Error with loading any embeddings using ROCm running natively

[mohmmdgaber]

Getting this error when trying to load any Aesthetic imgs embedding

Aesthetic optimization:   0%|                                                                                                                                                                                             | 0/5 [00:00<?, ?it/s]
Error completing request
Arguments: ('test prompt', '', 'None', 'None', 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 0, 0, 0, 0.9, 5, '0.0001', False, 'dreambooth', '', 0.1, False, False, False, None, '', 1, '', 0, '', True, False, False) {}
Traceback (most recent call last):
  File "/home/mo/Stable-diff/stable-diffusion-webui/modules/ui.py", line 221, in f
    res = list(func(*args, **kwargs))
  File "/home/mo/Stable-diff/stable-diffusion-webui/webui.py", line 63, in f
    res = func(*args, **kwargs)
  File "/home/mo/Stable-diff/stable-diffusion-webui/modules/txt2img.py", line 48, in txt2img
    processed = process_images(p)
  File "/home/mo/Stable-diff/stable-diffusion-webui/modules/processing.py", line 426, in process_images
    uc = prompt_parser.get_learned_conditioning(shared.sd_model, len(prompts) * [p.negative_prompt], p.steps)
  File "/home/mo/Stable-diff/stable-diffusion-webui/modules/prompt_parser.py", line 138, in get_learned_conditioning
    conds = model.get_learned_conditioning(texts)
  File "/home/mo/Stable-diff/stable-diffusion-webui/repositories/stable-diffusion/ldm/models/diffusion/ddpm.py", line 558, in get_learned_conditioning
    c = self.cond_stage_model(c)
  File "/home/mo/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1363, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/mo/Stable-diff/stable-diffusion-webui/modules/sd_hijack.py", line 334, in forward
    z1 = self.process_tokens(tokens, multipliers)
  File "/home/mo/Stable-diff/stable-diffusion-webui/extensions/aesthetic-gradients/aesthetic_clip.py", line 233, in __call__
    sim = text_embs @ img_embs.T
AttributeError: 'dict' object has no attribute 'T'

[oohohoo]

similar here:

Aesthetic optimization: 0% 0/5 [00:00<?, ?it/s] Error completing request Arguments: ('a cat', '((((ugly)))), (((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), (((group photo))), (((more than one person))), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face, (((disfigured))), out of frame, ugly, extra limbs, (bad anatomy), gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), (((headers))), (((logo)), (((letters))), (((font))), (((watermark))), (((double head)))', 'None', 'None', 100, 12, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 0, 0, 0, 0.9, 5, '0.0001', False, 'fantasy', '', 0.1, False, False, False, None, '', 1, '', 0, '', True, False, False) {} Traceback (most recent call last): File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/ui.py", line 185, in f res = list(func(*args, *kwargs)) File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/webui.py", line 63, in f res = func(args, kwargs) File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/txt2img.py", line 48, in txt2img processed = process_images(p) File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/processing.py", line 426, in process_images res = process_images_inner(p) File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/processing.py", line 508, in process_images_inner uc = prompt_parser.get_learned_conditioning(shared.sd_model, len(prompts) [p.negative_prompt], p.steps) File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/prompt_parser.py", line 138, in get_learned_conditioning conds = model.get_learned_conditioning(texts) File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/ldm/models/diffusion/ddpm.py", line 558, in get_learned_conditioning c = self.cond_stage_model(c) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(input, kwargs) File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/sd_hijack.py", line 334, in forward z1 = self.process_tokens(tokens, multipliers) File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-aesthetic-gradients/aesthetic_clip.py", line 233, in call sim = text_embs @ img_embs.T AttributeError: 'NoneType' object has no attribute 'T'

[initialxy]

I got the same error. However looking just above these console outputs, I saw this.

...
Exception: bad file inside /home/initialxy/git/stable-diffusion-webui/extensions/aesthetic-gradients/aesthetic_embeddings/my.pt: my/data.pkl

The file may be malicious, so the program is not going to read it.
You can skip this check with --disable-safe-unpickle commandline argument.

So I launched launcher.py with --disable-safe-unpickle and it worked.