tungsten-logo
Sign In
Halcyon SDXL
Halcyon SDXL

Halcyon SDXL

20 stars
Version: v1.4
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/65faf2d968d94b8abe1551e65ca0abe2/00000-1175959914.webp
https://files.tungsten.run/uploads/960e5f12970c47fd9fbcc53b0650325d/00001-1175959915.webp
https://files.tungsten.run/uploads/b80adefc4a0b416784cdd2eb3d6d0af1/00002-1175959916.webp
This example was created by sparks
Finished in 107.4 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: demonic, spooky, scary shadow figure young beautiful sexy woman emerging from the darkness wearing a sheer flowing transparent dress, cinematic color grading, black and grey gradient, foggy, realistic, 8k, unreal engine, cinematic, walking down the aisle inside of a (crowded:1.2) 1940's passenger train car full of people, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:02<01:28, 2.60s/it] 6%|▌ | 2/35 [00:05<01:36, 2.93s/it] 9%|▊ | 3/35 [00:08<01:37, 3.04s/it] 11%|█▏ | 4/35 [00:12<01:36, 3.13s/it] 14%|█▍ | 5/35 [00:15<01:34, 3.15s/it] 17%|█▋ | 6/35 [00:18<01:35, 3.28s/it] 20%|██ | 7/35 [00:22<01:32, 3.29s/it] 23%|██▎ | 8/35 [00:25<01:28, 3.29s/it] 26%|██▌ | 9/35 [00:28<01:25, 3.30s/it] 29%|██▊ | 10/35 [00:31<01:19, 3.19s/it] 31%|███▏ | 11/35 [00:34<01:16, 3.19s/it] 34%|███▍ | 12/35 [00:38<01:14, 3.22s/it] 37%|███▋ | 13/35 [00:41<01:11, 3.23s/it] 40%|████ | 14/35 [00:44<01:08, 3.25s/it] 43%|████▎ | 15/35 [00:47<01:03, 3.16s/it] 46%|████▌ | 16/35 [00:51<01:00, 3.19s/it] 49%|████▊ | 17/35 [00:54<00:57, 3.22s/it] 51%|█████▏ | 18/35 [00:57<00:52, 3.11s/it] 54%|█████▍ | 19/35 [01:00<00:50, 3.13s/it] 57%|█████▋ | 20/35 [01:03<00:47, 3.19s/it] 60%|██████ | 21/35 [01:06<00:43, 3.13s/it] 63%|██████▎ | 22/35 [01:09<00:38, 2.92s/it] 66%|██████▌ | 23/35 [01:11<00:33, 2.83s/it] 69%|██████▊ | 24/35 [01:14<00:30, 2.80s/it] 71%|███████▏ | 25/35 [01:17<00:29, 2.91s/it] 74%|███████▍ | 26/35 [01:20<00:27, 3.01s/it] 77%|███████▋ | 27/35 [01:23<00:23, 2.99s/it] 80%|████████ | 28/35 [01:26<00:20, 2.95s/it] 83%|████████▎ | 29/35 [01:29<00:17, 2.88s/it] 86%|████████▌ | 30/35 [01:32<00:14, 2.85s/it] 89%|████████▊ | 31/35 [01:35<00:11, 2.87s/it] 91%|█████████▏| 32/35 [01:37<00:08, 2.82s/it] 94%|█████████▍| 33/35 [01:40<00:05, 2.72s/it] 97%|█████████▋| 34/35 [01:41<00:02, 2.42s/it] 100%|██████████| 35/35 [01:43<00:00, 2.13s/it] 100%|██████████| 35/35 [01:43<00:00, 2.96s/it] Decoding latents in cuda:0... done in 2.84s 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/65faf2d968d94b8abe1551e65ca0abe2/00000-1175959914.webp
https://files.tungsten.run/uploads/960e5f12970c47fd9fbcc53b0650325d/00001-1175959915.webp
https://files.tungsten.run/uploads/b80adefc4a0b416784cdd2eb3d6d0af1/00002-1175959916.webp
This example was created by sparks
Finished in 107.4 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: demonic, spooky, scary shadow figure young beautiful sexy woman emerging from the darkness wearing a sheer flowing transparent dress, cinematic color grading, black and grey gradient, foggy, realistic, 8k, unreal engine, cinematic, walking down the aisle inside of a (crowded:1.2) 1940's passenger train car full of people, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:02<01:28, 2.60s/it] 6%|▌ | 2/35 [00:05<01:36, 2.93s/it] 9%|▊ | 3/35 [00:08<01:37, 3.04s/it] 11%|█▏ | 4/35 [00:12<01:36, 3.13s/it] 14%|█▍ | 5/35 [00:15<01:34, 3.15s/it] 17%|█▋ | 6/35 [00:18<01:35, 3.28s/it] 20%|██ | 7/35 [00:22<01:32, 3.29s/it] 23%|██▎ | 8/35 [00:25<01:28, 3.29s/it] 26%|██▌ | 9/35 [00:28<01:25, 3.30s/it] 29%|██▊ | 10/35 [00:31<01:19, 3.19s/it] 31%|███▏ | 11/35 [00:34<01:16, 3.19s/it] 34%|███▍ | 12/35 [00:38<01:14, 3.22s/it] 37%|███▋ | 13/35 [00:41<01:11, 3.23s/it] 40%|████ | 14/35 [00:44<01:08, 3.25s/it] 43%|████▎ | 15/35 [00:47<01:03, 3.16s/it] 46%|████▌ | 16/35 [00:51<01:00, 3.19s/it] 49%|████▊ | 17/35 [00:54<00:57, 3.22s/it] 51%|█████▏ | 18/35 [00:57<00:52, 3.11s/it] 54%|█████▍ | 19/35 [01:00<00:50, 3.13s/it] 57%|█████▋ | 20/35 [01:03<00:47, 3.19s/it] 60%|██████ | 21/35 [01:06<00:43, 3.13s/it] 63%|██████▎ | 22/35 [01:09<00:38, 2.92s/it] 66%|██████▌ | 23/35 [01:11<00:33, 2.83s/it] 69%|██████▊ | 24/35 [01:14<00:30, 2.80s/it] 71%|███████▏ | 25/35 [01:17<00:29, 2.91s/it] 74%|███████▍ | 26/35 [01:20<00:27, 3.01s/it] 77%|███████▋ | 27/35 [01:23<00:23, 2.99s/it] 80%|████████ | 28/35 [01:26<00:20, 2.95s/it] 83%|████████▎ | 29/35 [01:29<00:17, 2.88s/it] 86%|████████▌ | 30/35 [01:32<00:14, 2.85s/it] 89%|████████▊ | 31/35 [01:35<00:11, 2.87s/it] 91%|█████████▏| 32/35 [01:37<00:08, 2.82s/it] 94%|█████████▍| 33/35 [01:40<00:05, 2.72s/it] 97%|█████████▋| 34/35 [01:41<00:02, 2.42s/it] 100%|██████████| 35/35 [01:43<00:00, 2.13s/it] 100%|██████████| 35/35 [01:43<00:00, 2.96s/it] Decoding latents in cuda:0... done in 2.84s Move latents to cpu... done in 0.03s