tungsten-logo
Sign In
Female HALO Soldier with savsdxl
savsdxl:v5.2.3
sparks
sparks
·
Mar 19
318
Input
prompt
Specify things to see in the output
sci-fi skin HALO, a character in a futuristic suit with glowing visor, sigma female, titanium armor, andree wallin, concept art|feng zhu, artstyle andree wallin, artgerm, 3d unreal engine, olchas logan cure liang xing, hard surface character pinterest, 4 k portrait, loba andrade from apex legends
negative_prompt
Specify things to not see in the output
nipples,
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0.5
num_outputs
Number of output images
3
width
Output image width
1280
height
Output image height
1280
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
1
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
3047622940
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M SDE Heun Exponential
samping_steps
Number of denoising steps
48
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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.
false
Output
https://files.tungsten.run/uploads/1658358834284f6c856c8422d3623d95/00000-3047622940.webp
https://files.tungsten.run/uploads/c00f6b8e83c04d6d9d4431575e04963f/00001-3047622941.webp
https://files.tungsten.run/uploads/3b33451c7f564ad290d45af205defa07/00002-3047622942.webp
Finished in 206.3 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: sci-fi skin HALO, a character in a futuristic suit with glowing visor, sigma female, titanium armor, andree wallin, concept art|feng zhu, artstyle andree wallin, artgerm, 3d unreal engine, olchas logan cure liang xing, hard surface character pinterest, 4 k portrait, loba andrade from apex legends, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: nipples, 0%| | 0/48 [00:00<?, ?it/s] 2%|▏ | 1/48 [00:05<04:00, 5.12s/it] 4%|▍ | 2/48 [00:09<03:33, 4.65s/it] 6%|▋ | 3/48 [00:13<03:23, 4.53s/it] 8%|▊ | 4/48 [00:18<03:23, 4.62s/it] 10%|█ | 5/48 [00:23<03:18, 4.61s/it] 12%|█▎ | 6/48 [00:27<03:13, 4.60s/it] 15%|█▍ | 7/48 [00:34<03:31, 5.15s/it] 17%|█▋ | 8/48 [00:38<03:19, 4.98s/it] 19%|█▉ | 9/48 [00:42<03:06, 4.78s/it] 21%|██ | 10/48 [00:47<02:57, 4.68s/it] 23%|██▎ | 11/48 [00:51<02:44, 4.45s/it] 25%|██▌ | 12/48 [00:55<02:31, 4.21s/it] 27%|██▋ | 13/48 [00:59<02:27, 4.22s/it] 29%|██▉ | 14/48 [01:03<02:23, 4.21s/it] 31%|███▏ | 15/48 [01:08<02:24, 4.37s/it] 33%|███▎ | 16/48 [01:13<02:23, 4.50s/it] 35%|███▌ | 17/48 [01:17<02:15, 4.38s/it] 38%|███▊ | 18/48 [01:21<02:10, 4.36s/it] 40%|███▉ | 19/48 [01:25<02:03, 4.27s/it] 42%|████▏ | 20/48 [01:29<01:59, 4.25s/it] 44%|████▍ | 21/48 [01:34<01:57, 4.34s/it] 46%|████▌ | 22/48 [01:38<01:50, 4.23s/it] 48%|████▊ | 23/48 [01:42<01:46, 4.28s/it] 50%|█████ | 24/48 [01:46<01:40, 4.20s/it] 52%|█████▏ | 25/48 [01:50<01:36, 4.19s/it] 54%|█████▍ | 26/48 [01:55<01:33, 4.25s/it] 56%|█████▋ | 27/48 [01:59<01:26, 4.13s/it] 58%|█████▊ | 28/48 [02:02<01:20, 4.02s/it] 60%|██████ | 29/48 [02:06<01:15, 3.99s/it] 62%|██████▎ | 30/48 [02:10<01:12, 4.05s/it] 65%|██████▍ | 31/48 [02:15<01:09, 4.10s/it] 67%|██████▋ | 32/48 [02:19<01:05, 4.08s/it] 69%|██████▉ | 33/48 [02:23<01:00, 4.04s/it] 71%|███████ | 34/48 [02:26<00:55, 3.98s/it] 73%|███████▎ | 35/48 [02:30<00:51, 3.95s/it] 75%|███████▌ | 36/48 [02:34<00:45, 3.79s/it] 77%|███████▋ | 37/48 [02:37<00:41, 3.76s/it] 79%|███████▉ | 38/48 [02:41<00:35, 3.59s/it] 81%|████████▏ | 39/48 [02:45<00:33, 3.77s/it] 83%|████████▎ | 40/48 [02:48<00:29, 3.67s/it] 85%|████████▌ | 41/48 [02:52<00:26, 3.82s/it] 88%|████████▊ | 42/48 [02:56<00:22, 3.78s/it] 90%|████████▉ | 43/48 [03:00<00:18, 3.71s/it] 92%|█████████▏| 44/48 [03:04<00:15, 3.79s/it] 94%|█████████▍| 45/48 [03:07<00:11, 3.69s/it] 96%|█████████▌| 46/48 [03:11<00:07, 3.77s/it] 98%|█████████▊| 47/48 [03:13<00:03, 3.34s/it] 100%|██████████| 48/48 [03:16<00:00, 2.97s/it] 100%|██████████| 48/48 [03:16<00:00, 4.08s/it] Decoding latents in cuda:0... done in 3.88s Move latents to cpu... done in 0.05s Uploading outputs... Finished.
prompt
Specify things to see in the output
sci-fi skin HALO, a character in a futuristic suit with glowing visor, sigma female, titanium armor, andree wallin, concept art|feng zhu, artstyle andree wallin, artgerm, 3d unreal engine, olchas logan cure liang xing, hard surface character pinterest, 4 k portrait, loba andrade from apex legends
negative_prompt
Specify things to not see in the output
nipples,
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0.5
num_outputs
Number of output images
3
width
Output image width
1280
height
Output image height
1280
enhance_face_with_adetailer
Enhance face with adetailer
false
enhance_hands_with_adetailer
Enhance hands with adetailer
false
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.55
detail
Enhance/diminish detail while keeping the overall style/character
1
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
3047622940
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M SDE Heun Exponential
samping_steps
Number of denoising steps
48
cfg_scale
Scale for classifier-free guidance
7
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
sdxl_vae.safetensors
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.
false
https://files.tungsten.run/uploads/1658358834284f6c856c8422d3623d95/00000-3047622940.webp
https://files.tungsten.run/uploads/c00f6b8e83c04d6d9d4431575e04963f/00001-3047622941.webp
https://files.tungsten.run/uploads/3b33451c7f564ad290d45af205defa07/00002-3047622942.webp
Finished in 206.3 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: sci-fi skin HALO, a character in a futuristic suit with glowing visor, sigma female, titanium armor, andree wallin, concept art|feng zhu, artstyle andree wallin, artgerm, 3d unreal engine, olchas logan cure liang xing, hard surface character pinterest, 4 k portrait, loba andrade from apex legends, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: nipples, 0%| | 0/48 [00:00<?, ?it/s] 2%|▏ | 1/48 [00:05<04:00, 5.12s/it] 4%|▍ | 2/48 [00:09<03:33, 4.65s/it] 6%|▋ | 3/48 [00:13<03:23, 4.53s/it] 8%|▊ | 4/48 [00:18<03:23, 4.62s/it] 10%|█ | 5/48 [00:23<03:18, 4.61s/it] 12%|█▎ | 6/48 [00:27<03:13, 4.60s/it] 15%|█▍ | 7/48 [00:34<03:31, 5.15s/it] 17%|█▋ | 8/48 [00:38<03:19, 4.98s/it] 19%|█▉ | 9/48 [00:42<03:06, 4.78s/it] 21%|██ | 10/48 [00:47<02:57, 4.68s/it] 23%|██▎ | 11/48 [00:51<02:44, 4.45s/it] 25%|██▌ | 12/48 [00:55<02:31, 4.21s/it] 27%|██▋ | 13/48 [00:59<02:27, 4.22s/it] 29%|██▉ | 14/48 [01:03<02:23, 4.21s/it] 31%|███▏ | 15/48 [01:08<02:24, 4.37s/it] 33%|███▎ | 16/48 [01:13<02:23, 4.50s/it] 35%|███▌ | 17/48 [01:17<02:15, 4.38s/it] 38%|███▊ | 18/48 [01:21<02:10, 4.36s/it] 40%|███▉ | 19/48 [01:25<02:03, 4.27s/it] 42%|████▏ | 20/48 [01:29<01:59, 4.25s/it] 44%|████▍ | 21/48 [01:34<01:57, 4.34s/it] 46%|████▌ | 22/48 [01:38<01:50, 4.23s/it] 48%|████▊ | 23/48 [01:42<01:46, 4.28s/it] 50%|█████ | 24/48 [01:46<01:40, 4.20s/it] 52%|█████▏ | 25/48 [01:50<01:36, 4.19s/it] 54%|█████▍ | 26/48 [01:55<01:33, 4.25s/it] 56%|█████▋ | 27/48 [01:59<01:26, 4.13s/it] 58%|█████▊ | 28/48 [02:02<01:20, 4.02s/it] 60%|██████ | 29/48 [02:06<01:15, 3.99s/it] 62%|██████▎ | 30/48 [02:10<01:12, 4.05s/it] 65%|██████▍ | 31/48 [02:15<01:09, 4.10s/it] 67%|██████▋ | 32/48 [02:19<01:05, 4.08s/it] 69%|██████▉ | 33/48 [02:23<01:00, 4.04s/it] 71%|███████ | 34/48 [02:26<00:55, 3.98s/it] 73%|███████▎ | 35/48 [02:30<00:51, 3.95s/it] 75%|███████▌ | 36/48 [02:34<00:45, 3.79s/it] 77%|███████▋ | 37/48 [02:37<00:41, 3.76s/it] 79%|███████▉ | 38/48 [02:41<00:35, 3.59s/it] 81%|████████▏ | 39/48 [02:45<00:33, 3.77s/it] 83%|████████▎ | 40/48 [02:48<00:29, 3.67s/it] 85%|████████▌ | 41/48 [02:52<00:26, 3.82s/it] 88%|████████▊ | 42/48 [02:56<00:22, 3.78s/it] 90%|████████▉ | 43/48 [03:00<00:18, 3.71s/it] 92%|█████████▏| 44/48 [03:04<00:15, 3.79s/it] 94%|█████████▍| 45/48 [03:07<00:11, 3.69s/it] 96%|█████████▌| 46/48 [03:11<00:07, 3.77s/it] 98%|█████████▊| 47/48 [03:13<00:03, 3.34s/it] 100%|██████████| 48/48 [03:16<00:00, 2.97s/it] 100%|██████████| 48/48 [03:16<00:00, 4.08s/it] Decoding latents in cuda:0... done in 3.88s Move latents to cpu... done in 0.05s Uploading outputs... Finished.