# LocalAI v2.20.1 — Release & Upgrade Intelligence
- **Product:** LocalAI (https://localai.io)
- **Version:** v2.20.1
- **Released:** Aug 23, 2024
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/localai/updates/v2.20.1/

## Executive Summary (TL;DR)
LocalAI v2.20.1. Source highlight: It's that time again—I’m excited (and honestly, a bit proud) to announce the release of **LocalAI v2.20**! This one’s a biggie, with some of the most requested features and enhancements, all designed to make your self-hosted AI journey even smoother and more powerful.

## Breaking Changes & Deprecations
- Breaking Changes 🛠 * chore: drop gpt4all.cpp by @mudler in https://github.com/mudler/LocalAI/pull/3106 * chore: drop petals by @mudler in https://github.com/mudler/LocalAI/pull/3316

## New Features
- 🎨 **New Feature:** FLUX-1 image generation support
- **Load Balancing by Default:** This feature is now enabled by default (disable it with `LOCALAI_RANDOM_WORKER` if needed).
- feat(guesser): add gemma2
- feat(venv): shared env
- feat(openai): add `json_schema` format type and strict mode
- feat(p2p): allow to run multiple clusters in the same p2p network

## Improvements
- **Target Specific Workers:** Directly target workers in federated mode using `LOCALAI_TARGET_WORKER`.

## Bug Fixes
- 🐛 **Bug Fixes:** Diffusers and hipblas issues resolved
- fix(ui): do not show duplicate entries if not installed by gallery
- fix: be consistent in downloading files, check for scanner errors
- fix: ensure correct version of torch is always installed based on BUI…
- fix(python): move accelerate and GPU-specific libs to build-type
- fix(apple): disable BUILD_TYPE metal on fallback