Add FAQs to README + Common example snippets

[nateraw]

Keep getting same questions about things, should just put these in readme:

• [ ] Snippet: Loading 2.0+ models
• [ ] Snippet: Loading local models
• [ ] Question: Can you use custom non-generated images?
• [ ] Question: Controlling FPS/Video Generation params

Feel free to add/suggest more here if you are creeping on this issue and its still open. I'll make this PR asap

[jtoy]

would love to see common numbers to use as well, I ran a couple of experiments and so far the videos don't come out as good as the examples.

[quintendewilde]

Hi is it possible to show some examples on how to match the seeds.

I've managed to start the image part, but got errors when trying to create the video. So I have several folders on G drive with images, but no idea where to add those seeds to restart the video generation from those images.

This is the error I get when trying to generate the movie. Maybe there is something else I'm doing wrong.

`Traceback (most recent call last):
  File "/usr/local/lib/python3.8/dist-packages/gradio/routes.py", line 374, in run_predict
    output = await app.get_blocks().process_api(
  File "/usr/local/lib/python3.8/dist-packages/gradio/blocks.py", line 1017, in process_api
    result = await self.call_function(
  File "/usr/local/lib/python3.8/dist-packages/gradio/blocks.py", line 835, in call_function
    prediction = await anyio.to_thread.run_sync(
  File "/usr/local/lib/python3.8/dist-packages/anyio/to_thread.py", line 31, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "/usr/local/lib/python3.8/dist-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
    return await future
  File "/usr/local/lib/python3.8/dist-packages/anyio/_backends/_asyncio.py", line 867, in run
    result = context.run(func, *args)
  File "/usr/local/lib/python3.8/dist-packages/stable_diffusion_videos/app.py", line 91, in fn_videos
    return self.pipeline.walk(**kwargs)
  File "/usr/local/lib/python3.8/dist-packages/stable_diffusion_videos/stable_diffusion_pipeline.py", line 878, in walk
    return make_video_pyav(
  File "/usr/local/lib/python3.8/dist-packages/stable_diffusion_videos/stable_diffusion_pipeline.py", line 123, in make_video_pyav
    frames = frames.permute(0, 2, 3, 1)
AttributeError: 'NoneType' object has no attribute 'permute'`

[nateraw]

Examples. note to myself. add these to readme with accordion

SD 1.4

from stable_diffusion_videos import StableDiffusionWalkPipeline
import torch

device = "mps" if torch.backends.mps.is_available() else "cuda" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if device == "cuda" else torch.float32
pipe = StableDiffusionWalkPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    torch_dtype=torch_dtype,
    safety_checker=None
).to(device)

pipe.walk(
    prompts=['a cat', 'a dog'],
    seeds=[1234, 4321],
    num_interpolation_steps=5,
    num_inference_steps=30,
    fps=5
)

SD 1.5

from stable_diffusion_videos import StableDiffusionWalkPipeline
import torch

device = "mps" if torch.backends.mps.is_available() else "cuda" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if device == "cuda" else torch.float32
pipe = StableDiffusionWalkPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch_dtype,
    safety_checker=None,
).to(device)

pipe.walk(
    prompts=['a cat', 'a dog'],
    seeds=[1234, 4321],
    num_interpolation_steps=5,
    num_inference_steps=30,
    fps=5
)

SD 2.1

import torch

from stable_diffusion_videos import StableDiffusionWalkPipeline
from diffusers import DPMSolverMultistepScheduler

device = "mps" if torch.backends.mps.is_available() else "cuda" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if device == "cuda" else torch.float32
pipe = StableDiffusionWalkPipeline.from_pretrained(
    "stabilityai/stable-diffusion-2-1",
    torch_dtype=torch_dtype,
).to(device)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)

pipe.walk(
    prompts=['a cat', 'a dog'],
    seeds=[1234, 4321],
    num_interpolation_steps=5,
    num_inference_steps=50,
    fps=5,
)