tungsten-logo
Sign In
Rosalina in Bikini with Furry Nepotism DPO
Nepotism (SDXL+PONY):DPO
sparks
sparks
·
May 16
16
Input
prompt
Specify things to see in the output
score_9, score_8_up, score_7_up, Rosalina in bikini
negative_prompt
Specify things to not see in the output
score_6, score_5, score_4, ugly face, low res, blurry face, black and white, watermark, bad hands, missing fingers, EasyNegativeV2-SDXL, rating_explicit, bad hands
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0.5
num_outputs
Number of output images
3
width
Output image width
832
height
Output image height
1216
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.
4294967293
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 Karras
samping_steps
Number of denoising steps
45
cfg_scale
Scale for classifier-free guidance
4
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)
EasyNegativeV2-SDXL.safetensors
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/5d1c93ef51844b6e9913d5eceaf0675c/00000-4294967293.webp
https://files.tungsten.run/uploads/d3c7a4c24b054e008ccd3df81e5949b7/00001-4294967294.webp
https://files.tungsten.run/uploads/31bd83a19e77430f8881ad37b70b9c11/00002-4294967295.webp
Finished in 108.7 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: score_9, score_8_up, score_7_up, Rosalina in bikini, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: score_6, score_5, score_4, ugly face, low res, blurry face, black and white, watermark, bad hands, missing fingers, EasyNegativeV2-SDXL, rating_explicit, bad hands 0%| | 0/45 [00:00<?, ?it/s] 2%|▏ | 1/45 [00:01<01:27, 1.99s/it] 4%|▍ | 2/45 [00:04<01:36, 2.25s/it] 7%|▋ | 3/45 [00:07<01:41, 2.41s/it] 9%|▉ | 4/45 [00:09<01:43, 2.51s/it] 11%|█ | 5/45 [00:12<01:38, 2.46s/it] 13%|█▎ | 6/45 [00:14<01:36, 2.48s/it] 16%|█▌ | 7/45 [00:17<01:33, 2.46s/it] 18%|█▊ | 8/45 [00:19<01:32, 2.51s/it] 20%|██ | 9/45 [00:22<01:30, 2.52s/it] 22%|██▏ | 10/45 [00:24<01:28, 2.52s/it] 24%|██▍ | 11/45 [00:27<01:23, 2.47s/it] 27%|██▋ | 12/45 [00:29<01:21, 2.48s/it] 29%|██▉ | 13/45 [00:31<01:18, 2.46s/it] 31%|███ | 14/45 [00:34<01:18, 2.53s/it] 33%|███▎ | 15/45 [00:37<01:15, 2.52s/it] 36%|███▌ | 16/45 [00:39<01:13, 2.55s/it] 38%|███▊ | 17/45 [00:42<01:10, 2.50s/it] 40%|████ | 18/45 [00:44<01:06, 2.46s/it] 42%|████▏ | 19/45 [00:46<01:02, 2.42s/it] 44%|████▍ | 20/45 [00:49<01:01, 2.45s/it] 47%|████▋ | 21/45 [00:51<00:56, 2.36s/it] 49%|████▉ | 22/45 [00:54<00:55, 2.41s/it] 51%|█████ | 23/45 [00:56<00:53, 2.45s/it] 53%|█████▎ | 24/45 [00:58<00:50, 2.40s/it] 56%|█████▌ | 25/45 [01:01<00:48, 2.44s/it] 58%|█████▊ | 26/45 [01:03<00:46, 2.43s/it] 60%|██████ | 27/45 [01:06<00:44, 2.46s/it] 62%|██████▏ | 28/45 [01:08<00:40, 2.38s/it] 64%|██████▍ | 29/45 [01:10<00:38, 2.40s/it] 67%|██████▋ | 30/45 [01:13<00:35, 2.38s/it] 69%|██████▉ | 31/45 [01:15<00:33, 2.40s/it] 71%|███████ | 32/45 [01:17<00:30, 2.35s/it] 73%|███████▎ | 33/45 [01:20<00:28, 2.38s/it] 76%|███████▌ | 34/45 [01:22<00:25, 2.35s/it] 78%|███████▊ | 35/45 [01:25<00:23, 2.37s/it] 80%|████████ | 36/45 [01:27<00:21, 2.34s/it] 82%|████████▏ | 37/45 [01:29<00:18, 2.36s/it] 84%|████████▍ | 38/45 [01:31<00:16, 2.30s/it] 87%|████████▋ | 39/45 [01:34<00:13, 2.25s/it] 89%|████████▉ | 40/45 [01:36<00:11, 2.23s/it] 91%|█████████ | 41/45 [01:38<00:09, 2.26s/it] 93%|█████████▎| 42/45 [01:40<00:06, 2.21s/it] 96%|█████████▌| 43/45 [01:43<00:04, 2.25s/it] 98%|█████████▊| 44/45 [01:44<00:02, 2.01s/it] 100%|██████████| 45/45 [01:45<00:00, 1.78s/it] 100%|██████████| 45/45 [01:45<00:00, 2.35s/it] Decoding latents in cuda:0... done in 2.25s Move latents to cpu... done in 0.02s Uploading outputs...
prompt
Specify things to see in the output
score_9, score_8_up, score_7_up, Rosalina in bikini
negative_prompt
Specify things to not see in the output
score_6, score_5, score_4, ugly face, low res, blurry face, black and white, watermark, bad hands, missing fingers, EasyNegativeV2-SDXL, rating_explicit, bad hands
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0.5
num_outputs
Number of output images
3
width
Output image width
832
height
Output image height
1216
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.
4294967293
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 Karras
samping_steps
Number of denoising steps
45
cfg_scale
Scale for classifier-free guidance
4
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)
EasyNegativeV2-SDXL.safetensors
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/5d1c93ef51844b6e9913d5eceaf0675c/00000-4294967293.webp
https://files.tungsten.run/uploads/d3c7a4c24b054e008ccd3df81e5949b7/00001-4294967294.webp
https://files.tungsten.run/uploads/31bd83a19e77430f8881ad37b70b9c11/00002-4294967295.webp
Finished in 108.7 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: score_9, score_8_up, score_7_up, Rosalina in bikini, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: score_6, score_5, score_4, ugly face, low res, blurry face, black and white, watermark, bad hands, missing fingers, EasyNegativeV2-SDXL, rating_explicit, bad hands 0%| | 0/45 [00:00<?, ?it/s] 2%|▏ | 1/45 [00:01<01:27, 1.99s/it] 4%|▍ | 2/45 [00:04<01:36, 2.25s/it] 7%|▋ | 3/45 [00:07<01:41, 2.41s/it] 9%|▉ | 4/45 [00:09<01:43, 2.51s/it] 11%|█ | 5/45 [00:12<01:38, 2.46s/it] 13%|█▎ | 6/45 [00:14<01:36, 2.48s/it] 16%|█▌ | 7/45 [00:17<01:33, 2.46s/it] 18%|█▊ | 8/45 [00:19<01:32, 2.51s/it] 20%|██ | 9/45 [00:22<01:30, 2.52s/it] 22%|██▏ | 10/45 [00:24<01:28, 2.52s/it] 24%|██▍ | 11/45 [00:27<01:23, 2.47s/it] 27%|██▋ | 12/45 [00:29<01:21, 2.48s/it] 29%|██▉ | 13/45 [00:31<01:18, 2.46s/it] 31%|███ | 14/45 [00:34<01:18, 2.53s/it] 33%|███▎ | 15/45 [00:37<01:15, 2.52s/it] 36%|███▌ | 16/45 [00:39<01:13, 2.55s/it] 38%|███▊ | 17/45 [00:42<01:10, 2.50s/it] 40%|████ | 18/45 [00:44<01:06, 2.46s/it] 42%|████▏ | 19/45 [00:46<01:02, 2.42s/it] 44%|████▍ | 20/45 [00:49<01:01, 2.45s/it] 47%|████▋ | 21/45 [00:51<00:56, 2.36s/it] 49%|████▉ | 22/45 [00:54<00:55, 2.41s/it] 51%|█████ | 23/45 [00:56<00:53, 2.45s/it] 53%|█████▎ | 24/45 [00:58<00:50, 2.40s/it] 56%|█████▌ | 25/45 [01:01<00:48, 2.44s/it] 58%|█████▊ | 26/45 [01:03<00:46, 2.43s/it] 60%|██████ | 27/45 [01:06<00:44, 2.46s/it] 62%|██████▏ | 28/45 [01:08<00:40, 2.38s/it] 64%|██████▍ | 29/45 [01:10<00:38, 2.40s/it] 67%|██████▋ | 30/45 [01:13<00:35, 2.38s/it] 69%|██████▉ | 31/45 [01:15<00:33, 2.40s/it] 71%|███████ | 32/45 [01:17<00:30, 2.35s/it] 73%|███████▎ | 33/45 [01:20<00:28, 2.38s/it] 76%|███████▌ | 34/45 [01:22<00:25, 2.35s/it] 78%|███████▊ | 35/45 [01:25<00:23, 2.37s/it] 80%|████████ | 36/45 [01:27<00:21, 2.34s/it] 82%|████████▏ | 37/45 [01:29<00:18, 2.36s/it] 84%|████████▍ | 38/45 [01:31<00:16, 2.30s/it] 87%|████████▋ | 39/45 [01:34<00:13, 2.25s/it] 89%|████████▉ | 40/45 [01:36<00:11, 2.23s/it] 91%|█████████ | 41/45 [01:38<00:09, 2.26s/it] 93%|█████████▎| 42/45 [01:40<00:06, 2.21s/it] 96%|█████████▌| 43/45 [01:43<00:04, 2.25s/it] 98%|█████████▊| 44/45 [01:44<00:02, 2.01s/it] 100%|██████████| 45/45 [01:45<00:00, 1.78s/it] 100%|██████████| 45/45 [01:45<00:00, 2.35s/it] Decoding latents in cuda:0... done in 2.25s Move latents to cpu... done in 0.02s Uploading outputs...