OPEN SOURCE

–

23 October 2023 23h49

XMem plus ProPainter: Combines XMem video masking with ProPainter video inpainting https://
replicate.com/jd7h/xmem-prop
ainter-inpainting
…

Video Crafter: Open Diffusion Model for High-Quality Video Generation

By

–

23 October 2023 23h49

Crafter: Open diffusion model for high-quality video generation

Latent Consistency Model: Ultra-Fast Stable Diffusion Image Generation

By

–

23 October 2023 23h49

Latent consistency model: make very fast Stable diffusion images with just 4 to 8 steps (~1 second per image) https://
replicate.com/luosiallen/lat
ent-consistency-model
…

SDXL Canny ControlNet Now Supports LoRA Integration

By

–

23 October 2023 23h49

SDXL Canny controlnet with LoRA support: Use your Replicate trained loras with Canny controlnet

→ View original post on X — @ylecun

Regulation Strategy: Product Safety vs Research Freedom

By

@ylecun

–

23 October 2023 23h44

Incidentally:
– I am not anti-regulation.
– regulating the deployment of *product* is useful to guarantee safety. – but I'm very much against regulating research and development.
– and I'm very much against regulations that would make open source AI illegal or difficult.

→ View original post on X — @cerebras

ALiBi Models Performance Extension Without Fine-Tuning

By

@cerebras

–

23 October 2023 19h52

Unlike existing techniques – this method requires no additional fine tuning. By setting a few parameters in your HuggingFace config.json, you can instantly extend the performance of ALiBi models such as BTLM-3B-8K by ~2x: https://
huggingface.co/cerebras/btlm-
3b-8k-base#during-inference-without-fine-tuning
…

→ View original post on X — @cerebras

Position Interpolation Doubles Context Length for ALiBi Models

By

@cerebras

–

23 October 2023 19h48

Paper drop: Position Interpolation Improves ALiBi Extrapolation We found a simple method to 2x the context length of models that use ALiBi. This lets models like BTLM-3B-8K and MPT-7B-8K run high quality inference at up to 16K with no additional fine tuning.