@CaptGeek Actually, yes. The person who made that for reached out, but said it would need to be cleaned up before including in Ai Render. I'm happy to have the collaboration from anyone who wants to jump in!
Updated demo of this web novel to ebook to audiobook to feature film project.
It lives! It can now:
1. Crawl web novel
2. Do a bunch of LLM stuff
3. Text to speech on all narration and dialogue with different voices for each significant character
4. Stitch audio into audio book π
5. Create frame by frame storyboard with images
5. Stitch images together into video slideshow with audio book timing synced
Next steps:
- play with custom character loras and inpainting the storyboard images to create more consistent characters in them
- create more key frames and test out a few key frame to key frame img2video models
I'll post some demo videos to show the current outputs.
Back to work work in the AM but was a very fun holiday!
Fresh out of the oven! A reel of my brainchild from the past 6 months! Thank you for 1000 followers!
Sound on!
Created with @StabilityAI SVD, @runwayml , @pika_labs , @midjourney and #AnimateDiff
Music: Chris Avantgarde - Inside (ft. Red Rosamond)
This is amazing. Stable Cascade dropped last week while we were busy with OpenAI Sora and Google Gemini π
It can generates images significantly faster while maintaining image quality. π€―
10 wild examples (including live demo and code repo below): π§΅π
π€― Mind officially blown:
I recorded a screen capture of a task (looking for an apartment on Zillow). Gemini was able to generate Selenium code to replicate that task, and described everything I did step-by-step.
It even caught that my threshold was set to $3K, even though I didn't explicitly select it. π€―π₯
"This code will open a Chrome browser, navigate to Zillow, enter "Cupertino, CA" in the search bar, click on the "For Rent" tab, set the price range to "Up to $3K", set the number of bedrooms to "2+", select the "Apartments/Condos/Co-ops" checkbox, click on the "Apply" button, wait for the results to load, print the results, and close the browser."
@Quincey_Forder@Blender Good questions. It doesn't work with LoRA models right now, and there isn't a direct way to send the image to the Automatic1111 interface, unfortunately. I'll have to check to see if Automatic1111 has a way to do that now. (It didn't before)
[NEW] - Joshua Avatar 2.0 π€β¨. Both of these video clips were 100% AI-generated, featuring my own avatar and voice clone. ποΈπ₯
We've made massive enhancements to our life-style avatar's video quality and fine-tuned our voice technology to mimic my unique accent and speech patterns perfectly. ππ
Let me know how you like it. π This will be soon deployed to production and everyone can try it out! ππ
Midjourney-to-3D is now available!
(Indeed, you can convert any 2D image to 3D)
https://t.co/ii0y904taL
Please note that, for now, you'll need to manually set a depth map for your image in order to view its correct 3D version.
(You can use https://t.co/Lf17Q9hPOG to generate the depth map)
But... stay tuned! We'll soon be offering instant 3D conversion for any image.
*This is just an experimental version, and any feedback or videos of your results would be really interesting to see!