tungsten-logo
Sign In
Halcyon SDXL
Halcyon SDXL

Halcyon SDXL

20 stars
Version: v1.5
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/93064aa9283d4e12b87889e2fdb074b1/00000-1373078131.webp
https://files.tungsten.run/uploads/0f20994d80f940438c8e94edfaa61809/00001-1373078132.webp
https://files.tungsten.run/uploads/42e32fe1e0774373a3ae0c8093d05e7e/00002-1373078133.webp
This example was created by sparks
Finished in 57.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: adorable fluffy mouse pirate eyepatch, Scene from Rambo movie, mouse in the jungle, explosion, action scene, war chronicles, award winning masterpiece 8k artstation, cinematic, cinematic color grading, heroic, epic, <lora:add-detail-xl:1.0> Full negative prompt: cartoon, cgi, drawing, sketch, low quality, 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:02<01:19, 2.75s/it] 7%|▋ | 2/30 [00:04<00:57, 2.06s/it] 10%|█ | 3/30 [00:05<00:49, 1.83s/it] 13%|█▎ | 4/30 [00:07<00:44, 1.73s/it] 17%|█▋ | 5/30 [00:09<00:41, 1.67s/it] 20%|██ | 6/30 [00:10<00:39, 1.64s/it] 23%|██▎ | 7/30 [00:12<00:37, 1.62s/it] 27%|██▋ | 8/30 [00:13<00:35, 1.61s/it] 30%|███ | 9/30 [00:15<00:33, 1.60s/it] 33%|███▎ | 10/30 [00:16<00:32, 1.60s/it] 37%|███▋ | 11/30 [00:18<00:30, 1.60s/it] 40%|████ | 12/30 [00:20<00:28, 1.60s/it] 43%|████▎ | 13/30 [00:21<00:27, 1.60s/it] 47%|████▋ | 14/30 [00:23<00:25, 1.60s/it] 50%|█████ | 15/30 [00:24<00:24, 1.60s/it] 53%|█████▎ | 16/30 [00:26<00:22, 1.61s/it] 57%|█████▋ | 17/30 [00:28<00:20, 1.61s/it] 60%|██████ | 18/30 [00:29<00:19, 1.62s/it] 63%|██████▎ | 19/30 [00:31<00:17, 1.62s/it] 67%|██████▋ | 20/30 [00:33<00:16, 1.62s/it] 70%|███████ | 21/30 [00:34<00:14, 1.63s/it] 73%|███████▎ | 22/30 [00:36<00:13, 1.63s/it] 77%|███████▋ | 23/30 [00:38<00:11, 1.63s/it] 80%|████████ | 24/30 [00:39<00:09, 1.64s/it] 83%|████████▎ | 25/30 [00:41<00:08, 1.64s/it] 87%|████████▋ | 26/30 [00:42<00:06, 1.65s/it] 90%|█████████ | 27/30 [00:44<00:04, 1.65s/it] 93%|█████████▎| 28/30 [00:46<00:03, 1.65s/it] 97%|█████████▋| 29/30 [00:47<00:01, 1.65s/it] 100%|██████████| 30/30 [00:49<00:00, 1.66s/it] 100%|██████████| 30/30 [00:49<00:00, 1.65s/it] Decoding latents in cuda:0... done in 2.96s 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/93064aa9283d4e12b87889e2fdb074b1/00000-1373078131.webp
https://files.tungsten.run/uploads/0f20994d80f940438c8e94edfaa61809/00001-1373078132.webp
https://files.tungsten.run/uploads/42e32fe1e0774373a3ae0c8093d05e7e/00002-1373078133.webp
This example was created by sparks
Finished in 57.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: adorable fluffy mouse pirate eyepatch, Scene from Rambo movie, mouse in the jungle, explosion, action scene, war chronicles, award winning masterpiece 8k artstation, cinematic, cinematic color grading, heroic, epic, <lora:add-detail-xl:1.0> Full negative prompt: cartoon, cgi, drawing, sketch, low quality, 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:02<01:19, 2.75s/it] 7%|▋ | 2/30 [00:04<00:57, 2.06s/it] 10%|█ | 3/30 [00:05<00:49, 1.83s/it] 13%|█▎ | 4/30 [00:07<00:44, 1.73s/it] 17%|█▋ | 5/30 [00:09<00:41, 1.67s/it] 20%|██ | 6/30 [00:10<00:39, 1.64s/it] 23%|██▎ | 7/30 [00:12<00:37, 1.62s/it] 27%|██▋ | 8/30 [00:13<00:35, 1.61s/it] 30%|███ | 9/30 [00:15<00:33, 1.60s/it] 33%|███▎ | 10/30 [00:16<00:32, 1.60s/it] 37%|███▋ | 11/30 [00:18<00:30, 1.60s/it] 40%|████ | 12/30 [00:20<00:28, 1.60s/it] 43%|████▎ | 13/30 [00:21<00:27, 1.60s/it] 47%|████▋ | 14/30 [00:23<00:25, 1.60s/it] 50%|█████ | 15/30 [00:24<00:24, 1.60s/it] 53%|█████▎ | 16/30 [00:26<00:22, 1.61s/it] 57%|█████▋ | 17/30 [00:28<00:20, 1.61s/it] 60%|██████ | 18/30 [00:29<00:19, 1.62s/it] 63%|██████▎ | 19/30 [00:31<00:17, 1.62s/it] 67%|██████▋ | 20/30 [00:33<00:16, 1.62s/it] 70%|███████ | 21/30 [00:34<00:14, 1.63s/it] 73%|███████▎ | 22/30 [00:36<00:13, 1.63s/it] 77%|███████▋ | 23/30 [00:38<00:11, 1.63s/it] 80%|████████ | 24/30 [00:39<00:09, 1.64s/it] 83%|████████▎ | 25/30 [00:41<00:08, 1.64s/it] 87%|████████▋ | 26/30 [00:42<00:06, 1.65s/it] 90%|█████████ | 27/30 [00:44<00:04, 1.65s/it] 93%|█████████▎| 28/30 [00:46<00:03, 1.65s/it] 97%|█████████▋| 29/30 [00:47<00:01, 1.65s/it] 100%|██████████| 30/30 [00:49<00:00, 1.66s/it] 100%|██████████| 30/30 [00:49<00:00, 1.65s/it] Decoding latents in cuda:0... done in 2.96s Move latents to cpu... done in 0.04s