[Bug]: "lerp_kernel_scalar" not implemented for 'Half'

[Aypixl]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What happened?

Upon attempting to render using inpaint, i get a runtime error "lerp_kernel_scalar" not implemented for 'Half'

Steps to reproduce the problem

First inpaint attempt after fresh install with URPM safetensors

What should have happened?

the image should be rendered

Version or Commit where the problem happens

n/.a

What Python version are you running on ?

Python 3.10.x

What platforms do you use to access the UI ?

Windows

What device are you running WebUI on?

AMD GPUs (RX 6000 above)

Cross attention optimization

None

What browsers do you use to access the UI ?

Google Chrome

Command Line Arguments

no

List of extensions

no

Console logs

venv "C:\Users\Tom\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
fatal: No names found, cannot describe anything.
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: 1.5.1
Commit hash: 723974a8b74ffd5acc1a1fdaf36e9c2426651537
Launching Web UI with arguments:
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
Loading weights [3cb09d984c] from C:\Users\Tom\stable-diffusion-webui-directml\models\Stable-diffusion\uberRealisticPornMerge_urpmv13Inpainting.safetensors
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 5.7s (launcher: 0.3s, import torch: 2.0s, import gradio: 0.6s, setup paths: 0.5s, other imports: 1.1s, load scripts: 0.7s, create ui: 0.3s, gradio launch: 0.1s).
Creating model from config: C:\Users\Tom\stable-diffusion-webui-directml\configs\v1-inpainting-inference.yaml
LatentInpaintDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.54 M params.
Applying attention optimization: InvokeAI... done.
Model loaded in 2.6s (load weights from disk: 0.5s, create model: 0.3s, apply weights to model: 0.5s, apply half(): 0.5s, move model to device: 0.8s).
*** Error completing request
*** Arguments: ('task(lb3n7hr2lhe8mpf)', 2, 'boobs', '', [], <PIL.Image.Image image mode=RGBA size=620x1014 at 0x23468127FA0>, None, {'image': <PIL.Image.Image image mode=RGBA size=620x1014 at 0x234681269E0>, 'mask': <PIL.PngImagePlugin.PngImageFile image mode=RGBA size=620x1014 at 0x234681276A0>}, None, None, None, None, 40, 0, 4, 0, 0, False, False, 1, 1, 7, 1.5, 0.75, -1.0, -1.0, 0, 0, 0, False, 0, 512, 512, 1, 0, 1, 32, 0, '', '', '', [], False, [], '', <gradio.routes.Request object at 0x0000023468126800>, 0, '<ul>\n<li><code>CFG Scale</code> should be 2 or lower.</li>\n</ul>\n', True, True, '', '', True, 50, True, 1, 0, False, 4, 0.5, 'Linear', 'None', '<p style="margin-bottom:0.75em">Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8</p>', 128, 8, ['left', 'right', 'up', 'down'], 1, 0.05, 128, 4, 0, ['left', 'right', 'up', 'down'], False, False, 'positive', 'comma', 0, False, False, '', '<p style="margin-bottom:0.75em">Will upscale the image by the selected scale factor; use width and height sliders to set tile size</p>', 64, 0, 2, 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0) {}
    Traceback (most recent call last):
      File "C:\Users\Tom\stable-diffusion-webui-directml\modules\call_queue.py", line 58, in f
        res = list(func(*args, **kwargs))
      File "C:\Users\Tom\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
        res = func(*args, **kwargs)
      File "C:\Users\Tom\stable-diffusion-webui-directml\modules\img2img.py", line 232, in img2img
        processed = process_images(p)
      File "C:\Users\Tom\stable-diffusion-webui-directml\modules\processing.py", line 680, in process_images
        res = process_images_inner(p)
      File "C:\Users\Tom\stable-diffusion-webui-directml\modules\processing.py", line 737, in process_images_inner
        p.init(p.all_prompts, p.all_seeds, p.all_subseeds)
      File "C:\Users\Tom\stable-diffusion-webui-directml\modules\processing.py", line 1375, in init
        self.image_conditioning = self.img2img_image_conditioning(image, self.init_latent, image_mask)
      File "C:\Users\Tom\stable-diffusion-webui-directml\modules\processing.py", line 279, in img2img_image_conditioning
        return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
      File "C:\Users\Tom\stable-diffusion-webui-directml\modules\processing.py", line 250, in inpainting_image_conditioning
        conditioning_image = torch.lerp(
    RuntimeError: "lerp_kernel_scalar" not implemented for 'Half'

---

Additional information

No response

[w-e-w]

stable-diffusion-webui-directml

[Aypixl]

sorry, I don't understand....this hasn't helped

stable-diffusion-webui-directml

[w-e-w]

you are not using AUTOMATIC1111/stable-diffusion-webui your are using lshqqytiger/stable-diffusion-webui-directml which is a fork of AUTOMATIC1111/stable-diffusion-webui that's specifically changes stuff that supports AMD using DirectML when CUDA & ROCm backend are unavailable if you have issues with lshqqytiger/stable-diffusion-webui-directml you should go report to lshqqytiger/stable-diffusion-webui-directml

[Aypixl]

ah okay, sorry I assumed to come here. Thanks for your time anyways mate.