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/bbe1aeb73e674cedaa42e75c5b71bc52/00000-1100813483.webp
https://files.tungsten.run/uploads/f47214b5dc024d9e8b7d326555b4e94e/00001-1100813484.webp
https://files.tungsten.run/uploads/2024d80e02b74e37823f366ee6062a02/00002-1100813485.webp
This example was created by sparks
Finished in 53.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: 4K photograph, full body, Cinematic scene of Rex the toy tyrannosaurus from Toy Story, heroic, happy, smiling, green, epic, (cinematic:1.1), (cinematic color grading:1.2), detailed textures, fuji cinestill, sunset, backlit, dark moody lighting, evening, light leaks, lens flare, HDR, <lora:add-detail-xl:1.0> Full negative prompt: cartoon, cgi, mandalorian, drawing, child, painting, zombie, headphones, cropped, close-up, mustache , low quality, poor quality, bad art, bright, daylight, plastic, toy, sharp teeth, claws 0%| | 0/27 [00:00<?, ?it/s] 4%|▎ | 1/27 [00:02<01:09, 2.68s/it] 7%|▋ | 2/27 [00:04<00:51, 2.08s/it] 11%|█ | 3/27 [00:05<00:45, 1.88s/it] 15%|█▍ | 4/27 [00:07<00:41, 1.79s/it] 19%|█▊ | 5/27 [00:09<00:38, 1.74s/it] 22%|██▏ | 6/27 [00:10<00:35, 1.71s/it] 26%|██▌ | 7/27 [00:12<00:33, 1.70s/it] 30%|██▉ | 8/27 [00:14<00:32, 1.69s/it] 33%|███▎ | 9/27 [00:15<00:30, 1.68s/it] 37%|███▋ | 10/27 [00:17<00:28, 1.68s/it] 41%|████ | 11/27 [00:19<00:26, 1.68s/it] 44%|████▍ | 12/27 [00:21<00:25, 1.68s/it] 48%|████▊ | 13/27 [00:22<00:23, 1.68s/it] 52%|█████▏ | 14/27 [00:24<00:21, 1.68s/it] 56%|█████▌ | 15/27 [00:26<00:20, 1.68s/it] 59%|█████▉ | 16/27 [00:27<00:18, 1.68s/it] 63%|██████▎ | 17/27 [00:29<00:16, 1.67s/it] 67%|██████▋ | 18/27 [00:31<00:14, 1.67s/it] 70%|███████ | 19/27 [00:32<00:13, 1.66s/it] 74%|███████▍ | 20/27 [00:34<00:11, 1.66s/it] 78%|███████▊ | 21/27 [00:35<00:09, 1.66s/it] 81%|████████▏ | 22/27 [00:37<00:08, 1.65s/it] 85%|████████▌ | 23/27 [00:39<00:06, 1.65s/it] 89%|████████▉ | 24/27 [00:40<00:04, 1.65s/it] 93%|█████████▎| 25/27 [00:42<00:03, 1.64s/it] 96%|█████████▋| 26/27 [00:44<00:01, 1.64s/it] 100%|██████████| 27/27 [00:45<00:00, 1.64s/it] 100%|██████████| 27/27 [00:45<00:00, 1.70s/it] Decoding latents in cuda:0... done in 2.88s 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/bbe1aeb73e674cedaa42e75c5b71bc52/00000-1100813483.webp
https://files.tungsten.run/uploads/f47214b5dc024d9e8b7d326555b4e94e/00001-1100813484.webp
https://files.tungsten.run/uploads/2024d80e02b74e37823f366ee6062a02/00002-1100813485.webp
This example was created by sparks
Finished in 53.1 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: 4K photograph, full body, Cinematic scene of Rex the toy tyrannosaurus from Toy Story, heroic, happy, smiling, green, epic, (cinematic:1.1), (cinematic color grading:1.2), detailed textures, fuji cinestill, sunset, backlit, dark moody lighting, evening, light leaks, lens flare, HDR, <lora:add-detail-xl:1.0> Full negative prompt: cartoon, cgi, mandalorian, drawing, child, painting, zombie, headphones, cropped, close-up, mustache , low quality, poor quality, bad art, bright, daylight, plastic, toy, sharp teeth, claws 0%| | 0/27 [00:00<?, ?it/s] 4%|▎ | 1/27 [00:02<01:09, 2.68s/it] 7%|▋ | 2/27 [00:04<00:51, 2.08s/it] 11%|█ | 3/27 [00:05<00:45, 1.88s/it] 15%|█▍ | 4/27 [00:07<00:41, 1.79s/it] 19%|█▊ | 5/27 [00:09<00:38, 1.74s/it] 22%|██▏ | 6/27 [00:10<00:35, 1.71s/it] 26%|██▌ | 7/27 [00:12<00:33, 1.70s/it] 30%|██▉ | 8/27 [00:14<00:32, 1.69s/it] 33%|███▎ | 9/27 [00:15<00:30, 1.68s/it] 37%|███▋ | 10/27 [00:17<00:28, 1.68s/it] 41%|████ | 11/27 [00:19<00:26, 1.68s/it] 44%|████▍ | 12/27 [00:21<00:25, 1.68s/it] 48%|████▊ | 13/27 [00:22<00:23, 1.68s/it] 52%|█████▏ | 14/27 [00:24<00:21, 1.68s/it] 56%|█████▌ | 15/27 [00:26<00:20, 1.68s/it] 59%|█████▉ | 16/27 [00:27<00:18, 1.68s/it] 63%|██████▎ | 17/27 [00:29<00:16, 1.67s/it] 67%|██████▋ | 18/27 [00:31<00:14, 1.67s/it] 70%|███████ | 19/27 [00:32<00:13, 1.66s/it] 74%|███████▍ | 20/27 [00:34<00:11, 1.66s/it] 78%|███████▊ | 21/27 [00:35<00:09, 1.66s/it] 81%|████████▏ | 22/27 [00:37<00:08, 1.65s/it] 85%|████████▌ | 23/27 [00:39<00:06, 1.65s/it] 89%|████████▉ | 24/27 [00:40<00:04, 1.65s/it] 93%|█████████▎| 25/27 [00:42<00:03, 1.64s/it] 96%|█████████▋| 26/27 [00:44<00:01, 1.64s/it] 100%|██████████| 27/27 [00:45<00:00, 1.64s/it] 100%|██████████| 27/27 [00:45<00:00, 1.70s/it] Decoding latents in cuda:0... done in 2.88s Move latents to cpu... done in 0.04s