
Doron Adler
@Norod78
Followers
4K
Following
129K
Media
3K
Statuses
7K
Fooling around with Generative machine learning models since 2019
Joined January 2011
Midjourney rolled their video animation feature into Discord. I liked using the old "chat with Discord's bot" interface.
0
0
6
Very cool, works well on my iPhone's Safari browser
Introducing MirageLSD: The First Live-Stream Diffusion (LSD) AI Model. Input any video stream, from a camera or video chat to a computer screen or game, and transform it into any world you desire, in real-time (<40ms latency). Here’s how it works (w/ demo you can use!):
0
0
2
Famous movie scenes as minimalistic faceless vector images [2/3]
1
0
2
Famous movie scenes as minimalistic faceless vector images [1/3]
1
0
4
The new MidJourney animation feature is really good for making silly Gifs ^_^
1
1
13
RT @bilawalsidhu: Lmao. What niche even is this — grassroots dirt track racing meets google maps nerds?. Veo 3 videos are seriously ridicul….
0
351
0
RT @netanel_tamir: What Makes for a Good Stereoscopic Image? . Stereoscopic images, or stereo images, consist of two slightly horizontally….
0
3
0
Nvidia Parakeet is not only a blazing fast speech transcriber, it can actualy transcribe really fast words out of a song. That's really cool and open-source and you can try it here:
3
1
4
Same input and mask, prompt was in singular rather than plurar. Sharing the script, if anyone wants to play with it: It needs a valid OPENAI_API_KEY in environment , you need to be "Verified" with OpenAI "to access protected models". ~0.25 USD per edit.
0
0
1
I tried the new ChatGPT image inpainting API. To my surprise it did not alter only the masked area nor did it leave the rest untouched. Perhaps it's not meant to be given several masked regions? .Florence-2 was used for "prompt to mask" creation. The API:.
1
1
4