Viewing profile — synapticpaint

The camera motions do not need to be the same. Gaussian splatting reconstructs the scene in 3d, and you can then render the scene from arbitrary angles, so they just gave it a rand…

This technology is already close to making animation. Check out some of my experiments with text to video here: https://www.youtube.com/watch?v=CgKNTAjQpkk https://youtu.be/X0AhqMh…

Pretty close. Not the same kind of animation, but here are some of my experiments with text to video for narrative content: https://www.youtube.com/watch?v=CgKNTAjQpkk https://yout…

"The flickering comes from the fundamental nature of the de-noising mechanism involved in the diffusion model." -- agreed "Keeping the same seed wouldn't be helpful if you want the…

Are you using canny mode? One of the other modes (HED, segmentation, or depth) may give you more consistency. Lmk how it goes if you try this.

Not really, but I think there are other things you can do to reduce flickering that I'm looking into.

Yes, it's asking SD for an image with some set of characteristics, and SD has some notion of what is plausible from what it saw during training.

No, ControlNet wasn't made to solve temporal consistency, it was made to add more control (hence the name) to image models. I am using it in a way that the authors may not have tho…

So, the video was generated by applying ControlNet to the input video frame by frame. Every inference setting is the same for every frame -- seed, prompt, CFG, steps, and sampler. …

Correct, it's generated by SD.

Here is a preliminary test for video editing using ControlNet I made: https://www.youtube.com/watch?v=u52MOA4YaGk As you can see, there is still quite a bit of flicker, I'm working…

Proof of concept for video to video editing. An input video is transformed to an output that matches the pose but with an AI generated character via a prompt. There is some flicker…

I wouldn't say that "the opportunity all seems to be on the front end". Specifically for stable diffusion, there are a lot of different ways to use the model. I think we're just st…

Hi, I run http://synapticpaint.com/ and using AI image generation for graphic novels/comics is one of the directions I'm exploring. If you're interested in collaborating to make yo…

On AWS, a g5 instance costs $1/hr. I can generate roughly 10 images per minute (should be able to get this down with some optimization), so 600 images per hour, so the cost per ima…

"Finally, a vital question is, how will this affect today’s working artists? Here the answer is not so optimistic." I have a different take on this. I think this technology will al…

I've been working on https://synapticpaint.com/ to make content creation easier and more accessible to people. As part of this, I've been building a DreamBooth ecosystem around the…

Cheaper services are here now: https://synapticpaint.com/ I charge $2-$4 per model training. I don't think that the profile pic/avatar space is going to be very profitable. As you …

I don't think that AI image generation in its current form replaces human creativity. You still need a human to guide the process, compose the image, judge the output, etc. What's …

That's true. I just wanted to provide some context for OP and others reading since they mentioned an interest in AI generation, and I think not everyone knows that dreambooth + sta…

It sounds like your app turns photos into a watercolor style image? You can definitely do this faster with Stable Diffusion (~6s per image before optimization). Here's how I would …

Agree that dreambooth is the future. I'm building an app that lets users with no technical background train their own dreambooth models for $2-$4: https://synapticpaint.com/dreambo…

I'm building an app that lets users with no technical background train their own dreambooth models for $2-$4: https://synapticpaint.com/dreambooth/info/ They can also share their t…