Jump to content

richardmurray

Boycott Amazon
  • Posts

    2,413
  • Joined

  • Last visited

  • Days Won

    91

Everything posted by richardmurray

  1. I concur @Troy but I want to say, like many industries the problem is the usa itself. The usa doesn't have a history of managing inudstries well. They let industries fly as long as they make money and can pay for government protection. Googe is part of the digital six. I argue the only answer is alternative networks outside the usa that will free populaces outside the usa. China shows the way as at least china has its own ecosystem.
  2. topic Thirty-sixth of the Cento poetry series If You Made It This Far : AI films, Empire State building photos through time, Robert Forte alps photos, TheWiz multiverse URL https://rmnewsletter.over-blog.com/2023/09/01/28/2024-rmnewsletter.html The largest non food industry black owned business in harlem is Amsterdam news the most well known black designed building in harlem for me is the Renaissance Ballroom, destroyed now, but financed and designed by black people, a black architecture firm and black money.
  3. https://www.tumblr.com/blackexcellence/740595272723333120 lovely
  4. Google has a new software called Lumiere that does text to video, what are your thoughts? you can read more about it here https://aalbc.com/tc/profile/6477-richardmurray/?status=2582&type=status
  5. Google's New AI Text-to-Video Tool Is Fun to Look At. But What Next?

    Story by Lisa Lacy • 38m

     

    Google has teased an AI-based video generation tool, but it's not clear when — or if — anyone outside the search giant will be able to kick the tires. It's certainly fun to look at, though.

    On Wednesday, Google's Research arm released a video highlighting this new text-to-video model, which is called Lumiere.

     

    In a LinkedIn post, team leader Inbar Mosseri said the tool "generates coherent, high-quality videos using simple text prompts" that New Atlas says run up to five seconds. Sample inputs include, "A fluffy baby sloth with an orange knitted hat trying to figure out a laptop" and "An escaped panda eating popcorn in the park."

    In the year or so that generative AI has been the hottest technology going, much of the attention has been focused on tools like ChatGPT that produce text answers to prompts, or those like Dall-E that create still images. Video creation from text prompts is arguably the next frontier, so if Lumiere really can "demonstrate state-of-the-art text-to-video generation results" as Google says, we may already be evolving beyond the "grotesque abominations" of the AI-generated images of 2023.

    As the video illustrates, Lumiere's capabilities include text-to-video and image-to-video generation, as well as stylized generation — that is, using an image to create videos in a similar style. Other tricks include the ability to fill in any missing visuals within a video clip.

    That includes the ability to animate famous paintings, like Van Gogh's Starry Night ("A timelapse oil painting of a starry night with clouds moving") or Da Vinci's Mona Lisa ("A woman looking tired and yawning"). While the Starry Night example works almost flawlessly, Mona Lisa looks far more like she's laughing than yawning.

    And while many of the animals — such as "a muskox grazing on beautiful wildflowers" and "a happy elephant wearing a birthday hat walking under the sea" — look realistic, there's something off about some of the dogs. Both a toy poodle riding a skateboard and a golden retriever puppy running in the park are close to passing as real, but their faces — and perhaps their eyes specifically—betray the fact that they're CGI.

    Nevertheless, the video editing tools hold a lot of promise. Using a source video and prompts like "made of colorful toy bricks" or "made of flowers," users can purportedly change the style of the subject completely. And with inputs like "wearing a bathrobe," "wearing a party hat" and "wearing rain boots" to add said items to an image of, say, a baby chick, Lumiere may very well make fiddling with videos more accessible to those of us who didn't major in graphic design.

    Though the assets shared so far certainly make Lumiere seem like it's user-friendly, the description of how it works isn't. (Google didn't respond to a request for additional comment.)

    A project page < https://lumiere-video.github.io/  > describes Lumiere as "a space-time diffusion model," which sounds like something Doc Brown was working on in Back to the Future. Google Research said this means the text-to-image model learns to generate a video by processing it in multiple space-time scales, which helps create videos that "portray realistic, diverse and coherent motion."

    According to Google, this is superior to existing models, which "synthesize distant keyframes followed by temporal super-resolution." 

    Jason Alan Snyder, global chief technology officer at ad agency Momentum Worldwide, explained it this way: "It's like the difference between watching a puppet show and experiencing a ballet at Lincoln Center."

    That's because Lumiere "doesn't just focus on snapshots, it crafts smooth, flowing motion for every frame," he added.

    In other words, if you think about the traditional method of making a movie, you'd have to build key scenes and fill in the gaps later.

    "Lumiere is different. It sees the whole movie in its mind, understanding how characters move, objects interact and everything changes over time," Snyder said. "It's like drawing the entire flip book simultaneously, ensuring every page flows perfectly."

    So this "space-time thinking" helps Lumiere create videos that feel real, which, he added, means no more jumpy transitions or robotic movements. (Except maybe for puppy eyes.)

    Time will tell.

    In the meantime, as fans of Beauty and Beast will know, Lumiere is French for "light."  

    Editors' note: CNET is using an AI engine to help create some stories. For more, see this post. < https://www.cnet.com/ai-policy/#ftag=MSF491fea7 >

     

    URL

    https://www.msn.com/en-us/news/technology/googles-new-ai-text-to-video-tool-is-fun-to-look-at-but-what-next/ar-BB1hgBUi

  6. good I used edelweiss for other reviews and for reviews I am working on so if you still need when the time comes this will be simple:)
  7. @Troy change the link to the following https://ourtimepress.com/viola-plummer-last-of-original-december-12th-movement-transitions/
  8. @Pioneer1 a black man who when a teenager was accused of murdering the man who stole from his sister, is now out of prison. https://aalbc.com/tc/profile/6477-richardmurray/?status=2579&type=status
  9. 133art Commissions are Open ya'll! Pin-ups, Covers, and illustration. Commission details: $400.00USD for each full-color, 1-2 character(s), limited background commission piece. Half payment upfront, half payment upon completion. Paypal is the payment method of choice (but if that's not an option we can work it out). If additional characters are needed in the same piece the additional charge for each extra character is $50.00USD. (So in the case of a 3 character piece the charge will be $450.00USD and so on). Procedure: 1st draft pencils will be sent to purchaser for approval, with the option of (1) round of reasonable revisions At the pencil stage of the illustration. Once the final pencils are approved the illustration is sent off for coloring. 1st draft colors will be sent to purchaser for approval, with the option of (1) round of reasonable revisions At the color stage of the illustration. When the final piece is approved/completed the purchaser will receive a 300dpi jpeg. (or tiff.) digital file via Dropbox download. (Note: Both artist(s) must be credited for their work within the publication(s) to the best of the client's ability. Credits as follows: Jason Reeves/133art (Note on further revisions: if after the first round of reasonable revisions, in either stage, further revisions are needed, there will be an added charge a 25% of commission rate fee per round.) What we'll need to get started: The half payment(s), all character descriptions, and reference photos of the characters that apply. If all that is cool, clients can send emails to: 133artpublishing@gmail.com with the relevant materials. Paypal address is: 133artpublishing@gmail.com Thanks for the support! See more examples of our work at the 133art Gallery here: 133art.com/gallery/
  10. @ProfD Fair enough, i just want to say for the record i have been supporting/advocating a black party of governance in the usa for years to be made from black folk like you and pioneer who are determined americans
  11. @ProfD you forgot to add the rest of my quote Reparations doesn't fit the party of abraham lincoln position. They feel the black ADOS population isn't on equal footing or empowered in the usa, while the black ados position doesn't need reparations to achieve said equal footing or empowerment. The arty of abraham lincoln believes the usa system is adequate for all individuals in it, from native americans to the wealthiest whites. Second you can't find a consensus among a majority in the black ADOS populace in the usa to define reparations so legislation can't be introduced for something the people it is to be delivered to don't have a consensus on. Plus, you can't find a consensus among a majority in the black populace on what exactly needs to be dismantled in the bureaucracy of the usa. So to that end, ProfD if you live in a black town or live in a black district in a city, why don't you ask Black ados people in the street to explicitly define what reparations legislation will look like, for example 2 million dollars for each black person in the usa, and then also ask what needs to be dismantled in the usa government to lessen or end white supremacy, for example , delete all bequeathed positions in government like deputy mayor. In my mind profd the problem isn't that you don't know what you will like reparations or dismantling the tools of white power in government to look like but you are unwilling or able to get consensus among black people. The black elected officials don't seem interested. But you have the ability to communicate in your local community , so do it yourself and then present to your ocal officials: city council representative or house of representatives member or mayor.
×
×
  • Create New...