[BUG] does not work with --medvram

[dnl13]

Describe the bug
This extension stops working completely for me when "set COMMANDLINE_ARGS= --medvram" is applied in "webui-user.bat."

To Reproduce
Steps to reproduce the behavior:
add --medvram to COMMANDLINE_ARGS in webui-user.bat file, it gives errors
remove --medvram and it works
you can toggle the error in this way

Expected behavior
should work with --medvram applied

Screenshots of error
error when --medvram is applied

Batch 1/1
Loading weights [ef76aa2332] from E:\stable-diffusion-webui\models\Stable-diffusion\models\1.5\realisticVisionV51_v51VAE.safetensors
Creating model from config: E:\stable-diffusion-webui\configs\v1-inference.yaml
Applying attention optimization: xformers... done.
*** Error completing request
*** Arguments: ('Huge spectacular Waterfall in ', [[0, 'a dense tropical forest'], [2, 'a Lush jungle'], [3, 'a Thick rainforest'], [5, 'a Verdant canopy']], 'epic perspective,(vegetation overgrowth:1.3)(intricate, ornamentation:1.1),(baroque:1.1), fantasy, (realistic:1) digital painting , (magical,mystical:1.2) , (wide angle shot:1.4), (landscape composed:1.2)(medieval:1.1),(tropical forest:1.4),(river:1.3) volumetric lighting ,epic, style by Alex Horley Wenjun Lin greg rutkowski Ruan Jia (Wayne Barlowe:1.2)', 'frames, border, edges, borderline, text, character, duplicate, error, out of frame, watermark, low quality, ugly, deformed, blur, bad-artist', 5, 8, 35, None, None, 30, 0, 0, 0, 48, 2, 1, -1, 512, 512, 1, 'DDIM', False, 'None', 2, 1, 0, 0, None) {}
    Traceback (most recent call last):
      File "E:\stable-diffusion-webui\modules\call_queue.py", line 57, in f
        res = list(func(*args, **kwargs))
      File "E:\stable-diffusion-webui\modules\call_queue.py", line 36, in f
        res = func(*args, **kwargs)
      File "E:\stable-diffusion-webui\extensions\infinite-zoom-automatic1111-webui\iz_helpers\run.py", line 200, in create_zoom
        result = create_zoom_single(
      File "E:\stable-diffusion-webui\extensions\infinite-zoom-automatic1111-webui\iz_helpers\run.py", line 357, in create_zoom_single
        load_model_from_setting(
      File "E:\stable-diffusion-webui\extensions\infinite-zoom-automatic1111-webui\iz_helpers\helpers.py", line 48, in load_model_from_setting
        modules.sd_models.load_model(checkinfo)
      File "E:\stable-diffusion-webui\modules\sd_models.py", line 649, in load_model
        sd_model.cond_stage_model_empty_prompt = get_empty_cond(sd_model)
      File "E:\stable-diffusion-webui\modules\sd_models.py", line 537, in get_empty_cond
        return sd_model.cond_stage_model([""])
      File "E:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
        return forward_call(*args, **kwargs)
      File "E:\stable-diffusion-webui\modules\sd_hijack_clip.py", line 234, in forward
        z = self.process_tokens(tokens, multipliers)
      File "E:\stable-diffusion-webui\modules\sd_hijack_clip.py", line 273, in process_tokens
        z = self.encode_with_transformers(tokens)
      File "E:\stable-diffusion-webui\modules\sd_hijack_clip.py", line 326, in encode_with_transformers
        outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers)
      File "E:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
        result = hook(self, args)
      File "E:\stable-diffusion-webui\modules\lowvram.py", line 52, in send_me_to_gpu
        module_in_gpu.to(cpu)
      File "E:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1145, in to
        return self._apply(convert)
      File "E:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
        module._apply(fn)
      File "E:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
        module._apply(fn)
      File "E:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
        module._apply(fn)
      [Previous line repeated 2 more times]
      File "E:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 820, in _apply
        param_applied = fn(param)
      File "E:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1143, in convert
        return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
    NotImplementedError: Cannot copy out of meta tensor; no data!

---
Traceback (most recent call last):
  File "E:\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict
    output = await app.get_blocks().process_api(
  File "E:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1434, in process_api
    data = self.postprocess_data(fn_index, result["prediction"], state)
  File "E:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1297, in postprocess_data
    self.validate_outputs(fn_index, predictions)  # type: ignore
  File "E:\stable-diffusion-webui\venv\lib\site-packages\gradio\blocks.py", line 1272, in validate_outputs
    raise ValueError(
ValueError: An event handler (create_zoom) didn't receive enough output values (needed: 5, received: 4).
Wanted outputs:
    [video, gallery, textbox, html, html]
Received outputs:
    [None, "", "", "<div class='error'>NotImplementedError: Cannot copy out of meta tensor; no data!</div><div class='performance'><p class='time'>Time taken: <wbr><span class='measurement'>2.9 sec.</span></p><p class='vram'><abbr title='Active: peak amount of video memory used during generation (excluding cached data)'>A</abbr>: <span class='measurement'>0.27 GB</span>, <wbr><abbr title='Reserved: total amout of video memory allocated by the Torch library '>R</abbr>: <span class='measurement'>0.28 GB</span>, <wbr><abbr title='System: peak amout of video memory allocated by all running programs, out of total capacity'>Sys</abbr>: <span class='measurement'>2.2/8 GB</span> (27.0%)</p></div>"]

without --medvram

Batch 1/1
Loading weights [ef76aa2332] from E:\stable-diffusion-webui\models\Stable-diffusion\models\1.5\realisticVisionV51_v51VAE.safetensors
Creating model from config: E:\stable-diffusion-webui\configs\v1-inference.yaml
Applying attention optimization: xformers... done.
Model loaded in 3.2s (load weights from disk: 0.2s, create model: 0.3s, apply weights to model: 2.4s).
100%|██████████████████████████████████████████████████████████████████████████████████| 35/35 [00:05<00:00,  6.96it/s]
Loading weights [4dafaba867] from E:\stable-diffusion-webui\models\Stable-diffusion\inpaints\realisticVisionV51_v51VAE-inpainting.safetensors00:03<00:00,  9.43it/s]
Creating model from config: E:\stable-diffusion-webui\configs\v1-inpainting-inference.yaml
Applying attention optimization: xformers... done.
Model loaded in 2.5s (load weights from disk: 0.2s, create model: 0.3s, apply weights to model: 1.8s).
Outpaint step: 1 / 5 Seed: -1
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 33/33 [00:03<00:00,  9.25it/s]
Outpaint step: 2 / 5 Seed: -1 9.43it/s]
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 33/33 [00:03<00:00,  9.37it/s]
Outpaint step: 3 / 5 Seed: -1  9.36it/s]
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 33/33 [00:03<00:00,  9.36it/s]
Outpaint step: 4 / 5 Seed: -1  9.35it/s]
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 33/33 [00:03<00:00,  9.37it/s]
Outpaint step: 5 / 5 Seed: -1  9.33it/s]
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 33/33 [00:03<00:00,  9.36it/s]
Video saved in: E:\stable-diffusion-webui\outputs\infinite-zooms\infinite_zoom_1694025954.mp4

Desktop (please complete the following information):

• OS: Windows 10, RTX 2070Super 8GB
• Version
  infinite-zoom-automatic1111-webui version: d6461e7
  automatic1111 : version: [v1.6.0] •  python: 3.10.11  •  torch: 2.0.1+cu118  •  xformers: 0.0.20  •  gradio: 3.41.2  • 

Additional context
my complete "set COMMANDLINE_ARGS=--xformers --always-batch-cond-uncond --medvram --medvram-sdxl --no-half-vae --api --autolaunch --update-check --update-all-extensions"

Removing "--medvram" from "set COMMANDLINE_ARGS="
will fix it, but i need --medvram for other tasks in automatic1111 also, would be nice not to switch back and forth

I did not test it in a fresh install without other extensions, so I can't tell if other extensions are interfering.

Thank you, and I'm hoping that exit_frame will be merged into the main branch soon.