depthmap2mask icon indicating copy to clipboard operation
depthmap2mask copied to clipboard

All models except midas give a KeyError

Open magestyx opened this issue 1 year ago • 0 comments

I'm using the latest Stable Diffusion and depthmap2mask. I've tried using all the models, and they download fine but only the midas ones work. All others give an error 'Loading midas model weights'. Every model that starts with 'dpt' gives a KeyError.

Traceback (most recent call last): File "C:\stable-diffusion\stable-diffusion-webui-master\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "C:\stable-diffusion\stable-diffusion-webui-master\modules\call_queue.py", line 37, in f res = func(*args, **kwargs) File "C:\stable-diffusion\stable-diffusion-webui-master\modules\img2img.py", line 179, in img2img processed = modules.scripts.scripts_img2img.run(p, *args) File "C:\stable-diffusion\stable-diffusion-webui-master\modules\scripts.py", line 407, in run processed = script.run(p, *script_args) File "C:\stable-diffusion\stable-diffusion-webui-master\extensions\depthmap2mask\scripts\depth2image_depthmask.py", line 97, in run d_m = sdmg.calculate_depth_maps(p.init_images[0],img_x,img_y,model_type,invert_depth) File "C:\stable-diffusion\stable-diffusion-webui-master\extensions/depthmap2mask/scripts/depthmap_for_depth2img.py", line 294, in calculate_depth_maps model, transform = load_model(device, model_path, models[model_type_index], (img_x, img_y)) File "C:\stable-diffusion\stable-diffusion-webui-master\extensions/depthmap2mask/scripts/depthmap_for_depth2img.py", line 41, in load_model model = DPTDepthModel( File "C:\stable-diffusion\stable-diffusion-webui-master\repositories\midas\midas\dpt_depth.py", line 102, in init super().init(head, **kwargs) File "C:\stable-diffusion\stable-diffusion-webui-master\repositories\midas\midas\dpt_depth.py", line 55, in init hooks=hooks[backbone], KeyError: 'beitl16_512'

magestyx avatar May 09 '23 18:05 magestyx