3/ Matryoshka Diffusion Models – introduces an end-to-end framework for high-resolution image and video synthesis; involves a diffusion process that denoises inputs at multiple resolutions jointly and uses a NestedUNet architecture…
CREATIVE AI
-
Spooky Black Light SDXL Fine-Tune Model Released
By
–
Spooky black light SDXL fine tune anyone? https://
replicate.com/fofr/sdxl-blac
k-light
… -
Pika Labs Contest Prizes: Cash, NFT Access, and Social Promotion
By
–
Prizes: 1. 1000 Dollars cash prize for 1st place. 2. Surprise prizes for the 2nd, 3rd, and the most liked post on social media. (TBD)
3. 1-month access to non-watermark generations
4. Promotion of your work and social media accounts across all Pika official platforms. -
Pika Video Generation Challenge: Create Animated Content
By
–
Requirements: Participants must generate/animate videos solely with Pika, but feel free to choose your preferred ways to use other content including music, sound effects, images, etc.
-
Pika’s Halloween Film Contest: Win $1,000 with AI Video
By
–
🎃 Pika's Halloween Film Contest 🎃
— Pika (@pika_labs) 28 octobre 2023
Submit your videos by Oct 31st for a chance to win $1,000 in cash and other special prizes
Judges: @juliewdesign_ @CuriousRefuge @MatanCohenGrumi
Credit: @MatanCohenGrumi
More Details ⬇️ pic.twitter.com/414o30Ue5VPika's Halloween Film Contest Submit your videos by Oct 31st for a chance to win $1,000 in cash and other special prizes Judges: @juliewdesign_ @CuriousRefuge @MatanCohenGrumi Credit: @MatanCohenGrumi More Details
-
VALL-E Voice Cloning and Drag Your GAN Image Editing Advances
By
–
The new audio system VALL-E can duplicate a voice using a 3-second recording, expanding AI voice imitation limits. Meanwhile, Drag Your Gan applies StyleGAN2 tech for interactive and precise image editing.
-
Latent Consistency Models for Fast Video-to-Video Conversion
By
–
Using a latent consistency model for video2video is fast, but it needs control mechanisms.
— fofr (@fofrAI) 28 octobre 2023
The speed means you can do high frame rate video conversions. But the lack of control makes it a mess.
180 frames in 55 seconds:https://t.co/Y13KKTdAtp pic.twitter.com/CMaWM62C9AUsing a latent consistency model for video2video is fast, but it needs control mechanisms. The speed means you can do high frame rate video conversions. But the lack of control makes it a mess. 180 frames in 55 seconds: https://
replicate.com/p/qavcahlbjto6
6zcoq3eyubaclu
… -
Dream Gaussian and AnimateDiff: 3D Logo Video Generation
By
–
An early experiment with:
— fofr (@fofrAI) 27 octobre 2023
– Replicate logo image to 3d video with Dream Gaussian
– Video used as QR controlnet for animatediff
– Frame interpolated using ST-MFNet pic.twitter.com/2b5fdPVLmsAn early experiment with: – Replicate logo image to 3d video with Dream Gaussian
– used as QR controlnet for animatediff
– Frame interpolated using ST-MFNet
