I've updated my 3 latent consistency models on Replicate so they now all have Canny controlnet support: https://
replicate.com/fofr/latent-co
nsistency-model
… https://
replicate.com/fofr/lcm-anima
tion
… https://
replicate.com/fofr/lcm-video
2video
… Thank you to @radamar and taabata’s Comfy UI workflows
@fofrai
-
Latent Consistency Models Updated with Canny ControlNet Support
By
–
-
YouTune: Fine-tune MusicGen with YouTube Audio
By
–
I've added a feature to @charliebholtz’s YouTune, you can now easily fine-tune MusicGen using the audio from YouTube videos:
— fofr (@fofrAI) 8 novembre 2023
> python tune.py <youtube-url> –audio
Try it here:https://t.co/e4vNmeWEeX https://t.co/0bVV98SGka pic.twitter.com/1arMNKmJq0I've added a feature to @charlieholtz
’s YouTune, you can now easily fine-tune MusicGen using the audio from YouTube videos: > python tune.py –audio Try it here: https://
github.com/cbh123/youtune -
ChatGPT Voice Feature Issues With Web Search Transcript
By
–
This morning I tried using voice to ask ChatGPT to get some football scores from the web, as now it has all the features baked in. Seemed like it was working, but then I checked the transcript.
-
GPT-4 Vision and DALL-E 3 iterative avatar generation
By
–
I'm using GPT4 vision and dalle3 together to try and reproduce my abstract avatar. I asked it to: – analyze the original image
– analyze the generation
– iterate the prompt to improve accuracy These were the results of 4 iterations. -
ControlNet for LCM Now Available for Image Generation
By
–
Oh nice! I didn't know controlnet for LCM had landed.
-
OpenAI Text-to-Speech API: Weird Experiments Thread
By
–
OpenAI text2speech API.
— fofr (@fofrAI) 7 novembre 2023
A thread of weird experiments 🧵
Based. pic.twitter.com/yseNPDeSiXOpenAI text2speech API. A thread of weird experiments Based.
-
Combining AI Voices, Images, and Video Generation with Lip Sync
By
–
– OpenAI voices
– Midjourney image
– Runway Gen2 image to video
– VideoReTalking for lip sync https://
replicate.com/cjwbw/video-re
talking
… -
VideoReTalking AI Model Now Available on Replicate Platform
By
–
ReTalking model on Replicate https://
replicate.com/cjwbw/video-re
talking
… -
OpenAI Text-to-Speech Voices Layered for Borg Lip-Sync
By
–
Decided to get all the OpenAI text-to-speech voices to say the same thing and then layer them all back over each other.
— fofr (@fofrAI) 7 novembre 2023
And then lip-sync it to a borg.
It's interesting that the different voices all had exactly the same duration of output for the text. pic.twitter.com/Rl3ih3uDQADecided to get all the OpenAI text-to-speech voices to say the same thing and then layer them all back over each other. And then lip-sync it to a borg. It's interesting that the different voices all had exactly the same duration of output for the text.
-
Handling Large JSON Files Within Token Limits
By
–
I tried a 12mb json file which was too many tokens, I think 200k limit. I tried a smaller json file and it needed instructions on structure to efficiently search it.