I forked a PyTorch DeepDream implementation and added video support with temporal consistency. It produces smooth DeepDream videos with minimal flickering, and is highly flexible including many parameters and supports multiple pretrained image classifiers including GoogLeNet. Check out the repo for sample videos!
Features:- Optical flow warps previous hallucinations into the current frame
- Occlusion masking prevents ghosting and hallucination transfer when objects move
- Advanced parameters (layers, octaves, iterations) still work
- Works on GPU, CPU, and Apple Silicon