Batman with Addictive Future
Input
prompt
Specify things to see in the output
(ultra realistic:1.5), (ultra detailed:1.5), (award winning masterpiece:1.5), (real life:1.5), (best quality:1.5), analog style, <lora:Batman-KK77-V1:0.7>, ((1man)), batman, strong, ((canon m50)), ((award winning)), (High Detail), Sharp, 8k, Cinematic lighting, soft lighting, greg rutkowski, trending on artstation, intricate, gothic clothing, night, city skyline, moon, (natural skin texture:0.5), (from front:1.3), (epiC35mm), nice hands, perfect hands, <lora:add_detail:0.8>, <lora:FaceBeauty_qinglong_V3:1>
negative_prompt
Specify things to not see in the output
((woman)), ((girl)), ((feminine)), nudity, nsfw, (nipples), vagina, ((fat)), ((chubby)), bad-artist, bad-hands-5, bad_prompt, realisticvision-negative-embedding, verybadimagenegative_v1.3, UnrealisticDream, (((bad art))), (((stock image))), (((stock photo))), (((stock-photo))), ((bad fan art)), ((lazy art)), ((low quality)), (low efford), (rushed art), depressed, blue phase, immature, digimon, sonic, original character, OC, children, cartoon, stuffed animal, (((4chan))), (((twitter))), ((Tik Tok)), ((tiktok)), fascist, racist, Machiavellian, pepe the frog, blackface, dictated, controlled, dominated, uniform, medieval, religion, religious, holy, sacred, Russian, boring, monotone, normal, common, wrong distance, far away object in front of nearer object, (((out of frame))), ((watermark))),((signature)), striped, borders, white border, cutout, collage, incomplete word, cut off text, half letter, latent space, (((overexposed))), (((glow))), glare, lens flare, telescopic interference, low res, lowres, 3d render, (((underexposed))), ((dark)), blackness, dark background, black background, black rectangle, contour, monochrome, colorblind, green skin, ((long exposure time)), ((noisy)), (grainy), (dead pixel), (dusty), dirty, blurry, blur, smeared, fog, out of focus, high Depth of field, floating branch, floating rock, floating bush, floating tree, (((ugly))), (((bad composition))), (((bad proportions)), (((bad anatomy))), ((mangled)), ((distorted)), ((gross proportions), ((duplicate)), (((horrific))), ((mutated)), ((mutation)), (fisheye camera), wide angle camera, deformed, disfigured, morbid, long body, asymmetric, poorly drawn face, cloned face, cloned head, asymmetric ears, asymmetric ear rings, floating hair, (long neck), cross eyed, staring, stare, stare into the camera, look at the camera, blinking, winking, makeup, lipstick, eye liner, eyeliner, kitsch, bad art, bad taste, unnatural, staged, missing limb, missing arm, missing leg, floating limb, disconnected limb, extra limb, too many fingers, extra fingers, malformed limbs, malformed hands, poorly drawn hands, (mutated hands), (mutated fingers), mutilated hands, asymmetric butt, butthole, extra tail, missing tail,
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
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
0.2
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
4
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
40
cfg_scale
Scale for classifier-free guidance
8
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
blessed2_fp16.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/f073201a5f804ae58297abbfc5253f43/00000-4.webp
https://files.tungsten.run/uploads/b8589cb163af494499e3e0c924aff995/00001-5.webp
https://files.tungsten.run/uploads/91d5094b8d424e939db6203345a2b9be/00002-6.webp
https://files.tungsten.run/uploads/325776d1473b4a8792e939be4cb54d0f/00003-7.webp
Finished in 127.3 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (ultra realistic:1.5), (ultra detailed:1.5), (award winning masterpiece:1.5), (real life:1.5), (best quality:1.5), analog style, <lora:Batman-KK77-V1:0.7>, ((1man)), batman, strong, ((canon m50)), ((award winning)), (High Detail), Sharp, 8k, Cinematic lighting, soft lighting, greg rutkowski, trending on artstation, intricate, gothic clothing, night, city skyline, moon, (natural skin texture:0.5), (from front:1.3), (epiC35mm), nice hands, perfect hands, <lora:FaceBeauty_qinglong_V3:1>, <lora:add_detail:0.2> Full negative prompt: ((woman)), ((girl)), ((feminine)), nudity, nsfw, (nipples), vagina, ((fat)), ((chubby)), bad-artist, bad-hands-5, bad_prompt, realisticvision-negative-embedding, verybadimagenegative_v1.3, UnrealisticDream, (((bad art))), (((stock image))), (((stock photo))), (((stock-photo))), ((bad fan art)), ((lazy art)), ((low quality)), (low efford), (rushed art), depressed, blue phase, immature, digimon, sonic, original character, OC, children, cartoon, stuffed animal, (((4chan))), (((twitter))), ((Tik Tok)), ((tiktok)), fascist, racist, Machiavellian, pepe the frog, blackface, dictated, controlled, dominated, uniform, medieval, religion, religious, holy, sacred, Russian, boring, monotone, normal, common, wrong distance, far away object in front of nearer object, (((out of frame))), ((watermark))),((signature)), striped, borders, white border, cutout, collage, incomplete word, cut off text, half letter, latent space, (((overexposed))), (((glow))), glare, lens flare, telescopic interference, low res, lowres, 3d render, (((underexposed))), ((dark)), blackness, dark background, black background, black rectangle, contour, monochrome, colorblind, green skin, ((long exposure time)), ((noisy)), (grainy), (dead pixel), (dusty), dirty, blurry, blur, smeared, fog, out of focus, high Depth of field, floating branch, floating rock, floating bush, floating tree, (((ugly))), (((bad composition))), (((bad proportions)), (((bad anatomy))), ((mangled)), ((distorted)), ((gross proportions), ((duplicate)), (((horrific))), ((mutated)), ((mutation)), (fisheye camera), wide angle camera, deformed, disfigured, morbid, long body, asymmetric, poorly drawn face, cloned face, cloned head, asymmetric ears, asymmetric ear rings, floating hair, (long neck), cross eyed, staring, stare, stare into the camera, look at the camera, blinking, winking, makeup, lipstick, eye liner, eyeliner, kitsch, bad art, bad taste, unnatural, staged, missing limb, missing arm, missing leg, floating limb, disconnected limb, extra limb, too many fingers, extra fingers, malformed limbs, malformed hands, poorly drawn hands, (mutated hands), (mutated fingers), mutilated hands, asymmetric butt, butthole, extra tail, missing tail, 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:02<01:19, 2.04s/it] 5%|▌ | 2/40 [00:03<01:06, 1.75s/it] 8%|▊ | 3/40 [00:05<01:05, 1.77s/it] 10%|█ | 4/40 [00:07<01:04, 1.80s/it] 12%|█▎ | 5/40 [00:08<01:02, 1.79s/it] 15%|█▌ | 6/40 [00:10<01:00, 1.78s/it] 18%|█▊ | 7/40 [00:12<00:56, 1.72s/it] 20%|██ | 8/40 [00:13<00:53, 1.68s/it] 22%|██▎ | 9/40 [00:15<00:53, 1.72s/it] 25%|██▌ | 10/40 [00:17<00:51, 1.71s/it] 28%|██▊ | 11/40 [00:19<00:49, 1.72s/it] 30%|███ | 12/40 [00:20<00:47, 1.71s/it] 32%|███▎ | 13/40 [00:22<00:46, 1.72s/it] 35%|███▌ | 14/40 [00:24<00:44, 1.72s/it] 38%|███▊ | 15/40 [00:26<00:42, 1.71s/it] 40%|████ | 16/40 [00:27<00:40, 1.68s/it] 42%|████▎ | 17/40 [00:29<00:39, 1.70s/it] 45%|████▌ | 18/40 [00:31<00:37, 1.69s/it] 48%|████▊ | 19/40 [00:32<00:35, 1.68s/it] 50%|█████ | 20/40 [00:34<00:33, 1.66s/it] 52%|█████▎ | 21/40 [00:35<00:30, 1.61s/it] 55%|█████▌ | 22/40 [00:37<00:29, 1.61s/it] 57%|█████▊ | 23/40 [00:39<00:27, 1.62s/it] 60%|██████ | 24/40 [00:40<00:25, 1.60s/it] 62%|██████▎ | 25/40 [00:42<00:23, 1.56s/it] 65%|██████▌ | 26/40 [00:43<00:22, 1.61s/it] 68%|██████▊ | 27/40 [00:45<00:20, 1.61s/it] 70%|███████ | 28/40 [00:47<00:19, 1.62s/it] 72%|███████▎ | 29/40 [00:48<00:17, 1.55s/it] 75%|███████▌ | 30/40 [00:50<00:15, 1.55s/it] 78%|███████▊ | 31/40 [00:51<00:14, 1.57s/it] 80%|████████ | 32/40 [00:52<00:12, 1.51s/it] 82%|████████▎ | 33/40 [00:54<00:10, 1.51s/it] 85%|████████▌ | 34/40 [00:55<00:08, 1.45s/it] 88%|████████▊ | 35/40 [00:57<00:07, 1.49s/it] 90%|█████████ | 36/40 [00:58<00:05, 1.45s/it] 92%|█████████▎| 37/40 [01:00<00:04, 1.43s/it] 95%|█████████▌| 38/40 [01:01<00:02, 1.39s/it] 98%|█████████▊| 39/40 [01:02<00:01, 1.20s/it] 100%|██████████| 40/40 [01:02<00:00, 1.03s/it] 100%|██████████| 40/40 [01:02<00:00, 1.57s/it] Decoding latents in cuda:0... =========================================== A tensor with all NaNs was produced in VAE. Converted VAE into 32-bit float and retry. =========================================== done in 1.78s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 4.7ms preprocess, 7.8ms inference, 38.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:15, 1.46it/s] 9%|▊ | 2/23 [00:01<00:11, 1.77it/s] 13%|█▎ | 3/23 [00:01<00:10, 1.91it/s] 17%|█▋ | 4/23 [00:02<00:09, 2.05it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.08it/s] 26%|██▌ | 6/23 [00:03<00:08, 2.09it/s] 30%|███ | 7/23 [00:03<00:07, 2.12it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.17it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.10it/s] 43%|████▎ | 10/23 [00:04<00:06, 2.13it/s] 48%|████▊ | 11/23 [00:05<00:05, 2.11it/s] 52%|█████▏ | 12/23 [00:05<00:05, 2.18it/s] 57%|█████▋ | 13/23 [00:06<00:04, 2.18it/s] 61%|██████ | 14/23 [00:06<00:04, 2.14it/s] 65%|██████▌ | 15/23 [00:07<00:03, 2.23it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.18it/s] 74%|███████▍ | 17/23 [00:08<00:02, 2.28it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.25it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.30it/s] 87%|████████▋ | 20/23 [00:09<00:01, 2.34it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.40it/s] 96%|█████████▌| 22/23 [00:09<00:00, 2.75it/s] 100%|██████████| 23/23 [00:10<00:00, 3.17it/s] 100%|██████████| 23/23 [00:10<00:00, 2.27it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.0ms preprocess, 7.5ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:10, 2.11it/s] 9%|▊ | 2/23 [00:00<00:10, 2.06it/s] 13%|█▎ | 3/23 [00:01<00:09, 2.12it/s] 17%|█▋ | 4/23 [00:01<00:08, 2.18it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.18it/s] 26%|██▌ | 6/23 [00:02<00:07, 2.16it/s] 30%|███ | 7/23 [00:03<00:07, 2.18it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.23it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.13it/s] 43%|████▎ | 10/23 [00:04<00:06, 2.13it/s] 48%|████▊ | 11/23 [00:05<00:05, 2.13it/s] 52%|█████▏ | 12/23 [00:05<00:04, 2.23it/s] 57%|█████▋ | 13/23 [00:06<00:04, 2.18it/s] 61%|██████ | 14/23 [00:06<00:04, 2.16it/s] 65%|██████▌ | 15/23 [00:06<00:03, 2.25it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.24it/s] 74%|███████▍ | 17/23 [00:07<00:02, 2.34it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.30it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.36it/s] 87%|████████▋ | 20/23 [00:08<00:01, 2.37it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.45it/s] 96%|█████████▌| 22/23 [00:09<00:00, 2.80it/s] 100%|██████████| 23/23 [00:09<00:00, 3.19it/s] 100%|██████████| 23/23 [00:09<00:00, 2.35it/s] Decoding latents in cuda:0... done in 0.39s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.3ms Speed: 2.8ms preprocess, 7.3ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:10, 2.10it/s] 9%|▊ | 2/23 [00:00<00:10, 2.08it/s] 13%|█▎ | 3/23 [00:01<00:09, 2.13it/s] 17%|█▋ | 4/23 [00:01<00:08, 2.20it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.15it/s] 26%|██▌ | 6/23 [00:02<00:07, 2.14it/s] 30%|███ | 7/23 [00:03<00:07, 2.16it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.21it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.12it/s] 43%|████▎ | 10/23 [00:04<00:06, 2.14it/s] 48%|████▊ | 11/23 [00:05<00:05, 2.12it/s] 52%|█████▏ | 12/23 [00:05<00:04, 2.21it/s] 57%|█████▋ | 13/23 [00:05<00:04, 2.22it/s] 61%|██████ | 14/23 [00:06<00:04, 2.22it/s] 65%|██████▌ | 15/23 [00:06<00:03, 2.30it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.27it/s] 74%|███████▍ | 17/23 [00:07<00:02, 2.36it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.30it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.37it/s] 87%|████████▋ | 20/23 [00:08<00:01, 2.40it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.47it/s] 96%|█████████▌| 22/23 [00:09<00:00, 2.80it/s] 100%|██████████| 23/23 [00:09<00:00, 3.21it/s] 100%|██████████| 23/23 [00:09<00:00, 2.36it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:10, 2.13it/s] 9%|▊ | 2/23 [00:00<00:09, 2.11it/s] 13%|█▎ | 3/23 [00:01<00:09, 2.11it/s] 17%|█▋ | 4/23 [00:01<00:08, 2.17it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.13it/s] 26%|██▌ | 6/23 [00:02<00:07, 2.13it/s] 30%|███ | 7/23 [00:03<00:07, 2.16it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.21it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.15it/s] 43%|████▎ | 10/23 [00:04<00:06, 2.14it/s] 48%|████▊ | 11/23 [00:05<00:05, 2.14it/s] 52%|█████▏ | 12/23 [00:05<00:04, 2.21it/s] 57%|█████▋ | 13/23 [00:05<00:04, 2.21it/s] 61%|██████ | 14/23 [00:06<00:04, 2.19it/s] 65%|██████▌ | 15/23 [00:06<00:03, 2.28it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.27it/s] 74%|███████▍ | 17/23 [00:07<00:02, 2.37it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.32it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.35it/s] 87%|████████▋ | 20/23 [00:08<00:01, 2.39it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.46it/s] 96%|█████████▌| 22/23 [00:09<00:00, 2.78it/s] 100%|██████████| 23/23 [00:09<00:00, 3.21it/s] 100%|██████████| 23/23 [00:09<00:00, 2.35it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s Finished.
prompt
Specify things to see in the output
(ultra realistic:1.5), (ultra detailed:1.5), (award winning masterpiece:1.5), (real life:1.5), (best quality:1.5), analog style, <lora:Batman-KK77-V1:0.7>, ((1man)), batman, strong, ((canon m50)), ((award winning)), (High Detail), Sharp, 8k, Cinematic lighting, soft lighting, greg rutkowski, trending on artstation, intricate, gothic clothing, night, city skyline, moon, (natural skin texture:0.5), (from front:1.3), (epiC35mm), nice hands, perfect hands, <lora:add_detail:0.8>, <lora:FaceBeauty_qinglong_V3:1>
negative_prompt
Specify things to not see in the output
((woman)), ((girl)), ((feminine)), nudity, nsfw, (nipples), vagina, ((fat)), ((chubby)), bad-artist, bad-hands-5, bad_prompt, realisticvision-negative-embedding, verybadimagenegative_v1.3, UnrealisticDream, (((bad art))), (((stock image))), (((stock photo))), (((stock-photo))), ((bad fan art)), ((lazy art)), ((low quality)), (low efford), (rushed art), depressed, blue phase, immature, digimon, sonic, original character, OC, children, cartoon, stuffed animal, (((4chan))), (((twitter))), ((Tik Tok)), ((tiktok)), fascist, racist, Machiavellian, pepe the frog, blackface, dictated, controlled, dominated, uniform, medieval, religion, religious, holy, sacred, Russian, boring, monotone, normal, common, wrong distance, far away object in front of nearer object, (((out of frame))), ((watermark))),((signature)), striped, borders, white border, cutout, collage, incomplete word, cut off text, half letter, latent space, (((overexposed))), (((glow))), glare, lens flare, telescopic interference, low res, lowres, 3d render, (((underexposed))), ((dark)), blackness, dark background, black background, black rectangle, contour, monochrome, colorblind, green skin, ((long exposure time)), ((noisy)), (grainy), (dead pixel), (dusty), dirty, blurry, blur, smeared, fog, out of focus, high Depth of field, floating branch, floating rock, floating bush, floating tree, (((ugly))), (((bad composition))), (((bad proportions)), (((bad anatomy))), ((mangled)), ((distorted)), ((gross proportions), ((duplicate)), (((horrific))), ((mutated)), ((mutation)), (fisheye camera), wide angle camera, deformed, disfigured, morbid, long body, asymmetric, poorly drawn face, cloned face, cloned head, asymmetric ears, asymmetric ear rings, floating hair, (long neck), cross eyed, staring, stare, stare into the camera, look at the camera, blinking, winking, makeup, lipstick, eye liner, eyeliner, kitsch, bad art, bad taste, unnatural, staged, missing limb, missing arm, missing leg, floating limb, disconnected limb, extra limb, too many fingers, extra fingers, malformed limbs, malformed hands, poorly drawn hands, (mutated hands), (mutated fingers), mutilated hands, asymmetric butt, butthole, extra tail, missing tail,
num_outputs
Number of output images
4
width
Output image width
768
height
Output image height
768
enhance_face_with_adetailer
Enhance face with adetailer
true
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
0.2
brightness
Adjust brightness
0
contrast
Adjust contrast
0
saturation
Adjust saturation
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
4
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
40
cfg_scale
Scale for classifier-free guidance
8
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
blessed2_fp16.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/f073201a5f804ae58297abbfc5253f43/00000-4.webp
https://files.tungsten.run/uploads/b8589cb163af494499e3e0c924aff995/00001-5.webp
https://files.tungsten.run/uploads/91d5094b8d424e939db6203345a2b9be/00002-6.webp
https://files.tungsten.run/uploads/325776d1473b4a8792e939be4cb54d0f/00003-7.webp
Finished in 127.3 seconds
Setting up the model... Processing... Loading VAE weight: models/VAE/blessed2_fp16.safetensors Full prompt: (ultra realistic:1.5), (ultra detailed:1.5), (award winning masterpiece:1.5), (real life:1.5), (best quality:1.5), analog style, <lora:Batman-KK77-V1:0.7>, ((1man)), batman, strong, ((canon m50)), ((award winning)), (High Detail), Sharp, 8k, Cinematic lighting, soft lighting, greg rutkowski, trending on artstation, intricate, gothic clothing, night, city skyline, moon, (natural skin texture:0.5), (from front:1.3), (epiC35mm), nice hands, perfect hands, <lora:FaceBeauty_qinglong_V3:1>, <lora:add_detail:0.2> Full negative prompt: ((woman)), ((girl)), ((feminine)), nudity, nsfw, (nipples), vagina, ((fat)), ((chubby)), bad-artist, bad-hands-5, bad_prompt, realisticvision-negative-embedding, verybadimagenegative_v1.3, UnrealisticDream, (((bad art))), (((stock image))), (((stock photo))), (((stock-photo))), ((bad fan art)), ((lazy art)), ((low quality)), (low efford), (rushed art), depressed, blue phase, immature, digimon, sonic, original character, OC, children, cartoon, stuffed animal, (((4chan))), (((twitter))), ((Tik Tok)), ((tiktok)), fascist, racist, Machiavellian, pepe the frog, blackface, dictated, controlled, dominated, uniform, medieval, religion, religious, holy, sacred, Russian, boring, monotone, normal, common, wrong distance, far away object in front of nearer object, (((out of frame))), ((watermark))),((signature)), striped, borders, white border, cutout, collage, incomplete word, cut off text, half letter, latent space, (((overexposed))), (((glow))), glare, lens flare, telescopic interference, low res, lowres, 3d render, (((underexposed))), ((dark)), blackness, dark background, black background, black rectangle, contour, monochrome, colorblind, green skin, ((long exposure time)), ((noisy)), (grainy), (dead pixel), (dusty), dirty, blurry, blur, smeared, fog, out of focus, high Depth of field, floating branch, floating rock, floating bush, floating tree, (((ugly))), (((bad composition))), (((bad proportions)), (((bad anatomy))), ((mangled)), ((distorted)), ((gross proportions), ((duplicate)), (((horrific))), ((mutated)), ((mutation)), (fisheye camera), wide angle camera, deformed, disfigured, morbid, long body, asymmetric, poorly drawn face, cloned face, cloned head, asymmetric ears, asymmetric ear rings, floating hair, (long neck), cross eyed, staring, stare, stare into the camera, look at the camera, blinking, winking, makeup, lipstick, eye liner, eyeliner, kitsch, bad art, bad taste, unnatural, staged, missing limb, missing arm, missing leg, floating limb, disconnected limb, extra limb, too many fingers, extra fingers, malformed limbs, malformed hands, poorly drawn hands, (mutated hands), (mutated fingers), mutilated hands, asymmetric butt, butthole, extra tail, missing tail, 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:02<01:19, 2.04s/it] 5%|▌ | 2/40 [00:03<01:06, 1.75s/it] 8%|▊ | 3/40 [00:05<01:05, 1.77s/it] 10%|█ | 4/40 [00:07<01:04, 1.80s/it] 12%|█▎ | 5/40 [00:08<01:02, 1.79s/it] 15%|█▌ | 6/40 [00:10<01:00, 1.78s/it] 18%|█▊ | 7/40 [00:12<00:56, 1.72s/it] 20%|██ | 8/40 [00:13<00:53, 1.68s/it] 22%|██▎ | 9/40 [00:15<00:53, 1.72s/it] 25%|██▌ | 10/40 [00:17<00:51, 1.71s/it] 28%|██▊ | 11/40 [00:19<00:49, 1.72s/it] 30%|███ | 12/40 [00:20<00:47, 1.71s/it] 32%|███▎ | 13/40 [00:22<00:46, 1.72s/it] 35%|███▌ | 14/40 [00:24<00:44, 1.72s/it] 38%|███▊ | 15/40 [00:26<00:42, 1.71s/it] 40%|████ | 16/40 [00:27<00:40, 1.68s/it] 42%|████▎ | 17/40 [00:29<00:39, 1.70s/it] 45%|████▌ | 18/40 [00:31<00:37, 1.69s/it] 48%|████▊ | 19/40 [00:32<00:35, 1.68s/it] 50%|█████ | 20/40 [00:34<00:33, 1.66s/it] 52%|█████▎ | 21/40 [00:35<00:30, 1.61s/it] 55%|█████▌ | 22/40 [00:37<00:29, 1.61s/it] 57%|█████▊ | 23/40 [00:39<00:27, 1.62s/it] 60%|██████ | 24/40 [00:40<00:25, 1.60s/it] 62%|██████▎ | 25/40 [00:42<00:23, 1.56s/it] 65%|██████▌ | 26/40 [00:43<00:22, 1.61s/it] 68%|██████▊ | 27/40 [00:45<00:20, 1.61s/it] 70%|███████ | 28/40 [00:47<00:19, 1.62s/it] 72%|███████▎ | 29/40 [00:48<00:17, 1.55s/it] 75%|███████▌ | 30/40 [00:50<00:15, 1.55s/it] 78%|███████▊ | 31/40 [00:51<00:14, 1.57s/it] 80%|████████ | 32/40 [00:52<00:12, 1.51s/it] 82%|████████▎ | 33/40 [00:54<00:10, 1.51s/it] 85%|████████▌ | 34/40 [00:55<00:08, 1.45s/it] 88%|████████▊ | 35/40 [00:57<00:07, 1.49s/it] 90%|█████████ | 36/40 [00:58<00:05, 1.45s/it] 92%|█████████▎| 37/40 [01:00<00:04, 1.43s/it] 95%|█████████▌| 38/40 [01:01<00:02, 1.39s/it] 98%|█████████▊| 39/40 [01:02<00:01, 1.20s/it] 100%|██████████| 40/40 [01:02<00:00, 1.03s/it] 100%|██████████| 40/40 [01:02<00:00, 1.57s/it] Decoding latents in cuda:0... =========================================== A tensor with all NaNs was produced in VAE. Converted VAE into 32-bit float and retry. =========================================== done in 1.78s Move latents to cpu... done in 0.02s 0: 640x640 1 face, 7.8ms Speed: 4.7ms preprocess, 7.8ms inference, 38.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:15, 1.46it/s] 9%|▊ | 2/23 [00:01<00:11, 1.77it/s] 13%|█▎ | 3/23 [00:01<00:10, 1.91it/s] 17%|█▋ | 4/23 [00:02<00:09, 2.05it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.08it/s] 26%|██▌ | 6/23 [00:03<00:08, 2.09it/s] 30%|███ | 7/23 [00:03<00:07, 2.12it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.17it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.10it/s] 43%|████▎ | 10/23 [00:04<00:06, 2.13it/s] 48%|████▊ | 11/23 [00:05<00:05, 2.11it/s] 52%|█████▏ | 12/23 [00:05<00:05, 2.18it/s] 57%|█████▋ | 13/23 [00:06<00:04, 2.18it/s] 61%|██████ | 14/23 [00:06<00:04, 2.14it/s] 65%|██████▌ | 15/23 [00:07<00:03, 2.23it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.18it/s] 74%|███████▍ | 17/23 [00:08<00:02, 2.28it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.25it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.30it/s] 87%|████████▋ | 20/23 [00:09<00:01, 2.34it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.40it/s] 96%|█████████▌| 22/23 [00:09<00:00, 2.75it/s] 100%|██████████| 23/23 [00:10<00:00, 3.17it/s] 100%|██████████| 23/23 [00:10<00:00, 2.27it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.5ms Speed: 3.0ms preprocess, 7.5ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:10, 2.11it/s] 9%|▊ | 2/23 [00:00<00:10, 2.06it/s] 13%|█▎ | 3/23 [00:01<00:09, 2.12it/s] 17%|█▋ | 4/23 [00:01<00:08, 2.18it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.18it/s] 26%|██▌ | 6/23 [00:02<00:07, 2.16it/s] 30%|███ | 7/23 [00:03<00:07, 2.18it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.23it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.13it/s] 43%|████▎ | 10/23 [00:04<00:06, 2.13it/s] 48%|████▊ | 11/23 [00:05<00:05, 2.13it/s] 52%|█████▏ | 12/23 [00:05<00:04, 2.23it/s] 57%|█████▋ | 13/23 [00:06<00:04, 2.18it/s] 61%|██████ | 14/23 [00:06<00:04, 2.16it/s] 65%|██████▌ | 15/23 [00:06<00:03, 2.25it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.24it/s] 74%|███████▍ | 17/23 [00:07<00:02, 2.34it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.30it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.36it/s] 87%|████████▋ | 20/23 [00:08<00:01, 2.37it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.45it/s] 96%|█████████▌| 22/23 [00:09<00:00, 2.80it/s] 100%|██████████| 23/23 [00:09<00:00, 3.19it/s] 100%|██████████| 23/23 [00:09<00:00, 2.35it/s] Decoding latents in cuda:0... done in 0.39s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.3ms Speed: 2.8ms preprocess, 7.3ms inference, 1.7ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:10, 2.10it/s] 9%|▊ | 2/23 [00:00<00:10, 2.08it/s] 13%|█▎ | 3/23 [00:01<00:09, 2.13it/s] 17%|█▋ | 4/23 [00:01<00:08, 2.20it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.15it/s] 26%|██▌ | 6/23 [00:02<00:07, 2.14it/s] 30%|███ | 7/23 [00:03<00:07, 2.16it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.21it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.12it/s] 43%|████▎ | 10/23 [00:04<00:06, 2.14it/s] 48%|████▊ | 11/23 [00:05<00:05, 2.12it/s] 52%|█████▏ | 12/23 [00:05<00:04, 2.21it/s] 57%|█████▋ | 13/23 [00:05<00:04, 2.22it/s] 61%|██████ | 14/23 [00:06<00:04, 2.22it/s] 65%|██████▌ | 15/23 [00:06<00:03, 2.30it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.27it/s] 74%|███████▍ | 17/23 [00:07<00:02, 2.36it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.30it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.37it/s] 87%|████████▋ | 20/23 [00:08<00:01, 2.40it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.47it/s] 96%|█████████▌| 22/23 [00:09<00:00, 2.80it/s] 100%|██████████| 23/23 [00:09<00:00, 3.21it/s] 100%|██████████| 23/23 [00:09<00:00, 2.36it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s 0: 640x640 1 face, 7.4ms Speed: 3.0ms preprocess, 7.4ms inference, 1.9ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:10, 2.13it/s] 9%|▊ | 2/23 [00:00<00:09, 2.11it/s] 13%|█▎ | 3/23 [00:01<00:09, 2.11it/s] 17%|█▋ | 4/23 [00:01<00:08, 2.17it/s] 22%|██▏ | 5/23 [00:02<00:08, 2.13it/s] 26%|██▌ | 6/23 [00:02<00:07, 2.13it/s] 30%|███ | 7/23 [00:03<00:07, 2.16it/s] 35%|███▍ | 8/23 [00:03<00:06, 2.21it/s] 39%|███▉ | 9/23 [00:04<00:06, 2.15it/s] 43%|████▎ | 10/23 [00:04<00:06, 2.14it/s] 48%|████▊ | 11/23 [00:05<00:05, 2.14it/s] 52%|█████▏ | 12/23 [00:05<00:04, 2.21it/s] 57%|█████▋ | 13/23 [00:05<00:04, 2.21it/s] 61%|██████ | 14/23 [00:06<00:04, 2.19it/s] 65%|██████▌ | 15/23 [00:06<00:03, 2.28it/s] 70%|██████▉ | 16/23 [00:07<00:03, 2.27it/s] 74%|███████▍ | 17/23 [00:07<00:02, 2.37it/s] 78%|███████▊ | 18/23 [00:08<00:02, 2.32it/s] 83%|████████▎ | 19/23 [00:08<00:01, 2.35it/s] 87%|████████▋ | 20/23 [00:08<00:01, 2.39it/s] 91%|█████████▏| 21/23 [00:09<00:00, 2.46it/s] 96%|█████████▌| 22/23 [00:09<00:00, 2.78it/s] 100%|██████████| 23/23 [00:09<00:00, 3.21it/s] 100%|██████████| 23/23 [00:09<00:00, 2.35it/s] Decoding latents in cuda:0... done in 0.4s Move latents to cpu... done in 0.0s Finished.