Tag
Introducing Logocreator, an open-source AI logo generator developed by Nutlope, powered by Together AI's FLUX model. It generates high-quality logos in seconds, has 7.6k+ stars on GitHub, and supports custom API keys and localized fine-tuning.
A practical roundup of uncensored AI image generators, recommending FLUX run locally via ComfyUI for serious users, and Krea 2 Turbo plus Wan spicy images via Atlas Cloud for hosted speed and prompt-following.
FLUX 3 proposes multimodal flow models as a foundational approach for real-world visual intelligence, building on prior FLUX work.
ReChannel adapts pretrained diffusion transformers (e.g., FLUX-Klein) for dense prediction tasks by mapping tokens directly to pixel-space patches, achieving state-of-the-art results on trimap-free matting, KITTI depth, and referring segmentation with minimal additional parameters.
Modular's MAX inference serving achieves 3x faster image generation for FLUX.2-dev than competitors, as per Artificial Analysis benchmarks.
A LoRA model for Flux 2 Klein 9B that enables controlling sun direction in exterior images by using a reference ball image and an overcast intermediate step. Includes a custom ComfyUI node for rendering sphere light references.
A simplified open-source PyTorch implementation of FLUX diffusion transformers with verifiable line-by-line source mappings, designed for educational purposes.
Comfy-Org has repackaged Boogu-Image model files for ComfyUI, including base, edit, and turbo variants with different quantization formats, plus a LoRA and text encoder.
An open-source local AI dungeon app using Gemma 4 and FLUX for text and image generation, fully private and runs under 8GB RAM.
Martin Scorsese joins Black Forest Labs as an advisor and uses FLUX for storyboarding, showcasing AI's role in visual creativity.
Built an open-source pipeline that takes a single sentence and produces a cinematic reel with characters, animation, music, and narration, using FLUX.2, Wan2.2, and other models on a single AMD GPU. The pipeline includes a director agent, character generation, keyframe animation, vision critic, music, and narration stages.
Black Forest Labs shared the evolution of the Flux series models at the AI Engineer Conference and released the SelfFlow research paper, proposing a self-supervised multimodal training method that does not require external encoders.
Hugging Face introduces Modular Diffusers, a new framework for building diffusion pipelines using composable, reusable building blocks instead of monolithic pipeline implementations. The system allows flexible mixing and matching of components for image generation workflows, with integration support for visual workflow tools like Mellon.
PrunaAI presents Flux Fast, an optimized endpoint for Black Forest Labs' FLUX.1-dev model, claiming the fastest Flux inference via compression, caching, and compilation.