tungsten-logo
Sign In
Silverstar XL
Silverstar XL

Silverstar XL

10 stars
Version: v4.0
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/c12ed9caedc84d35899bffb671bbd743/00000-3843984014.webp
https://files.tungsten.run/uploads/a56eaf4d38c04e2ea5007a87964b52b8/00001-3843984015.webp
https://files.tungsten.run/uploads/1194b26b9cb543bf91a3152b787c0e94/00002-3843984016.webp
This example was created by sparks
Finished in 88.2 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: street photography of a young adult man, emo, very detailed, waving, (perfectly-lit, crisp focus, absurdres, 8k UHD, HDR, vivid color, depth of field, contrast, clarity, balance), <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: painting, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, poorly, badly, poor, horrible, horribly, disproportion, fused, uneven, monochrome, ugly, ugliest, hideous, crappy, cropped, crop, doodle, sketch, preview, jpeg, compression artifacts 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:02<01:10, 2.44s/it] 7%|▋ | 2/30 [00:05<01:19, 2.83s/it] 10%|█ | 3/30 [00:08<01:19, 2.93s/it] 13%|█▎ | 4/30 [00:11<01:19, 3.06s/it] 17%|█▋ | 5/30 [00:14<01:15, 3.03s/it] 20%|██ | 6/30 [00:17<01:13, 3.05s/it] 23%|██▎ | 7/30 [00:21<01:12, 3.15s/it] 27%|██▋ | 8/30 [00:24<01:07, 3.05s/it] 30%|███ | 9/30 [00:26<01:02, 2.98s/it] 33%|███▎ | 10/30 [00:29<01:00, 3.00s/it] 37%|███▋ | 11/30 [00:33<00:57, 3.04s/it] 40%|████ | 12/30 [00:36<00:54, 3.01s/it] 43%|████▎ | 13/30 [00:39<00:51, 3.03s/it] 47%|████▋ | 14/30 [00:42<00:49, 3.07s/it] 50%|█████ | 15/30 [00:45<00:45, 3.07s/it] 53%|█████▎ | 16/30 [00:48<00:41, 2.99s/it] 57%|█████▋ | 17/30 [00:51<00:38, 2.99s/it] 60%|██████ | 18/30 [00:54<00:35, 2.96s/it] 63%|██████▎ | 19/30 [00:56<00:32, 2.94s/it] 67%|██████▋ | 20/30 [00:59<00:29, 2.97s/it] 70%|███████ | 21/30 [01:02<00:26, 2.94s/it] 73%|███████▎ | 22/30 [01:05<00:22, 2.81s/it] 77%|███████▋ | 23/30 [01:08<00:19, 2.79s/it] 80%|████████ | 24/30 [01:10<00:16, 2.76s/it] 83%|████████▎ | 25/30 [01:13<00:13, 2.80s/it] 87%|████████▋ | 26/30 [01:16<00:11, 2.76s/it] 90%|█████████ | 27/30 [01:19<00:08, 2.74s/it] 93%|█████████▎| 28/30 [01:21<00:05, 2.67s/it] 97%|█████████▋| 29/30 [01:23<00:02, 2.35s/it] 100%|██████████| 30/30 [01:24<00:00, 2.08s/it] 100%|██████████| 30/30 [01:24<00:00, 2.82s/it] Decoding latents in cuda:0... done in 2.72s Move latents to cpu... done in 0.02s
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/c12ed9caedc84d35899bffb671bbd743/00000-3843984014.webp
https://files.tungsten.run/uploads/a56eaf4d38c04e2ea5007a87964b52b8/00001-3843984015.webp
https://files.tungsten.run/uploads/1194b26b9cb543bf91a3152b787c0e94/00002-3843984016.webp
This example was created by sparks
Finished in 88.2 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: street photography of a young adult man, emo, very detailed, waving, (perfectly-lit, crisp focus, absurdres, 8k UHD, HDR, vivid color, depth of field, contrast, clarity, balance), <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: painting, drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, poorly, badly, poor, horrible, horribly, disproportion, fused, uneven, monochrome, ugly, ugliest, hideous, crappy, cropped, crop, doodle, sketch, preview, jpeg, compression artifacts 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:02<01:10, 2.44s/it] 7%|▋ | 2/30 [00:05<01:19, 2.83s/it] 10%|█ | 3/30 [00:08<01:19, 2.93s/it] 13%|█▎ | 4/30 [00:11<01:19, 3.06s/it] 17%|█▋ | 5/30 [00:14<01:15, 3.03s/it] 20%|██ | 6/30 [00:17<01:13, 3.05s/it] 23%|██▎ | 7/30 [00:21<01:12, 3.15s/it] 27%|██▋ | 8/30 [00:24<01:07, 3.05s/it] 30%|███ | 9/30 [00:26<01:02, 2.98s/it] 33%|███▎ | 10/30 [00:29<01:00, 3.00s/it] 37%|███▋ | 11/30 [00:33<00:57, 3.04s/it] 40%|████ | 12/30 [00:36<00:54, 3.01s/it] 43%|████▎ | 13/30 [00:39<00:51, 3.03s/it] 47%|████▋ | 14/30 [00:42<00:49, 3.07s/it] 50%|█████ | 15/30 [00:45<00:45, 3.07s/it] 53%|█████▎ | 16/30 [00:48<00:41, 2.99s/it] 57%|█████▋ | 17/30 [00:51<00:38, 2.99s/it] 60%|██████ | 18/30 [00:54<00:35, 2.96s/it] 63%|██████▎ | 19/30 [00:56<00:32, 2.94s/it] 67%|██████▋ | 20/30 [00:59<00:29, 2.97s/it] 70%|███████ | 21/30 [01:02<00:26, 2.94s/it] 73%|███████▎ | 22/30 [01:05<00:22, 2.81s/it] 77%|███████▋ | 23/30 [01:08<00:19, 2.79s/it] 80%|████████ | 24/30 [01:10<00:16, 2.76s/it] 83%|████████▎ | 25/30 [01:13<00:13, 2.80s/it] 87%|████████▋ | 26/30 [01:16<00:11, 2.76s/it] 90%|█████████ | 27/30 [01:19<00:08, 2.74s/it] 93%|█████████▎| 28/30 [01:21<00:05, 2.67s/it] 97%|█████████▋| 29/30 [01:23<00:02, 2.35s/it] 100%|██████████| 30/30 [01:24<00:00, 2.08s/it] 100%|██████████| 30/30 [01:24<00:00, 2.82s/it] Decoding latents in cuda:0... done in 2.72s Move latents to cpu... done in 0.02s