A basic image segmentation model (Yolo-v8) trained on around 200 images. Has some benefits over the kind of model that uses bounding boxes (The squares you see during generation) since it only inpaints the target area (belly). Trained primarily on realistic images, but can do furry / anime too. Sometimes it will recognize round things as bellies, but otherwise works well enough.
Instructions:
Unzip the archive and place the .pt in the /models/adetailer directory of your install
If it isn't working go to your stable diffusion folder and try:
venv\Scripts\activate pip install --upgrade ultralytics Note this is for windows, if you are on linux I trust you already fixed this
Description
Bounding box version, just adding this because it was requested in a bounty - I can recommend the seg version though
FAQ
Comments (23)
Lots of potential here, thanks for sharing.
ty, np at all. Did this for a bounty after all
Anyone know of a way to get this working with forge? Forge doesnt have the venv folder
what error are you getting? Dont use forge myself, but the process should be similar
@aaaaaa12212332202 its a trace back error. i will copy it here in a second when i re enable it
*** Error running postprocess_image: C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\scripts\!adetailer.py
Traceback (most recent call last):
File "C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\modules\scripts.py", line 883, in postprocess_image
script.postprocess_image(p, pp, *script_args)
File "C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\aaaaaa\traceback.py", line 173, in wrapper
raise error from None
AttributeError:
╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ System info │
│ ┏━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ │
│ ┃ ┃ Value ┃ │
│ ┡━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ │
│ │ Platform │ Windows-10-10.0.22631-SP0 │ │
│ │ Python │ 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] │ │
│ │ Version │ f0.0.17v1.8.0rc-latest-278-gbfee03d8 │ │
│ │ Commit │ bfee03d8d9415a925616f40ede030fe7a51cbcfd │ │
│ │ Commandline │ ['launch.py', '--theme', 'dark', '--ckpt-dir', │ │
│ │ │ 'C:/Users/USERNAME/OneDrive/Desktop/A1111/stable-diffusion-webui/models/Stable-diffusion', │ │
│ │ │ '--hypernetwork-dir', │ │
│ │ │ 'C:/Users/USERNAME/OneDrive/Desktop/A1111/stable-diffusion-webui/models/hypernetworks', │ │
│ │ │ '--embeddings-dir', 'C:/Users/USERNAME/OneDrive/Desktop/A1111/stable-diffusion-webui/embeddings', │ │
│ │ │ '--lora-dir', 'C:/Users/USERNAME/OneDrive/Desktop/A1111/stable-diffusion-webui/models/Lora'] │ │
│ │ Libraries │ {'torch': '2.1.2+cu121', 'torchvision': '0.16.2+cu121', 'ultralytics': '8.2.2', 'mediapipe': │ │
│ │ │ '0.10.14'} │ │
│ └─────────────┴────────────────────────────────────────────────────────────────────────────────────────────────┘ │
│ Inputs │
│ ┏━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ │
│ ┃ ┃ Value ┃ │
│ ┡━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ │
│ │ prompt │ anime artwork score_9, score_8_up, score_7_up, score_6_up, source_anime || okojo, 0k0j0 || │ │
│ │ │ 1girl, solo, full body || pregnant, round belly || small breasts || outie navel, big outie │ │
│ │ │ navel, hyper outie navel || navel ring, navel piercing || Digimon, digimon, │ │
│ │ │ digimon/(creature), humanoid, animal, beast, monster, creature, deity, mythical, royal │ │
│ │ │ knights, divine, divine judgement || furry, anthro, animal ears, animal nose, tail, claws, │ │
│ │ │ fur, fur body, white fur, colored eyes, large feet, long legs, long arms, big ears, long │ │
│ │ │ poibnty ears || body markings, face markings, arm markings, leg markings || detached │ │
│ │ │ sleeves, gloves, choker, baggy pants, robes, belts, straps, harness, belly harness, belly │ │
│ │ │ belt, belly strap, jewelry, gemstones, armor || cute, adorable, sexy, flirty, smug, │ │
│ │ │ taunting, seductive, temptress, mischievous || symmetrical || │ │
│ │ │ <lora:DigimonV1Pony:1.5> <lora:Pregnancy Slider_alpha1.0_rank4_noxattn_last:1> │ │
│ │ │ <lora:OkojoV1-6Pony:1> . anime style, key visual, vibrant, studio anime, highly detailed │ │
│ │ negative_prompt │ words, text, signature, watermark, key, cross, naked, nude, NSFW, nsfw, nipples │ │
│ │ n_iter │ 1 │ │
│ │ batch_size │ 1 │ │
│ │ width │ 512 │ │
│ │ height │ 1024 │ │
│ │ sampler_name │ Euler a │ │
│ │ enable_hr │ False │ │
│ │ hr_upscaler │ 4x-UltraSharp │ │
│ │ checkpoint │ ponyDiffusionV6XL_v6StartWithThisOne [67ab2fd8ec] │ │
│ │ vae │ sdxl_vae.safetensors │ │
│ │ unet │ Automatic │ │
│ └─────────────────┴────────────────────────────────────────────────────────────────────────────────────────────┘ │
│ ADetailer │
│ ┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓ │
│ ┃ ┃ Value ┃ │
│ ┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩ │
│ │ version │ 24.6.0 │ │
│ │ ad_model │ mediapipe_face_full │ │
│ │ ad_prompt │ │ │
│ │ ad_negative_prompt │ │ │
│ │ ad_controlnet_model │ openposeSDXL_v10 │ │
│ │ is_api │ False │ │
│ └─────────────────────┴─────────────────────┘ │
│ ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\aaaaaa\traceback.py:153 in │ │
│ │ wrapper │ │
│ │ │ │
│ │ 152 │ │ try: │ │
│ │ ❱ 153 │ │ │ return func(*args, **kwargs) │ │
│ │ 154 │ │ except Exception as e: │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\scripts\!adetailer.py:818 in │ │
│ │ postprocess_image │ │
│ │ │ │
│ │ 817 │ │ │ │ │ continue │ │
│ │ ❱ 818 │ │ │ │ is_processed |= self._postprocess_image_inner(p, pp, args, n=n) │ │
│ │ 819 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\scripts\!adetailer.py:739 in │ │
│ │ postprocessimage_inner │ │
│ │ │ │
│ │ 738 │ │ with change_torch_load(): │ │
│ │ ❱ 739 │ │ │ pred = predictor(ad_model, pp.image, args.ad_confidence, **kwargs) │ │
│ │ 740 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\adetailer\ultralytics.py:29 in │ │
│ │ ultralytics_predict │ │
│ │ │ │
│ │ 28 │ apply_classes(model, model_path, classes) │ │
│ │ ❱ 29 │ pred = model(image, conf=confidence, device=device) │ │
│ │ 30 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\engine\model.p │ │
│ │ y:176 in call │ │
│ │ │ │
│ │ 175 │ │ """ │ │
│ │ ❱ 176 │ │ return self.predict(source, stream, **kwargs) │ │
│ │ 177 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\engine\model.p │ │
│ │ y:452 in predict │ │
│ │ │ │
│ │ 451 │ │ │ self.predictor.set_prompts(prompts) │ │
│ │ ❱ 452 │ │ return self.predictor.predict_cli(source=source) if is_cli else self.predictor(s │ │
│ │ 453 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\engine\predict │ │
│ │ or.py:168 in call │ │
│ │ │ │
│ │ 167 │ │ else: │ │
│ │ ❱ 168 │ │ │ return list(self.stream_inference(source, model, args, *kwargs)) # merge │ │
│ │ 169 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\engine\predict │ │
│ │ or.py:228 in stream_inference │ │
│ │ │ │
│ │ 227 │ │ │ if not self.done_warmup: │ │
│ │ ❱ 228 │ │ │ │ self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else se │ │
│ │ 229 │ │ │ │ self.done_warmup = True │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\autobackend │ │
│ │ .py:627 in warmup │ │
│ │ │ │
│ │ 626 │ │ │ for _ in range(2 if self.jit else 1): │ │
│ │ ❱ 627 │ │ │ │ self.forward(im) # warmup │ │
│ │ 628 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\autobackend │ │
│ │ .py:453 in forward │ │
│ │ │ │
│ │ 452 │ │ if self.pt or self.nn_module: │ │
│ │ ❱ 453 │ │ │ y = self.model(im, augment=augment, visualize=visualize, embed=embed) │ │
│ │ 454 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1518 in wrappedcall_impl │ │
│ │ │ │
│ │ 1517 │ │ else: │ │
│ │ ❱ 1518 │ │ │ return self._call_impl(*args, **kwargs) │ │
│ │ 1519 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1527 in callimpl │ │
│ │ │ │
│ │ 1526 │ │ │ │ or globalforward_hooks or globalforward_pre_hooks): │ │
│ │ ❱ 1527 │ │ │ return forward_call(*args, **kwargs) │ │
│ │ 1528 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\tasks.py:89 │ │
│ │ in forward │ │
│ │ │ │
│ │ 88 │ │ │ return self.loss(x, args, *kwargs) │ │
│ │ ❱ 89 │ │ return self.predict(x, args, *kwargs) │ │
│ │ 90 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\tasks.py:10 │ │
│ │ 7 in predict │ │
│ │ │ │
│ │ 106 │ │ │ return self._predict_augment(x) │ │
│ │ ❱ 107 │ │ return self._predict_once(x, profile, visualize, embed) │ │
│ │ 108 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\tasks.py:12 │ │
│ │ 8 in predictonce │ │
│ │ │ │
│ │ 127 │ │ │ │ self._profile_one_layer(m, x, dt) │ │
│ │ ❱ 128 │ │ │ x = m(x) # run │ │
│ │ 129 │ │ │ y.append(x if m.i in self.save else None) # save output │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1518 in wrappedcall_impl │ │
│ │ │ │
│ │ 1517 │ │ else: │ │
│ │ ❱ 1518 │ │ │ return self._call_impl(*args, **kwargs) │ │
│ │ 1519 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1527 in callimpl │ │
│ │ │ │
│ │ 1526 │ │ │ │ or globalforward_hooks or globalforward_pre_hooks): │ │
│ │ ❱ 1527 │ │ │ return forward_call(*args, **kwargs) │ │
│ │ 1528 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\modules\hea │ │
│ │ d.py:112 in forward │ │
│ │ │ │
│ │ 111 │ │ mc = torch.cat([self.cv4[i](x[i]).view(bs, self.nm, -1) for i in range(self.nl)] │ │
│ │ ❱ 112 │ │ x = self.detect(self, x) │ │
│ │ 113 │ │ if self.training: │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1695 in getattr │ │
│ │ │ │
│ │ 1694 │ │ │ │ return modules[name] │ │
│ │ ❱ 1695 │ │ raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'" │ │
│ │ 1696 │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ AttributeError: 'Segment' object has no attribute 'detect' │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
---
@allelujahnightingale definitely outdated ultralytics, had the same issue. Forge does have a venv folder from what i can tell looking at webui.bat, what folders are in the forge folder?
@allelujahnightingale oh wait if it was installed with the 1click installer then there wont be one, gimme a minute
@aaaaaa12212332202 yeah i believe this setup was done with the 1 click installer.
@allelujahnightingale alright try going to system/python then open cmd in that dir, run the command "pip install --upgrade ultralytics"
@aaaaaa12212332202 ok so i did that just now, ran a test generation and got this error. Not sure if its the same one or if i did something wrong, but its another long one.
*** Error running postprocess_image: C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\scripts\!adetailer.py
Traceback (most recent call last):
File "C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\modules\scripts.py", line 883, in postprocess_image
script.postprocess_image(p, pp, *script_args)
File "C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\aaaaaa\traceback.py", line 173, in wrapper
raise error from None
AttributeError:
╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ System info │
│ ┏━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ │
│ ┃ ┃ Value ┃ │
│ ┡━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ │
│ │ Platform │ Windows-10-10.0.22631-SP0 │ │
│ │ Python │ 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] │ │
│ │ Version │ f0.0.17v1.8.0rc-latest-278-gbfee03d8 │ │
│ │ Commit │ bfee03d8d9415a925616f40ede030fe7a51cbcfd │ │
│ │ Commandline │ ['launch.py', '--theme', 'dark', '--ckpt-dir', │ │
│ │ │ 'C:/Users/USERNAME/OneDrive/Desktop/A1111/stable-diffusion-webui/models/Stable-diffusion', │ │
│ │ │ '--hypernetwork-dir', │ │
│ │ │ 'C:/Users/USERNAME/OneDrive/Desktop/A1111/stable-diffusion-webui/models/hypernetworks', │ │
│ │ │ '--embeddings-dir', 'C:/Users/USERNAME/OneDrive/Desktop/A1111/stable-diffusion-webui/embeddings', │ │
│ │ │ '--lora-dir', 'C:/Users/USERNAME/OneDrive/Desktop/A1111/stable-diffusion-webui/models/Lora'] │ │
│ │ Libraries │ {'torch': '2.1.2+cu121', 'torchvision': '0.16.2+cu121', 'ultralytics': '8.2.2', 'mediapipe': │ │
│ │ │ '0.10.14'} │ │
│ └─────────────┴────────────────────────────────────────────────────────────────────────────────────────────────┘ │
│ Inputs │
│ ┏━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ │
│ ┃ ┃ Value ┃ │
│ ┡━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ │
│ │ prompt │ anime artwork score_9, score_8_up, score_7_up, score_6_up, source_anime || okojo, 0k0j0 || │ │
│ │ │ 1girl, solo, full body || pregnant, round belly || small breasts || outie navel, big outie │ │
│ │ │ navel, hyper outie navel || navel ring, navel piercing || Digimon, digimon, │ │
│ │ │ digimon/(creature), humanoid, animal, beast, monster, creature, deity, mythical, royal │ │
│ │ │ knights, divine, divine judgement || furry, anthro, animal ears, animal nose, tail, claws, │ │
│ │ │ fur, fur body, white fur, colored eyes, large feet, long legs, long arms, big ears, long │ │
│ │ │ poibnty ears || body markings, face markings, arm markings, leg markings || detached │ │
│ │ │ sleeves, gloves, choker, baggy pants, robes, belts, straps, harness, belly harness, belly │ │
│ │ │ belt, belly strap, jewelry, gemstones, armor || cute, adorable, sexy, flirty, smug, │ │
│ │ │ taunting, seductive, temptress, mischievous || symmetrical || │ │
│ │ │ <lora:DigimonV1Pony:1.5> <lora:Pregnancy Slider_alpha1.0_rank4_noxattn_last:1> │ │
│ │ │ <lora:OkojoV1-6Pony:1> . anime style, key visual, vibrant, studio anime, highly detailed │ │
│ │ negative_prompt │ words, text, signature, watermark, key, cross, naked, nude, NSFW, nsfw, nipples │ │
│ │ n_iter │ 1 │ │
│ │ batch_size │ 1 │ │
│ │ width │ 512 │ │
│ │ height │ 1024 │ │
│ │ sampler_name │ Euler a │ │
│ │ enable_hr │ False │ │
│ │ hr_upscaler │ 4x-UltraSharp │ │
│ │ checkpoint │ ponyDiffusionV6XL_v6StartWithThisOne [67ab2fd8ec] │ │
│ │ vae │ sdxl_vae.safetensors │ │
│ │ unet │ Automatic │ │
│ └─────────────────┴────────────────────────────────────────────────────────────────────────────────────────────┘ │
│ ADetailer │
│ ┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓ │
│ ┃ ┃ Value ┃ │
│ ┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩ │
│ │ version │ 24.6.0 │ │
│ │ ad_model │ belly-segV3.pt │ │
│ │ ad_prompt │ │ │
│ │ ad_negative_prompt │ │ │
│ │ ad_controlnet_model │ openposeSDXL_v10 │ │
│ │ is_api │ False │ │
│ └─────────────────────┴───────────────────┘ │
│ ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\aaaaaa\traceback.py:153 in │ │
│ │ wrapper │ │
│ │ │ │
│ │ 152 │ │ try: │ │
│ │ ❱ 153 │ │ │ return func(*args, **kwargs) │ │
│ │ 154 │ │ except Exception as e: │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\scripts\!adetailer.py:818 in │ │
│ │ postprocess_image │ │
│ │ │ │
│ │ 817 │ │ │ │ │ continue │ │
│ │ ❱ 818 │ │ │ │ is_processed |= self._postprocess_image_inner(p, pp, args, n=n) │ │
│ │ 819 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\scripts\!adetailer.py:739 in │ │
│ │ postprocessimage_inner │ │
│ │ │ │
│ │ 738 │ │ with change_torch_load(): │ │
│ │ ❱ 739 │ │ │ pred = predictor(ad_model, pp.image, args.ad_confidence, **kwargs) │ │
│ │ 740 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\webui\extensions\adetailer\adetailer\ultralytics.py:29 in │ │
│ │ ultralytics_predict │ │
│ │ │ │
│ │ 28 │ apply_classes(model, model_path, classes) │ │
│ │ ❱ 29 │ pred = model(image, conf=confidence, device=device) │ │
│ │ 30 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\engine\model.p │ │
│ │ y:176 in call │ │
│ │ │ │
│ │ 175 │ │ """ │ │
│ │ ❱ 176 │ │ return self.predict(source, stream, **kwargs) │ │
│ │ 177 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\engine\model.p │ │
│ │ y:452 in predict │ │
│ │ │ │
│ │ 451 │ │ │ self.predictor.set_prompts(prompts) │ │
│ │ ❱ 452 │ │ return self.predictor.predict_cli(source=source) if is_cli else self.predictor(s │ │
│ │ 453 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\engine\predict │ │
│ │ or.py:168 in call │ │
│ │ │ │
│ │ 167 │ │ else: │ │
│ │ ❱ 168 │ │ │ return list(self.stream_inference(source, model, args, *kwargs)) # merge │ │
│ │ 169 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\engine\predict │ │
│ │ or.py:228 in stream_inference │ │
│ │ │ │
│ │ 227 │ │ │ if not self.done_warmup: │ │
│ │ ❱ 228 │ │ │ │ self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else se │ │
│ │ 229 │ │ │ │ self.done_warmup = True │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\autobackend │ │
│ │ .py:627 in warmup │ │
│ │ │ │
│ │ 626 │ │ │ for _ in range(2 if self.jit else 1): │ │
│ │ ❱ 627 │ │ │ │ self.forward(im) # warmup │ │
│ │ 628 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\autobackend │ │
│ │ .py:453 in forward │ │
│ │ │ │
│ │ 452 │ │ if self.pt or self.nn_module: │ │
│ │ ❱ 453 │ │ │ y = self.model(im, augment=augment, visualize=visualize, embed=embed) │ │
│ │ 454 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1518 in wrappedcall_impl │ │
│ │ │ │
│ │ 1517 │ │ else: │ │
│ │ ❱ 1518 │ │ │ return self._call_impl(*args, **kwargs) │ │
│ │ 1519 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1527 in callimpl │ │
│ │ │ │
│ │ 1526 │ │ │ │ or globalforward_hooks or globalforward_pre_hooks): │ │
│ │ ❱ 1527 │ │ │ return forward_call(*args, **kwargs) │ │
│ │ 1528 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\tasks.py:89 │ │
│ │ in forward │ │
│ │ │ │
│ │ 88 │ │ │ return self.loss(x, args, *kwargs) │ │
│ │ ❱ 89 │ │ return self.predict(x, args, *kwargs) │ │
│ │ 90 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\tasks.py:10 │ │
│ │ 7 in predict │ │
│ │ │ │
│ │ 106 │ │ │ return self._predict_augment(x) │ │
│ │ ❱ 107 │ │ return self._predict_once(x, profile, visualize, embed) │ │
│ │ 108 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\tasks.py:12 │ │
│ │ 8 in predictonce │ │
│ │ │ │
│ │ 127 │ │ │ │ self._profile_one_layer(m, x, dt) │ │
│ │ ❱ 128 │ │ │ x = m(x) # run │ │
│ │ 129 │ │ │ y.append(x if m.i in self.save else None) # save output │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1518 in wrappedcall_impl │ │
│ │ │ │
│ │ 1517 │ │ else: │ │
│ │ ❱ 1518 │ │ │ return self._call_impl(*args, **kwargs) │ │
│ │ 1519 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1527 in callimpl │ │
│ │ │ │
│ │ 1526 │ │ │ │ or globalforward_hooks or globalforward_pre_hooks): │ │
│ │ ❱ 1527 │ │ │ return forward_call(*args, **kwargs) │ │
│ │ 1528 │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\ultralytics\nn\modules\hea │ │
│ │ d.py:112 in forward │ │
│ │ │ │
│ │ 111 │ │ mc = torch.cat([self.cv4[i](x[i]).view(bs, self.nm, -1) for i in range(self.nl)] │ │
│ │ ❱ 112 │ │ x = self.detect(self, x) │ │
│ │ 113 │ │ if self.training: │ │
│ │ │ │
│ │ C:\Users\USERNAME\OneDrive\Desktop\Forge\system\python\lib\site-packages\torch\nn\modules\module.py │ │
│ │ :1695 in getattr │ │
│ │ │ │
│ │ 1694 │ │ │ │ return modules[name] │ │
│ │ ❱ 1695 │ │ raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'" │ │
│ │ 1696 │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ AttributeError: 'Segment' object has no attribute 'detect' │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
---
@allelujahnightingale yeah its the same error lol, well idk what else to do except maybe install forge / a1111 using git or using my other model (Does same thing, slightly less well) https://civitai.com/models/537813?modelVersionId=600390
@aaaaaa12212332202 alrighty lol was really hopping to get it to work but oh well. will take a look at your other one as well
Forge has a venv folder but this won't even go there, just go to your models folder and select adetailer and paste it in there. When you start forge again it will show under your adetailer models.
@JBob03 might not work since a package needs an update to even use it, which is why the venv needs to be accessed
I'm confused, what is this even for?
ADetailer is a program that allows the use of machine vision models to automatically inpaint. This is such a model
@aaaaaa12212332202 So would you use this in conjunction with another pregnancy lora?
@mrguy007 this isn't a Lora just to be clear, you wont be able to use this on civitai. But yeah, you can use Loras in the Adetailer options (at least as far as i know in a1111)
@aaaaaa12212332202 I see, so does it make pregnant bellies come out "better looking"?
@mrguy007 it can correct minor defects and make the look a little more detailed. Check the images people have posted below. https://github.com/Bing-su/adetailer - if you have a1111 and want to give adetailer a shot
@mrguy007 You use it with automatic1111 or comfyui plugin called "adetailer" - it lets you use a different prompt and different LoRas on only a specific part of the image. So if you find a good belly LoRa that messes up the face for example, you can use the belly LoRa on only the belly and it wont effect the face anymore.
Thank you so, so much for this. You have no idea how long I was waiting for one of these.