Inpainting doesn't work with the Cosmos Predict2 text to image model.

[StablePerception]

I'm on the latest version of ComfyUI and normal text to image generation with the model works well. But inpainting doesn't work at all.

When trying to use the InpaintModelConditioning node:

I get this error at the KSampler node: !!! Exception during processing !!! Dimension out of range (expected to be in range of [-4, 3], but got 4) Traceback (most recent call last): File "/home/user/ComfyUI/execution.py", line 361, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "/home/user/ComfyUI/execution.py", line 236, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "/home/user/ComfyUI/execution.py", line 208, in _map_node_over_list process_inputs(input_dict, i) File "/home/user/ComfyUI/execution.py", line 197, in process_inputs results.append(getattr(obj, func)(**inputs)) File "/home/user/ComfyUI/nodes.py", line 1516, in sample return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise) File "/home/user/ComfyUI/nodes.py", line 1483, in common_ksampler samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, File "/home/user/ComfyUI/comfy/sample.py", line 45, in sample samples = sampler.sample(noise, positive, negative, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed) File "/home/user/ComfyUI/comfy/samplers.py", line 1139, in sample return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed) File "/home/user/ComfyUI/comfy/samplers.py", line 1029, in sample return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "/home/user/ComfyUI/comfy/samplers.py", line 1014, in sample output = executor.execute(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "/home/user/ComfyUI/comfy/patcher_extension.py", line 111, in execute return self.original(*args, **kwargs) File "/home/user/ComfyUI/comfy/samplers.py", line 982, in outer_sample output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed) File "/home/user/ComfyUI/comfy/samplers.py", line 965, in inner_sample samples = executor.execute(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar) File "/home/user/ComfyUI/comfy/patcher_extension.py", line 111, in execute return self.original(*args, **kwargs) File "/home/user/ComfyUI/comfy/samplers.py", line 744, in sample samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options) File "/home/user/ComfyUI/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) File "/home/user/ComfyUI/comfy/k_diffusion/sampling.py", line 189, in sample_euler denoised = model(x, sigma_hat * s_in, **extra_args) File "/home/user/ComfyUI/comfy/samplers.py", line 396, in __call__ out = self.inner_model(x, sigma, model_options=model_options, seed=seed) File "/home/user/ComfyUI/comfy/samplers.py", line 945, in __call__ return self.predict_noise(*args, **kwargs) File "/home/user/ComfyUI/comfy/samplers.py", line 948, in predict_noise return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed) File "/home/user/ComfyUI/comfy/samplers.py", line 376, in sampling_function out = calc_cond_batch(model, conds, x, timestep, model_options) File "/home/user/ComfyUI/comfy/samplers.py", line 206, in calc_cond_batch return executor.execute(model, conds, x_in, timestep, model_options) File "/home/user/ComfyUI/comfy/patcher_extension.py", line 111, in execute return self.original(*args, **kwargs) File "/home/user/ComfyUI/comfy/samplers.py", line 325, in _calc_cond_batch output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks) File "/home/user/ComfyUI/comfy/model_base.py", line 151, in apply_model return comfy.patcher_extension.WrapperExecutor.new_class_executor( File "/home/user/ComfyUI/comfy/patcher_extension.py", line 111, in execute return self.original(*args, **kwargs) File "/home/user/ComfyUI/comfy/model_base.py", line 188, in _apply_model t = self.process_timestep(t, x=x, **extra_conds) File "/home/user/ComfyUI/comfy/model_base.py", line 1027, in process_timestep condition_video_mask_B_1_T_1_1 = denoise_mask.mean(dim=[1, 3, 4], keepdim=True) IndexError: Dimension out of range (expected to be in range of [-4, 3], but got 4)

When trying to use the VAE Encode (for Inpainting) node:

I get this error at the VAE Encode (for Inpainting) node: !!! Exception during processing !!! unsupported operand type(s) for //: 'int' and 'tuple' Traceback (most recent call last): File "/home/user/ComfyUI/execution.py", line 361, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "/home/user/ComfyUI/execution.py", line 236, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "/home/user/ComfyUI/execution.py", line 208, in _map_node_over_list process_inputs(input_dict, i) File "/home/user/ComfyUI/execution.py", line 197, in process_inputs results.append(getattr(obj, func)(**inputs)) File "/home/user/ComfyUI/nodes.py", line 369, in encode x = (pixels.shape[1] // vae.downscale_ratio) * vae.downscale_ratio TypeError: unsupported operand type(s) for //: 'int' and 'tuple'