mishu2

Thank you everyone for taking a look. The website had around 1,200 visitors and received over 90 sketches over the past 24 hours, and I'm happy to say I could approve almost all of them (all except 2 'rocket' sketches which were starting to look a bit dubious, but all in good fun).

The results look very interesting to me, and I think as a next step I will look into adjusting the prompts (both positive and negative). On the one hand, I'd like to keep the sketch/drawing look rather than going full photorealism as some of the videos do, on the other hand I don't want to restrict the users' creativity too much.

I plan to simplify this further and optimize it for tablets. Some friends said they'd like to have their kids try it out it and I like the idea, as by having to sketch it keeps the user in a more active role.

Please let me know if you have any other suggestions.

I'm actually trying to reduce the 'funkyness', initially the idea was to start from a child's sketch and bring it to life (so kids can safely use it as part of an exhibit at an art festival) :)

There's a world of possibilities though, I hadn't even thought of combining color channels.

I think the main reason is that the model has a lot of training material with Chinese text in it (I'm assuming, since the research group who released it is from China), but having the negative prompt in Chinese might also play a role.

What I've found interesting so far is that sometimes the image plays a big part in the final video, but other times it gets discarded almost immediately after the first few frames. It really depends on the prompt, so prompt engineering is (at least for this model) even more important than I expected. I'm now thinking of adding a 'system' positive prompt and appending the user prompt to it.

Once you set up a pipeline, sure. They'd need a lot of bandwidth to ensure the combined output makes any kind of sense, not unlike the GPU I guess.

Otherwise it's similar to the way nine women can make a baby in a month. :)

Thank you. I've noticed that too, and also that it has a tendency to introduce garbled text when not given a prompt (or a short one).

This is using the default parameters for the ComfyUI workflow (including a negative prompt written in Chinese), so there is a lot of room for adjustments.

Thank you. I'm running it locally on a 4090 (24 GB).

I was running into OOM issues with Wan 2.2 before, but I found the latest version of ComfyUI can now run it (using about 17 GB of VRAM for what I assume is a quantized model?).

Author here, I forgot to mention the project is written using Svelte 5 and daisyUI, because I wanted to try the tech stack out.

I have to say I quite like it for more complex interactive components like this one, but still much prefer django with some htmx + Stimulus JS sprinkled in for the rest of the website.

Thank you for the feedback, that's a point that several commenters have brought up.

The problem with the interdental brushing video specifically is that we can't show how to use larger brushes on young healthy patients, as they don't have the spaces for it. But I will think about how we can improve that video (the comment above suggested moving it down in the page, to start with the 'gentler' videos).