tungsten-logo
Sign In
Enchanting Lily XL
Enchanting Lily XL

Enchanting Lily XL

7 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/6175872ad4314887b044fa9d4027ee0e/00000-3073987828.webp
https://files.tungsten.run/uploads/fb0fb94146834d28a076c5747befbff3/00001-3073987829.webp
https://files.tungsten.run/uploads/57138fa218114ea29d85a28b7b35a30c/00002-3073987830.webp
This example was created by sparks
Finished in 190.7 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1girl, white curly hair, tuxedo, smoking a pipe, sitting in a big red chair, cozy living room, fireplace, bookshelves, window, cold outside, <lora:add-detail-xl:1.0> Full negative prompt: Bad quality, worst quality, out of frame, cropped, blurry, ugly, deformed, mutated, bad proportions, bad anatomy, extra limbs, missing limbs, extra fingers, missing fingers, 6 fingers, 4 fingers, 3 arms, 4 arms, 3 legs, 4 legs, extra digit, fewer digits, deformed limbs, deformed fingers, mutated limbs, mutated fingers, ugly limbs, ugly fingers, writing, text, watermark, username, signature, comics, speech bubble, several images, collage, monochrome, smudge, artifact 0%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:03<03:47, 3.85s/it] 3%|▎ | 2/60 [00:07<03:28, 3.59s/it] 5%|▌ | 3/60 [00:10<03:13, 3.39s/it] 7%|▋ | 4/60 [00:13<03:09, 3.39s/it] 8%|▊ | 5/60 [00:17<03:03, 3.34s/it] 10%|█ | 6/60 [00:20<03:02, 3.37s/it] 12%|█▏ | 7/60 [00:23<02:57, 3.36s/it] 13%|█▎ | 8/60 [00:26<02:48, 3.25s/it] 15%|█▌ | 9/60 [00:29<02:43, 3.20s/it] 17%|█▋ | 10/60 [00:33<02:44, 3.29s/it] 18%|█▊ | 11/60 [00:36<02:40, 3.27s/it] 20%|██ | 12/60 [00:39<02:37, 3.28s/it] 22%|██▏ | 13/60 [00:43<02:35, 3.31s/it] 23%|██▎ | 14/60 [00:47<02:42, 3.54s/it] 25%|██▌ | 15/60 [00:50<02:38, 3.53s/it] 27%|██▋ | 16/60 [00:54<02:33, 3.49s/it] 28%|██▊ | 17/60 [00:57<02:27, 3.43s/it] 30%|███ | 18/60 [01:01<02:24, 3.43s/it] 32%|███▏ | 19/60 [01:04<02:18, 3.38s/it] 33%|███▎ | 20/60 [01:07<02:15, 3.39s/it] 35%|███▌ | 21/60 [01:10<02:08, 3.31s/it] 37%|███▋ | 22/60 [01:14<02:06, 3.32s/it] 38%|███▊ | 23/60 [01:17<01:59, 3.24s/it] 40%|████ | 24/60 [01:20<01:57, 3.26s/it] 42%|████▏ | 25/60 [01:23<01:52, 3.21s/it] 43%|████▎ | 26/60 [01:26<01:50, 3.25s/it] 45%|████▌ | 27/60 [01:30<01:46, 3.22s/it] 47%|████▋ | 28/60 [01:32<01:38, 3.08s/it] 48%|████▊ | 29/60 [01:35<01:32, 2.98s/it] 50%|█████ | 30/60 [01:38<01:30, 3.01s/it] 52%|█████▏ | 31/60 [01:41<01:28, 3.05s/it] 53%|█████▎ | 32/60 [01:44<01:23, 2.98s/it] 55%|█████▌ | 33/60 [01:47<01:23, 3.09s/it] 57%|█████▋ | 34/60 [01:50<01:19, 3.05s/it] 58%|█████▊ | 35/60 [01:53<01:15, 3.03s/it] 60%|██████ | 36/60 [01:57<01:15, 3.13s/it] 62%|██████▏ | 37/60 [02:00<01:10, 3.08s/it] 63%|██████▎ | 38/60 [02:03<01:06, 3.00s/it] 65%|██████▌ | 39/60 [02:06<01:05, 3.11s/it] 67%|██████▋ | 40/60 [02:09<01:01, 3.09s/it] 68%|██████▊ | 41/60 [02:12<00:57, 3.05s/it] 70%|███████ | 42/60 [02:15<00:54, 3.01s/it] 72%|███████▏ | 43/60 [02:18<00:50, 2.98s/it] 73%|███████▎ | 44/60 [02:20<00:45, 2.85s/it] 75%|███████▌ | 45/60 [02:23<00:41, 2.76s/it] 77%|███████▋ | 46/60 [02:26<00:39, 2.83s/it] 78%|███████▊ | 47/60 [02:29<00:36, 2.80s/it] 80%|████████ | 48/60 [02:31<00:34, 2.84s/it] 82%|████████▏ | 49/60 [02:34<00:31, 2.83s/it] 83%|████████▎ | 50/60 [02:37<00:28, 2.82s/it] 85%|████████▌ | 51/60 [02:40<00:26, 2.90s/it] 87%|████████▋ | 52/60 [02:43<00:22, 2.75s/it] 88%|████████▊ | 53/60 [02:46<00:19, 2.81s/it] 90%|█████████ | 54/60 [02:48<00:16, 2.72s/it] 92%|█████████▏| 55/60 [02:51<00:13, 2.78s/it] 93%|█████████▎| 56/60 [02:54<00:11, 2.75s/it] 95%|█████████▌| 57/60 [02:57<00:08, 2.85s/it] 97%|█████████▋| 58/60 [02:59<00:05, 2.74s/it] 98%|█████████▊| 59/60 [03:01<00:02, 2.46s/it] 100%|██████████| 60/60 [03:03<00:00, 2.17s/it] 100%|██████████| 60/60 [03:03<00:00, 3.05s/it] Decoding latents in cuda:0... done in 2.88s 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/6175872ad4314887b044fa9d4027ee0e/00000-3073987828.webp
https://files.tungsten.run/uploads/fb0fb94146834d28a076c5747befbff3/00001-3073987829.webp
https://files.tungsten.run/uploads/57138fa218114ea29d85a28b7b35a30c/00002-3073987830.webp
This example was created by sparks
Finished in 190.7 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: 1girl, white curly hair, tuxedo, smoking a pipe, sitting in a big red chair, cozy living room, fireplace, bookshelves, window, cold outside, <lora:add-detail-xl:1.0> Full negative prompt: Bad quality, worst quality, out of frame, cropped, blurry, ugly, deformed, mutated, bad proportions, bad anatomy, extra limbs, missing limbs, extra fingers, missing fingers, 6 fingers, 4 fingers, 3 arms, 4 arms, 3 legs, 4 legs, extra digit, fewer digits, deformed limbs, deformed fingers, mutated limbs, mutated fingers, ugly limbs, ugly fingers, writing, text, watermark, username, signature, comics, speech bubble, several images, collage, monochrome, smudge, artifact 0%| | 0/60 [00:00<?, ?it/s] 2%|▏ | 1/60 [00:03<03:47, 3.85s/it] 3%|▎ | 2/60 [00:07<03:28, 3.59s/it] 5%|▌ | 3/60 [00:10<03:13, 3.39s/it] 7%|▋ | 4/60 [00:13<03:09, 3.39s/it] 8%|▊ | 5/60 [00:17<03:03, 3.34s/it] 10%|█ | 6/60 [00:20<03:02, 3.37s/it] 12%|█▏ | 7/60 [00:23<02:57, 3.36s/it] 13%|█▎ | 8/60 [00:26<02:48, 3.25s/it] 15%|█▌ | 9/60 [00:29<02:43, 3.20s/it] 17%|█▋ | 10/60 [00:33<02:44, 3.29s/it] 18%|█▊ | 11/60 [00:36<02:40, 3.27s/it] 20%|██ | 12/60 [00:39<02:37, 3.28s/it] 22%|██▏ | 13/60 [00:43<02:35, 3.31s/it] 23%|██▎ | 14/60 [00:47<02:42, 3.54s/it] 25%|██▌ | 15/60 [00:50<02:38, 3.53s/it] 27%|██▋ | 16/60 [00:54<02:33, 3.49s/it] 28%|██▊ | 17/60 [00:57<02:27, 3.43s/it] 30%|███ | 18/60 [01:01<02:24, 3.43s/it] 32%|███▏ | 19/60 [01:04<02:18, 3.38s/it] 33%|███▎ | 20/60 [01:07<02:15, 3.39s/it] 35%|███▌ | 21/60 [01:10<02:08, 3.31s/it] 37%|███▋ | 22/60 [01:14<02:06, 3.32s/it] 38%|███▊ | 23/60 [01:17<01:59, 3.24s/it] 40%|████ | 24/60 [01:20<01:57, 3.26s/it] 42%|████▏ | 25/60 [01:23<01:52, 3.21s/it] 43%|████▎ | 26/60 [01:26<01:50, 3.25s/it] 45%|████▌ | 27/60 [01:30<01:46, 3.22s/it] 47%|████▋ | 28/60 [01:32<01:38, 3.08s/it] 48%|████▊ | 29/60 [01:35<01:32, 2.98s/it] 50%|█████ | 30/60 [01:38<01:30, 3.01s/it] 52%|█████▏ | 31/60 [01:41<01:28, 3.05s/it] 53%|█████▎ | 32/60 [01:44<01:23, 2.98s/it] 55%|█████▌ | 33/60 [01:47<01:23, 3.09s/it] 57%|█████▋ | 34/60 [01:50<01:19, 3.05s/it] 58%|█████▊ | 35/60 [01:53<01:15, 3.03s/it] 60%|██████ | 36/60 [01:57<01:15, 3.13s/it] 62%|██████▏ | 37/60 [02:00<01:10, 3.08s/it] 63%|██████▎ | 38/60 [02:03<01:06, 3.00s/it] 65%|██████▌ | 39/60 [02:06<01:05, 3.11s/it] 67%|██████▋ | 40/60 [02:09<01:01, 3.09s/it] 68%|██████▊ | 41/60 [02:12<00:57, 3.05s/it] 70%|███████ | 42/60 [02:15<00:54, 3.01s/it] 72%|███████▏ | 43/60 [02:18<00:50, 2.98s/it] 73%|███████▎ | 44/60 [02:20<00:45, 2.85s/it] 75%|███████▌ | 45/60 [02:23<00:41, 2.76s/it] 77%|███████▋ | 46/60 [02:26<00:39, 2.83s/it] 78%|███████▊ | 47/60 [02:29<00:36, 2.80s/it] 80%|████████ | 48/60 [02:31<00:34, 2.84s/it] 82%|████████▏ | 49/60 [02:34<00:31, 2.83s/it] 83%|████████▎ | 50/60 [02:37<00:28, 2.82s/it] 85%|████████▌ | 51/60 [02:40<00:26, 2.90s/it] 87%|████████▋ | 52/60 [02:43<00:22, 2.75s/it] 88%|████████▊ | 53/60 [02:46<00:19, 2.81s/it] 90%|█████████ | 54/60 [02:48<00:16, 2.72s/it] 92%|█████████▏| 55/60 [02:51<00:13, 2.78s/it] 93%|█████████▎| 56/60 [02:54<00:11, 2.75s/it] 95%|█████████▌| 57/60 [02:57<00:08, 2.85s/it] 97%|█████████▋| 58/60 [02:59<00:05, 2.74s/it] 98%|█████████▊| 59/60 [03:01<00:02, 2.46s/it] 100%|██████████| 60/60 [03:03<00:00, 2.17s/it] 100%|██████████| 60/60 [03:03<00:00, 3.05s/it] Decoding latents in cuda:0... done in 2.88s Move latents to cpu... done in 0.03s