![]() ![]() But the cherry-picked samples from the model do look rather impressive, at least compared to the other text-to-video technologies we’ve seen.įor starters, Sora can generate videos in a range of styles (e.g., photorealistic, animated, black and white) up to a minute long - far longer than most text-to-video models. Now, there’s a lot of bombast in OpenAI’s demo page for Sora - the above statement being an example. “ The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world.” “Sora has a deep understanding of language, enabling it to accurately interpret prompts and generate compelling characters that express vibrant emotions,” OpenAI writes in a blog post. Sora can also “extend” existing video clips - doing its best to fill in the missing details. Given a brief - or detailed - description or a still image, Sora can generate 1080p movie-like scenes with multiple characters, different types of motion and background details, OpenAI claims. OpenAI today unveiled Sora, a generative AI model that creates video from text. Now, repeat that part, the only difference is that you won't be using the mask '01.png', but '02.png', and you will save the resulting flag as '02.gif', do that until that folder looks like that (you must have '20.OpenAI, following in the footsteps of startups like Runway and tech giants like Google and Meta, is getting into video generation. like that) and save this image as '01.GIF'. Make a new folder in the folder of your masks (named 'Flags' or sth. Without changing the selection, go to the other layer (of the shadows, actually) and hit 'Del'-ete. Next, select the 'Magic Wand'-tool, set the Tolerance to '50' or less and go to the layer of the distorted flag.Ĭlick somewhere on the transparent area around the flag. ![]() Go to this newly imported :Properties: layer's properties (F4), set the Blending mode to 'Multiply' and the opacity to '128'. That file should be the mask you applied to the FlagTemplate, here '01.png'. :ImportLayers: Import another layer from a file. Run the 'Alpha-Displacement'-effect as following:Ĭheck the checkbox for 'Displacement on'. I'll only explain it once, so read very carefully: Save that image as 'FlagTemplate.png' or something like that, main thing is you can find and open it and that you know what it is. Set the transparency alpha of your secondary color to '0' and :ExpandCanvas: expand the canvas of your image to the mask's dimensions (here (once again): 600x400). Next, :Resize: resize the image to 90% of its size. If you're having trouble doing this, make sure 'Maintain aspect ratio' is unchecked. :Resize: Resize it to your mask's dimensions (here: 600x400). Now, download or save or whatever but simply open a flag with Paint.NET. Making the actual flag (though based on the displacement masks): repeat this until you have saved the image '20.png'. Save this image as '02.png' in the same folder. Then, go to Rotate/Zoom, click 'Reset All', make sure 'Tiling' is still checked, and set 'X Pan' to '0.100'. Go to Adjustments - Brightness/Contrast, set Brightness to '0' and Contrast to '40'.Ĭreate somewhere on your computer a new folder. Now, go to :ExpandCanvas: Canvas Size, halve the width (here: 600), and set the Anchor to 'Middle'. Press Enter and apply :GaussianBlur: 'Gaussian Blur' at Radius '40'. + Shift + Z), click 'Reset All', check 'Tiling', and set 'X Pan' to '0.500'. Next, we go to Layers - Rotate/Zoom (Ctrl. + Shift + R), uncheck 'Maintain aspect ratio', double the width (here: 1200), and set the Anchor to 'Right'. Then we go to Image - :ExpandCanvas: Canvas Size (Ctrl. Now comes the tricky part: we want it to be panoramic: Then, in order to make the pattern appear random, we render clouds, all default values. So we make a new 600pix wide times 400pix high image. First of all, you need to decide, how big you want the flag to be. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |