tungsten-logo
Sign In
From behind with Pony Realism v2.1VAE
Pony Realism:v2.1VAE
sparks
sparks
·
May 28
28
Input
prompt
Specify things to see in the output
score_9, score_8_up, score_7_up, BREAK, rating_safe, beautiful female, from behind, resting looking at the sunset, from behind, landscape, mountain, intricate, princess, portrait, highly detailed, detailed skin, depth of field, film grain
negative_prompt
Specify things to not see in the output
score_1, score_2, score_3, text
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0.5
num_outputs
Number of output images
3
width
Output image width
768
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.
2537907942
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++ SDE Karras
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
6
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/dde0ad82426b4feea93327d7cc5c8e39/00000-2537907942.webp
https://files.tungsten.run/uploads/1a0e9ab0e27746e6a7bd8cd85ac0b9e6/00001-2537907943.webp
https://files.tungsten.run/uploads/c04d92ecbad1462eb163e73e1e217545/00002-2537907944.webp
Finished in 131.3 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: score_9, score_8_up, score_7_up, BREAK, rating_safe, beautiful female, from behind, resting looking at the sunset, from behind, landscape, mountain, intricate, princess, portrait, highly detailed, detailed skin, depth of field, film grain, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: score_1, score_2, score_3, text 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:44, 3.59s/it] 7%|▋ | 2/30 [00:08<02:01, 4.35s/it] 10%|█ | 3/30 [00:13<02:04, 4.61s/it] 13%|█▎ | 4/30 [00:18<02:02, 4.71s/it] 17%|█▋ | 5/30 [00:23<01:59, 4.78s/it] 20%|██ | 6/30 [00:27<01:54, 4.79s/it] 23%|██▎ | 7/30 [00:32<01:51, 4.85s/it] 27%|██▋ | 8/30 [00:37<01:47, 4.87s/it] 30%|███ | 9/30 [00:42<01:41, 4.83s/it] 33%|███▎ | 10/30 [00:47<01:37, 4.87s/it] 37%|███▋ | 11/30 [00:52<01:31, 4.84s/it] 40%|████ | 12/30 [00:57<01:27, 4.86s/it] 43%|████▎ | 13/30 [01:01<01:21, 4.81s/it] 47%|████▋ | 14/30 [01:05<01:11, 4.49s/it] 50%|█████ | 15/30 [01:10<01:07, 4.51s/it] 53%|█████▎ | 16/30 [01:14<01:03, 4.50s/it] 57%|█████▋ | 17/30 [01:19<00:57, 4.44s/it] 60%|██████ | 18/30 [01:23<00:53, 4.48s/it] 63%|██████▎ | 19/30 [01:27<00:48, 4.44s/it] 67%|██████▋ | 20/30 [01:32<00:45, 4.53s/it] 70%|███████ | 21/30 [01:36<00:39, 4.34s/it] 73%|███████▎ | 22/30 [01:40<00:34, 4.26s/it] 77%|███████▋ | 23/30 [01:45<00:30, 4.32s/it] 80%|████████ | 24/30 [01:49<00:25, 4.31s/it] 83%|████████▎ | 25/30 [01:53<00:20, 4.11s/it] 87%|████████▋ | 26/30 [01:57<00:16, 4.12s/it] 90%|█████████ | 27/30 [02:00<00:11, 3.94s/it] 93%|█████████▎| 28/30 [02:04<00:07, 3.83s/it] 97%|█████████▋| 29/30 [02:07<00:03, 3.56s/it] 100%|██████████| 30/30 [02:08<00:00, 2.83s/it] 100%|██████████| 30/30 [02:08<00:00, 4.28s/it] Decoding latents in cuda:0... done in 2.2s Move latents to cpu... done in 0.01s
prompt
Specify things to see in the output
score_9, score_8_up, score_7_up, BREAK, rating_safe, beautiful female, from behind, resting looking at the sunset, from behind, landscape, mountain, intricate, princess, portrait, highly detailed, detailed skin, depth of field, film grain
negative_prompt
Specify things to not see in the output
score_1, score_2, score_3, text
EnvyBetterHiresFixXL01
Envy Better Hires Fix Xl01
0.5
num_outputs
Number of output images
3
width
Output image width
768
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.
2537907942
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++ SDE Karras
samping_steps
Number of denoising steps
30
cfg_scale
Scale for classifier-free guidance
6
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/dde0ad82426b4feea93327d7cc5c8e39/00000-2537907942.webp
https://files.tungsten.run/uploads/1a0e9ab0e27746e6a7bd8cd85ac0b9e6/00001-2537907943.webp
https://files.tungsten.run/uploads/c04d92ecbad1462eb163e73e1e217545/00002-2537907944.webp
Finished in 131.3 seconds
Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: score_9, score_8_up, score_7_up, BREAK, rating_safe, beautiful female, from behind, resting looking at the sunset, from behind, landscape, mountain, intricate, princess, portrait, highly detailed, detailed skin, depth of field, film grain, <lora:EnvyBetterHiresFixXL01:0.5>, <lora:add-detail-xl:1.0> Full negative prompt: score_1, score_2, score_3, text 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:44, 3.59s/it] 7%|▋ | 2/30 [00:08<02:01, 4.35s/it] 10%|█ | 3/30 [00:13<02:04, 4.61s/it] 13%|█▎ | 4/30 [00:18<02:02, 4.71s/it] 17%|█▋ | 5/30 [00:23<01:59, 4.78s/it] 20%|██ | 6/30 [00:27<01:54, 4.79s/it] 23%|██▎ | 7/30 [00:32<01:51, 4.85s/it] 27%|██▋ | 8/30 [00:37<01:47, 4.87s/it] 30%|███ | 9/30 [00:42<01:41, 4.83s/it] 33%|███▎ | 10/30 [00:47<01:37, 4.87s/it] 37%|███▋ | 11/30 [00:52<01:31, 4.84s/it] 40%|████ | 12/30 [00:57<01:27, 4.86s/it] 43%|████▎ | 13/30 [01:01<01:21, 4.81s/it] 47%|████▋ | 14/30 [01:05<01:11, 4.49s/it] 50%|█████ | 15/30 [01:10<01:07, 4.51s/it] 53%|█████▎ | 16/30 [01:14<01:03, 4.50s/it] 57%|█████▋ | 17/30 [01:19<00:57, 4.44s/it] 60%|██████ | 18/30 [01:23<00:53, 4.48s/it] 63%|██████▎ | 19/30 [01:27<00:48, 4.44s/it] 67%|██████▋ | 20/30 [01:32<00:45, 4.53s/it] 70%|███████ | 21/30 [01:36<00:39, 4.34s/it] 73%|███████▎ | 22/30 [01:40<00:34, 4.26s/it] 77%|███████▋ | 23/30 [01:45<00:30, 4.32s/it] 80%|████████ | 24/30 [01:49<00:25, 4.31s/it] 83%|████████▎ | 25/30 [01:53<00:20, 4.11s/it] 87%|████████▋ | 26/30 [01:57<00:16, 4.12s/it] 90%|█████████ | 27/30 [02:00<00:11, 3.94s/it] 93%|█████████▎| 28/30 [02:04<00:07, 3.83s/it] 97%|█████████▋| 29/30 [02:07<00:03, 3.56s/it] 100%|██████████| 30/30 [02:08<00:00, 2.83s/it] 100%|██████████| 30/30 [02:08<00:00, 4.28s/it] Decoding latents in cuda:0... done in 2.2s Move latents to cpu... done in 0.01s