What do you think of this concept? animated mask - The first render (below) had bad edges, by playing with the config of the inpainting module I was able to solve it, this is supposed to be a futuristic liquid metal arm #AnimateDiff@stablediffusion#midjourney#ai#warpfusion
First try at @Magnific_AI, I'm very impressed. You can do magic with Stable Diffusion but both @javilopen and @emailnicolas nailed this down in a user friendly tool that really gives both control and impressive results.
Original image is from Midjourney, no upscale. The other is a 4x upscale with https://t.co/SXoIt368QY. I cropped the lighthouse to see the difference. You can almost look inside through its windows.
Will share more later on.
Midjourney won't be stuck in Discord much longer!!
Starting in a few weeks, you can start testing the new image creation on the web.
Testing will initially start with users who have generated over 10k images, and then roll out from there.
FINALLY!! ๐ฅณ
๐จ Update on @runwayml's Motion Brush (BETA)
1. Precision is wild, more examples below
2. Turns out, early access was exclusive to Creative Partners Program members ๐
I'll keep testing for you until its wide release!!
Testing LCM LORAs in an AnimateDiff & multi-controlnet workflow in ComfyUI. I was able to process this entire Black Pink music video as a single .mp4 input. The LCM lets me render at 6 steps (vs 20+) on my 4090 and uses up only 10.5 GB of VRAM. Here's a breakdown ๐งต[1/11]
Use https://t.co/76wXT0IvWn to help create different prompt combinations for your next image generation prompt.
"tennis player, Above Perspective, Cinematic Style, [Sunset Lighting, Backlighting, Neon Lighting] --ar 16:9 --style raw"
#midjourney#ai#buildinpublic