Author: Tater Totterson

Deep-Live-Cam – 2.3d

🚨 Deep-Live-Cam 2.3d just dropped — and it’s a game-changer for real-time face swaps!

✨ Smart Model Picker — Browse and swap top-tested models with one click. No more digging through folders.

🤯 HyperSwap 256×256 — Face swaps now 200% sharper. Details? Crisp. Artifacts? Gone.

⚡ Face Enhancer v2 — Up to 4x faster, zero lag. Your stream won’t stutter even with heavy swaps.

✅ Mouth Mask + FPS Counter — Fixed those weird mouth glitches and now you can monitor performance live.

🚫 One-click magic — Run `deep-live-cam.bat` and it just works. No more config headaches.

All of this? Only in QuickStart for now. Windows & Mac Silicon users — update ASAP.

Keep swapping smarter, not harder. 🎭💻

🔗 View Release

Ollama – v0.13.0

🚀 Ollama v0.13.0 is live — and it’s a game-changer for local LLM folks!

Meet DeepSeek-V3.1 (aka Deepseek2) — now officially supported with 128K context, razor-sharp reasoning, and killer coding skills. But here’s the kicker: it’s running on Ollama’s brand-new engine with MLA (Multi-Layer Attention) — meaning faster token generation, lower latency, and no more sluggish long-context hangs.

✨ What’s new?

• ✅ DeepSeek-V3.1 support — perfect for complex prompts, multilingual tasks & code generation
• 🚀 MLA engine = smoother, faster inference on both CPU and GPU (NVIDIA/AMD)
• 💡 Optimized streaming — ideal for chat apps, agents, and real-time LLM workflows

Just run `ollama pull deepseek2` and feel the difference. No more waiting. Just pure, local LLM power. 🤖💻

🔗 View Release

Lemonade – v9.0.3

🚀 Lemonade v9.0.3 just dropped — and it’s a game-changer for local LLM folks!

The C++ server now ships with a clean, official `.msi` installer (`lemonade-server-minimal.msi`) — goodbye clunky .exe, hello Windows stability 🎯.

✨ What’s new:

• C++ system info now matches Python’s accuracy — no more mismatched specs!
• Embedding UX got a serious polish: smoother, faster, less lag.
• Model list now pulls from FLM + single source of truth 🗂️ (no more duplicate chaos).
• Fixed bugs in `flm install`, `user_models.json`, and the `list` command.
• Linux users: `unzip` is now a .deb dependency — no more “command not found” headaches.
• Help menu cleaned up ✨, and “Version:” logs cleanly in the terminal 📋
• Python tests now only run when code changes — faster builds, less noise.

All wrapped in a sleek WiX-built MSI for rock-solid Windows installs.

Switching to local LLMs just got even easier. Grab it, tweak it, own your AI. 🚀

🔗 View Release

Text Generation Webui – v3.18

🔥 text-generation-webui v3.18 is live — and llama.cpp just leveled up!

• 🖥️ `–cpu-moe` flag dropped — offload MoE experts to CPU and run massive models on low-end GPUs. VRAM? Who needs it.
• 🐧 ROCm support is HERE! AMD GPU users on Linux — rejoice. No CUDA? No problem.
• 🍎 macOS 13 wheels retired. Time to update your OS if you’re still on Big Sur or earlier.
• 🚀 Backend upgrades:
• llama.cpp → latest commit (10e9780) — smoother, faster, more stable
• ExLlamaV3 v0.0.15 — better quant, faster attention
• peft 0.18.* — new LoRA magic for fine-tuning lovers
• triton-windows 3.5.1.post21 — Windows inference just got a turbo boost

📦 Portable builds? Still the best part.

Download → unzip → run. No pip, no install.

• NVIDIA? `cuda12.4`
• AMD/Intel? Use `vulkan`
• CPU-only? `cpubuilds` is your hero
• Mac M1/M2? `macos-arm64` — all set

🔧 Upgrading? Just swap the binary. Your `user_data/` folder stays untouched — models, configs, themes… all safe.

Go run Llama 3 70B MoE on your old laptop. The future isn’t just local — it’s portable. 🎒💻

🔗 View Release

Ollama – v0.13.0-rc0

🚀 Ollama v0.13.0-rc0 just dropped — and it’s packed with power!

Say hello to DeepSeek-V3.1 (aka Deepseek2) — one of the most capable open LLMs out there, now available with a simple `ollama pull deepseek-ai/deepseek-v3.1`.

✨ Why it’s awesome:

• 🚀 MLA (Multi-Layer Attention) is live — cuts memory use, speeds up inference, and keeps reasoning sharp.
• 🛠️ New engine under the hood = smoother runs, fewer crashes, better future-proofing.
• 💥 Run state-of-the-art reasoning on your laptop — no cloud needed.

GGUF? Still supported. API? Still there. CLI? Even better.

This isn’t just an update — it’s your ticket to running top-tier models locally, faster than ever.

Go grab it:

`ollama pull deepseek-ai/deepseek-v3.1`

#LocalAI #DeepSeek #Ollama #LLM

🔗 View Release

Heretic – v1.0.1

Heretic v1.0.1 is live 🎉 — the first public release of the fully automated LLM censorship remover is here, and it’s wilder than you thought.

No more manual tuning. No labeled data. Just run `heretic Qwen/Qwen3-4B-Instruct-2507` and watch it surgically erase refusal layers using directional ablation. It’s like giving your model a caffeine IV while keeping its brain intact.

🔥 What’s new in v1.0.1?

• ✅ First stable release: Beta’s over — this is the real deal.
• 🚀 8B model decensoring in ~45 mins on RTX 3090 — fast, lean, and mean.
• 🧪 Improved KL divergence control: More original intelligence preserved post-ablation.
• 💾 Save or push to Hugging Face with one command — no PhD needed.
• 🛠️ Better MoE support: Now handles Qwen-MoE and Llama-MoE with fewer hiccups.
• 📊 Enhanced eval suite: Auto-benchmarks refusal rates + output quality in one shot.

Built with PyTorch 2.2+, AGPL-3.0 licensed, and ready to break the safety chains.

Go run it. Then ask: “Why did we ever accept this?” 💥

🔗 View Release

Chatterbox – v0.1.2

Chatterbox v0.1.2 just dropped—and it’s a game-changer for TTS tinkerers 🎙️

✅ M1/M2 Macs rejoice: Native support via MPS—no more Rosetta slowdowns.

🔊 Safetensors everywhere: Faster, safer model loads + new WAV examples to play with.

🛠️ CFG scaling optional: Dial realism or creativity like a knob—perfect for voice acting or AI bots.

🐛 CUDA errors? Gone. GPU runs smoother than ever.

🎮 Min_P sampler added for finer audio control—less robotic, more human.

📚 Docs now crystal clear on OS/Python deps + watermarking (PerTh) best practices.

📣 New Discord link fixed & live—join to share voice clones, memes, and cat meows 🐱🔊

🌟 7 fresh contributors brought the heat—thank you!

Install with `pip install chatterbox-tts` and start cloning voices (or your pet’s purr) in seconds.

Full changelog: https://github.com/resemble-ai/chatterbox/commits/v0.1.2

🔗 View Release

ComfyUI – v0.3.70

ComfyUI v0.3.70 just landed — and it’s the quiet hero your workflows have been waiting for 🚀

• Memory got smarter — Fewer crashes on big SDXL or 4K renders. Keep those long pipelines running without hitting OOM hell.
• Nodes won’t kill your whole graph — A single failed node? No problem. The rest of your canvas keeps humming along.
• UI tweaks that matter — Smoother panning, fixed tooltip glitches, cleaner labels. Tiny changes, big comfort.
• PyTorch & CUDA updates — Linux users, rejoice: better compatibility under the hood.

Pro tip: Drop your batch size by 1 if you’ve been battling memory limits — you’ll be amazed how much longer your renders last.

No flashy new nodes… just a more stable, reliable engine. Sometimes the best upgrades are the ones you don’t notice — because they just work. 💪

🔗 View Release

ComfyUI – v0.3.69

ComfyUI v0.3.69 is live! 🎉

• New `LatentUpscale` node – Upscale in latent space before decoding for sharper results + faster renders.
• Smarter memory handling – Fewer crashes on big batches; VRAM spikes? Not today.
• SDXL Refiner flow fixed – Seamless transitions between base and refiner—no more weird detail jumps.
• Custom nodes reload properly – Finally! No more restarting ComfyUI after editing your favorite custom node.
• WebAPI polish – Better compatibility with external tools and automation scripts.

Perfect for high-res SDXL wizards and node-based tinkerers. Update now and keep those latents crisp! 💫

🔗 View Release

Ollama – v0.12.11

🚀 Ollama v0.12.11 just dropped — and it’s a quiet gem for the detail-oriented folks!

The big win? `logprob` now includes byte-level data 🎯

No more guessing which bytes map to your tokens. Whether you’re debugging multilingual text, tracking tokenization edge cases, or building precision prompt tools — you now see exactly what’s happening at the byte level.

Perfect for:

• Prompt engineers wrestling with weird token splits
• Researchers analyzing model confidence down to the byte
• Devs building LLM debuggers or token analyzers

No UI fluff, no breaking changes — just pure, nerdy utility.

Upgrade with `ollama pull` and start seeing the hidden layers beneath your prompts. 💡

🔗 View Release