Black Forest Labs Upgrades FLUX 3 Klein to Fix Weak Short-Prompt Results
Black Forest Labs refreshes its FLUX 3 Image Klein workflows, pushing prompt upsampling and 2K rendering as the recommended path to top quality.
20 stories
Black Forest Labs refreshes its FLUX 3 Image Klein workflows, pushing prompt upsampling and 2K rendering as the recommended path to top quality.
A community GGUF port of OpenMOSS's 8B music understanding model lets a C++/GGML desktop app caption your own audio dataset locally.
Google released quantization-aware trained Q4_0 GGUF checkpoints of Gemma 4 E4B, delivering near-bfloat16 quality in a 5.15 GB on-device package.
Nace.AI open-sourced Drex Max v1, a 27B multimodal decision model that returns calibrated probabilities instead of generated text, running locally on Apple Silicon.
A 28M-parameter ConvNeXt variant trained on an 11,821-class ImageNet subset hits 84.2% top-1 while pushing 2,400+ images per second on a single RTX 3090.
A 4-bit MLX conversion of Qwen3.8-27B squeezes a native multimodal dense model into roughly 16 GB, making it practical on Apple Silicon Macs.
AutoTrust AI's open-weights JEV-35B turns a Qwen3.5 MoE into a System 1 decision model that picks among 256 options in 204 ms.
A researcher converted Qwen3.8-27B into a masked diffusion language model that generates tokens in parallel instead of left to right, with open weights and code.
Alibaba's Qwen team shipped an 8-step accelerated version of their 7B open-weight image model, cutting denoising work by 5x while keeping 2K output quality.
Speridlabs released a 3B pixel-space diffusion transformer that skips the VAE entirely, generating 1024px images and doubling as a depth and restoration backbone.
UkisAI released compact 2-bit and 3-bit GGUF quantizations of Swift 1.5 that run a 27B reasoning model in under 10GB while cutting thinking tokens by more than half.
NVIDIA's new open 120B vision-language MoE activates just 12B parameters per token, handles 1M context, and runs on a single DGX Spark at NVFP4.
A full set of imatrix GGUF quantizations lets you run Qwen2.5-32B-Instruct locally, from a 9GB phone-friendly build up to lossless 65GB weights.
ChatR Labs released a rank-128 LoRA that handles both text-to-image and reference-based image editing on Qwen-Image-2.1 using one adapter.
A 0.3B EmbeddingGemma 2 fine-tune turns workflow states into typed, calibrated answers to yes/no, multiple-choice and ranked-level questions.
A refusal-removed build of Qwen3.8-Flash-Next transplants 144 tensors into an already-quantized GGUF without recomputing a single learned value.
A 7.6M-parameter Turkish text-to-speech model runs 50x faster than real time on a laptop CPU, with the fewest character errors among 15 Turkish systems benchmarked.
A community-maintained repackaging of Alibaba's Wan 2.1 video model lets 6GB consumer GPUs generate 480p clips through the WanGP toolbox.
AutoTrust AI Lab released GEV-26B-Decide, a Gemma-4 based decision model that outputs calibrated probabilities and thinks only when uncertain.
The compact RepVGG-A0 checkpoint is live on the Hugging Face Hub via timm, offering a 9M-parameter plain-conv backbone trained on ImageNet-1k.