[bug]: Model not on gpu in inpaint function when using free_gpu_mem option

[rmagur1203]

Is there an existing issue for this?

• I have searched the existing issues

OS

Linux

GPU

cuda

VRAM

No response

What happened?

When using the free_gpu_mem option, the inpaint function does not implement a function to load the model back to the gpu.

Screenshots

No response

Additional context

Traceback (most recent call last):
  File "f:\novel\invokeai\ldm\generate.py", line 492, in prompt2image
    results = generator.generate(
  File "f:\novel\invokeai\ldm\invoke\generator\base.py", line 98, in generate
    image = make_image(x_T)
  File "F:\Anaconda3\envs\invokeai\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "f:\novel\invokeai\ldm\invoke\generator\inpaint.py", line 295, in make_image
    samples = sampler.decode(
  File "F:\Anaconda3\envs\invokeai\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "f:\novel\invokeai\ldm\models\diffusion\sampler.py", line 365, in decode
    outs = self.p_sample(
  File "F:\Anaconda3\envs\invokeai\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "f:\novel\invokeai\ldm\models\diffusion\ddim.py", line 58, in p_sample
    e_t = self.invokeai_diffuser.do_diffusion_step(
  File "f:\novel\invokeai\ldm\models\diffusion\shared_invokeai_diffusion.py", line 107, in do_diffusion_step
    unconditioned_next_x, conditioned_next_x = self.apply_standard_conditioning(x, sigma, unconditioning, conditioning)
  File "f:\novel\invokeai\ldm\models\diffusion\shared_invokeai_diffusion.py", line 123, in apply_standard_conditioning
    unconditioned_next_x, conditioned_next_x = self.model_forward_callback(x_twice, sigma_twice,
  File "f:\novel\invokeai\ldm\models\diffusion\ddim.py", line 13, in <lambda>
    model_forward_callback = lambda x, sigma, cond: self.model.apply_model(x, sigma, cond))
  File "f:\novel\invokeai\ldm\models\diffusion\ddpm.py", line 1441, in apply_model
    x_recon = self.model(x_noisy, t, **cond)
  File "F:\Anaconda3\envs\invokeai\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "f:\novel\invokeai\ldm\models\diffusion\ddpm.py", line 2167, in forward
    out = self.diffusion_model(x, t, context=cc)
  File "F:\Anaconda3\envs\invokeai\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "f:\novel\invokeai\ldm\modules\diffusionmodules\openaimodel.py", line 798, in forward
    emb = self.time_embed(t_emb)
  File "F:\Anaconda3\envs\invokeai\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "F:\Anaconda3\envs\invokeai\lib\site-packages\torch\nn\modules\container.py", line 139, in forward
    input = module(input)
  File "F:\Anaconda3\envs\invokeai\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "F:\Anaconda3\envs\invokeai\lib\site-packages\torch\nn\modules\linear.py", line 114, in forward
    return F.linear(input, self.weight, self.bias)
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_addmm)

Contact Details

No response