏ | 1/64 [00:02<02:31, 2.40s/it] 3%|▎ | 2/64 [00:04<02:30, 2.42s/it] 5%|▍ | 3/64 [00:07<02:28, 2.43s/it] 6%|▋ | 4/64 [00:09<02:26, 2.44s/it] 8%|▊ | 5/64 [00:12<02:24, 2.45s/it] 9%|▉ | 6/64 [00:14<02:22, 2.45s/it] 11%|█ | 7/64 [00:17<02:20, 2.46s/it] 12%|█▎ | 8/64 [00:19<02:18, 2.47s/it] 14%|█▍ | 9/64 [00:22<02:15, 2.47s/it] 16%|█▌ | 10/64 [00:24<02:13, 2.48s/it] 17%|█▋ | 11/64 [00:27<02:11, 2.48s/it] 19%|█▉ | 12/64 [00:29<02:08, 2.48s/it] 20%|██ | 13/64 [00:32<02:06, 2.48s/it] 22%|██▏ | 14/64 [00:34<02:03, 2.48s/it] 23%|██▎ | 15/64 [00:36<02:01, 2.48s/it] 25%|██▌ | 16/64 [00:39<01:58, 2.48s/it] 27%|██▋ | 17/64 [00:41<01:56, 2.47s/it] 28%|██▊ | 18/64 [00:44<01:53, 2.47s/it] 30%|██▉ | 19/64 [00:46<01:51, 2.47s/it] 31%|███▏ | 20/64 [00:49<01:48, 2.47s/it] 33%|███▎ | 21/64 [00:51<01:45, 2.46s/it] 34%|███▍ | 22/64 [00:54<01:43, 2.46s/it] 36%|███▌ | 23/64 [00:56<01:40, 2.46s/it] 38%|███▊ | 24/64 [00:59<01:38, 2.46s/it] 39%|███▉ | 25/64 [01:01<01:35, 2.46s/it] 41%|████ | 26/64 [01:04<01:33, 2.46s/it] 42%|████▏ | 27/64 [01:06<01:30, 2.46s/it] 44%|████▍ | 28/64 [01:08<01:28, 2.46s/it] 45%|████▌ | 29/64 [01:11<01:26, 2.46s/it] 47%|████▋ | 30/64 [01:13<01:23, 2.46s/it] 48%|████▊ | 31/64 [01:16<01:21, 2.47s/it] 50%|█████ | 32/64 [01:18<01:19, 2.47s/it] 52%|█████▏ | 33/64 [01:21<01:16, 2.48s/it] 53%|█████▎ | 34/64 [01:23<01:14, 2.49s/it] 55%|█████▍ | 35/64 [01:26<01:12, 2.50s/it] 56%|█████▋ | 36/64 [01:28<01:10, 2.50s/it] 58%|█████▊ | 37/64 [01:31<01:07, 2.51s/it] 59%|█████▉ | 38/64 [01:33<01:05, 2.52s/it] 61%|██████ | 39/64 [01:36<01:03, 2.52s/it] 62%|██████▎ | 40/64 [01:39<01:00, 2.53s/it] 64%|██████▍ | 41/64 [01:41<00:58, 2.54s/it] 66%|██████▌ | 42/64 [01:44<00:56, 2.55s/it] 67%|██████▋ | 43/64 [01:46<00:53, 2.56s/it] 69%|██████▉ | 44/64 [01:49<00:51, 2.56s/it] 70%|███████ | 45/64 [01:51<00:48, 2.56s/it] 72%|███████▏ | 46/64 [01:54<00:45, 2.56s/it] 73%|███████▎ | 47/64 [01:56<00:43, 2.55s/it] 75%|███████▌ | 48/64 [01:59<00:40, 2.55s/it] 77%|███████▋ | 49/64 [02:02<00:38, 2.54s/it] 78%|███████▊ | 50/64 [02:04<00:35, 2.53s/it] 80%|███████▉ | 51/64 [02:07<00:32, 2.53s/it] 81%|████████▏ | 52/64 [02:09<00:30, 2.52s/it] 83%|████████▎ | 53/64 [02:12<00:27, 2.52s/it] 84%|████████▍ | 54/64 [02:14<00:25, 2.53s/it] 86%|████████▌ | 55/64 [02:17<00:22, 2.53s/it] 88%|████████▊ | 56/64 [02:19<00:20, 2.52s/it] 89%|████████▉ | 57/64 [02:22<00:17, 2.52s/it] 91%|█████████ | 58/64 [02:24<00:15, 2.52s/it] 92%|█████████▏| 59/64 [02:27<00:12, 2.52s/it] 94%|█████████▍| 60/64 [02:29<00:10, 2.52s/it] 95%|█████████▌| 61/64 [02:32<00:07, 2.52s/it] 97%|█████████▋| 62/64 [02:34<00:05, 2.51s/it] 98%|█████████▊| 63/64 [02:37<00:02, 2.51s/it] 100%|██████████| 64/64 [02:39<00:00, 2.52s/it] 100%|██████████| 64/64 [02:39<00:00, 2.50s/it] Decoding latents in cuda:0... done in 2.86s Move latents to cpu... done in 0.03s