tungsten-logo
Sign In
savsdxl
savsdxl

savsdxl

2 stars
Version: v5.2.3
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/8556b77137e0420d917d2c1bb6230b8f/00000-4217923931.webp
https://files.tungsten.run/uploads/b4d8a8ad409c4eb59478118bdadf192c/00001-4217923932.webp
https://files.tungsten.run/uploads/f60f478f7c494e7dad09a1763542055a/00002-4217923933.webp
This example was created by sparks
Finished in 117.5 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a woman in a fur coat holding a rifle, concept art by senior character artist, cgsociety, antipodeans, cgsociety 9, loba andrade from apex legends, alita battle angel, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: simplified, low resolution, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, disconnected limbs, mutation, mutated, ugly, disgusting, cropped, (worst quality, low quality:1.4), text, watermark, signature, logo, (mutated hands and fingers:1.10), open mouth, teeth, blurry, Asian, abstract, unrealistic, impressionistic, black and white, b&w, anime, 3D render, cartoon, (ears:0.1), (human ear:1.4) 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:03<02:53, 3.55s/it] 4%|▍ | 2/50 [00:05<02:09, 2.69s/it] 6%|▌ | 3/50 [00:07<01:54, 2.43s/it] 8%|▊ | 4/50 [00:09<01:45, 2.30s/it] 10%|█ | 5/50 [00:11<01:40, 2.23s/it] 12%|█▏ | 6/50 [00:14<01:36, 2.20s/it] 14%|█▍ | 7/50 [00:16<01:33, 2.16s/it] 16%|█▌ | 8/50 [00:18<01:30, 2.15s/it] 18%|█▊ | 9/50 [00:20<01:27, 2.14s/it] 20%|██ | 10/50 [00:22<01:25, 2.13s/it] 22%|██▏ | 11/50 [00:24<01:23, 2.13s/it] 24%|██▍ | 12/50 [00:26<01:20, 2.13s/it] 26%|██▌ | 13/50 [00:28<01:18, 2.13s/it] 28%|██▊ | 14/50 [00:31<01:16, 2.13s/it] 30%|███ | 15/50 [00:33<01:14, 2.14s/it] 32%|███▏ | 16/50 [00:35<01:12, 2.14s/it] 34%|███▍ | 17/50 [00:37<01:10, 2.14s/it] 36%|███▌ | 18/50 [00:39<01:08, 2.14s/it] 38%|███▊ | 19/50 [00:41<01:06, 2.14s/it] 40%|████ | 20/50 [00:43<01:04, 2.13s/it] 42%|████▏ | 21/50 [00:46<01:01, 2.13s/it] 44%|████▍ | 22/50 [00:48<00:59, 2.13s/it] 46%|████▌ | 23/50 [00:50<00:57, 2.13s/it] 48%|████▊ | 24/50 [00:52<00:55, 2.13s/it] 50%|█████ | 25/50 [00:54<00:53, 2.13s/it] 52%|█████▏ | 26/50 [00:56<00:50, 2.12s/it] 54%|█████▍ | 27/50 [00:58<00:48, 2.12s/it] 56%|█████▌ | 28/50 [01:00<00:46, 2.12s/it] 58%|█████▊ | 29/50 [01:03<00:44, 2.12s/it] 60%|██████ | 30/50 [01:05<00:42, 2.12s/it] 62%|██████▏ | 31/50 [01:07<00:40, 2.12s/it] 64%|██████▍ | 32/50 [01:09<00:38, 2.12s/it] 66%|██████▌ | 33/50 [01:11<00:36, 2.12s/it] 68%|██████▊ | 34/50 [01:13<00:33, 2.12s/it] 70%|███████ | 35/50 [01:15<00:31, 2.12s/it] 72%|███████▏ | 36/50 [01:17<00:29, 2.12s/it] 74%|███████▍ | 37/50 [01:19<00:27, 2.11s/it] 76%|███████▌ | 38/50 [01:22<00:25, 2.12s/it] 78%|███████▊ | 39/50 [01:24<00:23, 2.12s/it] 80%|████████ | 40/50 [01:26<00:21, 2.11s/it] 82%|████████▏ | 41/50 [01:28<00:19, 2.11s/it] 84%|████████▍ | 42/50 [01:30<00:16, 2.12s/it] 86%|████████▌ | 43/50 [01:32<00:14, 2.12s/it] 88%|████████▊ | 44/50 [01:34<00:12, 2.11s/it] 90%|█████████ | 45/50 [01:36<00:10, 2.11s/it] 92%|█████████▏| 46/50 [01:38<00:08, 2.11s/it] 94%|█████████▍| 47/50 [01:41<00:06, 2.12s/it] 96%|█████████▌| 48/50 [01:43<00:04, 2.12s/it] 98%|█████████▊| 49/50 [01:45<00:02, 2.12s/it] 100%|██████████| 50/50 [01:47<00:00, 2.11s/it] 100%|██████████| 50/50 [01:47<00:00, 2.15s/it] Decoding latents in cuda:0... done in 3.85s Move latents to cpu... done in 0.04s Uploading outputs... Finished.
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/8556b77137e0420d917d2c1bb6230b8f/00000-4217923931.webp
https://files.tungsten.run/uploads/b4d8a8ad409c4eb59478118bdadf192c/00001-4217923932.webp
https://files.tungsten.run/uploads/f60f478f7c494e7dad09a1763542055a/00002-4217923933.webp
This example was created by sparks
Finished in 117.5 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: a woman in a fur coat holding a rifle, concept art by senior character artist, cgsociety, antipodeans, cgsociety 9, loba andrade from apex legends, alita battle angel, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: simplified, low resolution, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, disconnected limbs, mutation, mutated, ugly, disgusting, cropped, (worst quality, low quality:1.4), text, watermark, signature, logo, (mutated hands and fingers:1.10), open mouth, teeth, blurry, Asian, abstract, unrealistic, impressionistic, black and white, b&w, anime, 3D render, cartoon, (ears:0.1), (human ear:1.4) 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:03<02:53, 3.55s/it] 4%|▍ | 2/50 [00:05<02:09, 2.69s/it] 6%|▌ | 3/50 [00:07<01:54, 2.43s/it] 8%|▊ | 4/50 [00:09<01:45, 2.30s/it] 10%|█ | 5/50 [00:11<01:40, 2.23s/it] 12%|█▏ | 6/50 [00:14<01:36, 2.20s/it] 14%|█▍ | 7/50 [00:16<01:33, 2.16s/it] 16%|█▌ | 8/50 [00:18<01:30, 2.15s/it] 18%|█▊ | 9/50 [00:20<01:27, 2.14s/it] 20%|██ | 10/50 [00:22<01:25, 2.13s/it] 22%|██▏ | 11/50 [00:24<01:23, 2.13s/it] 24%|██▍ | 12/50 [00:26<01:20, 2.13s/it] 26%|██▌ | 13/50 [00:28<01:18, 2.13s/it] 28%|██▊ | 14/50 [00:31<01:16, 2.13s/it] 30%|███ | 15/50 [00:33<01:14, 2.14s/it] 32%|███▏ | 16/50 [00:35<01:12, 2.14s/it] 34%|███▍ | 17/50 [00:37<01:10, 2.14s/it] 36%|███▌ | 18/50 [00:39<01:08, 2.14s/it] 38%|███▊ | 19/50 [00:41<01:06, 2.14s/it] 40%|████ | 20/50 [00:43<01:04, 2.13s/it] 42%|████▏ | 21/50 [00:46<01:01, 2.13s/it] 44%|████▍ | 22/50 [00:48<00:59, 2.13s/it] 46%|████▌ | 23/50 [00:50<00:57, 2.13s/it] 48%|████▊ | 24/50 [00:52<00:55, 2.13s/it] 50%|█████ | 25/50 [00:54<00:53, 2.13s/it] 52%|█████▏ | 26/50 [00:56<00:50, 2.12s/it] 54%|█████▍ | 27/50 [00:58<00:48, 2.12s/it] 56%|█████▌ | 28/50 [01:00<00:46, 2.12s/it] 58%|█████▊ | 29/50 [01:03<00:44, 2.12s/it] 60%|██████ | 30/50 [01:05<00:42, 2.12s/it] 62%|██████▏ | 31/50 [01:07<00:40, 2.12s/it] 64%|██████▍ | 32/50 [01:09<00:38, 2.12s/it] 66%|██████▌ | 33/50 [01:11<00:36, 2.12s/it] 68%|██████▊ | 34/50 [01:13<00:33, 2.12s/it] 70%|███████ | 35/50 [01:15<00:31, 2.12s/it] 72%|███████▏ | 36/50 [01:17<00:29, 2.12s/it] 74%|███████▍ | 37/50 [01:19<00:27, 2.11s/it] 76%|███████▌ | 38/50 [01:22<00:25, 2.12s/it] 78%|███████▊ | 39/50 [01:24<00:23, 2.12s/it] 80%|████████ | 40/50 [01:26<00:21, 2.11s/it] 82%|████████▏ | 41/50 [01:28<00:19, 2.11s/it] 84%|████████▍ | 42/50 [01:30<00:16, 2.12s/it] 86%|████████▌ | 43/50 [01:32<00:14, 2.12s/it] 88%|████████▊ | 44/50 [01:34<00:12, 2.11s/it] 90%|█████████ | 45/50 [01:36<00:10, 2.11s/it] 92%|█████████▏| 46/50 [01:38<00:08, 2.11s/it] 94%|█████████▍| 47/50 [01:41<00:06, 2.12s/it] 96%|█████████▌| 48/50 [01:43<00:04, 2.12s/it] 98%|█████████▊| 49/50 [01:45<00:02, 2.12s/it] 100%|██████████| 50/50 [01:47<00:00, 2.11s/it] 100%|██████████| 50/50 [01:47<00:00, 2.15s/it] Decoding latents in cuda:0... done in 3.85s Move latents to cpu... done in 0.04s Uploading outputs... Finished.