7Latent Space (swyx)·
Black Forest Labs releases FLUX 3 multimodal flow model, reportedly outperforming Seedance 2.0, Gemini Omni, and Grok Imagine
Black Forest Labs has released FLUX 3, a multimodal flow model that reportedly beats competing image/video generation systems including Seedance 2.0, Gemini Omni, and Grok Imagine on key benchmarks. The release also includes a FLUX-mimic video-action robotics model, extending the FLUX family into embodied AI applications. This represents a significant capability advance for BFL in the competitive generative media space.
Related guides (3)
Related events (8)
Diffusers welcomes FLUX-2
Hugging Face's Diffusers library has added support for FLUX-2, the successor to Black Forest Labs' FLUX image generation model. The blog post announces integration of the new model into the Diffusers ecosystem, enabling developers to use FLUX-2 through the standard Diffusers API. This represents a tooling and ecosystem update for one of the leading open-weights image generation model families.
FLUX3D: Diffusion-aligned sparse representation for high-fidelity image-to-3D Gaussian Splatting
Researchers introduce FLUX3D, an image-to-3D Gaussian Splatting framework that addresses two structural bottlenecks in sparse voxel-based 3D generation: a representation bottleneck from discriminative 2D features and a cross-modal correspondence bottleneck in diffusion transformers. The system introduces Diffusion-Aligned Structured Latents (DA-SLAT) and a Sparse-structure Multimodal Diffusion Transformer (SMDiT) with Modal-Aware Rotary Positional Embedding (MARoPE) to improve 2D-3D alignment. Benchmark results claim substantial improvements in appearance fidelity over all current state-of-the-art methods for 3DGS asset generation.
Google DeepMind Introduces Veo 3, Imagen 4, and Flow Filmmaking Tool
Google DeepMind has announced Veo 3 and Imagen 4, new generative video and image models respectively, alongside a filmmaking tool called Flow. The announcement comes from DeepMind's official blog and represents the next generation of their generative media capabilities. These releases expand Google's multimodal generative AI portfolio targeting creative and professional media production use cases.
Fast LoRA inference for Flux with Diffusers and PEFT
Hugging Face published a technical blog post detailing optimizations for LoRA inference speed with the Flux image generation model using the Diffusers and PEFT libraries. The post covers techniques to accelerate adapter loading and inference throughput for diffusion models. This is relevant to practitioners deploying fine-tuned image generation models in production or research settings.
Expanding Flow Maps (EFMs): flow-based generative models with variable output dimensionality
A new arXiv preprint introduces Expanding Generative Flows (EFlows) and Expanding Flow Maps (EFMs), a framework that extends flow-based generative models to handle variable output dimensions and sequence lengths. The approach defines flows between distributions of increasing dimensionality via an expanding interpolant, factoring the generative map into an expand operator and a transport map. The framework covers both continuous and discrete modalities, enabling variable-size graph and variable-length sequence generation, and subsumes existing fixed-canvas flows as a special case.
GLM-5.2 passes community vibe checks; Z.ai forecasts Open Fable by December
GLM-5.2, a new open model, is reportedly passing community vibe checks and drawing comparisons to GPT-class frontier models. Z.ai has forecast the release of Open Fable by December. The item signals a potential shift in the open-weights landscape toward genuine frontier-level capability.
(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware
This Hugging Face blog post covers techniques for fine-tuning the FLUX.1-dev image generation model using LoRA (Low-Rank Adaptation) on consumer-grade hardware. The post likely addresses quantization strategies (QLoRA) to reduce memory requirements, enabling training on GPUs with limited VRAM. This is relevant to the open-weights and accessible fine-tuning ecosystem for diffusion models.
DeerFlow 2.0 launches as open-source agent harness; Anthropic sues Pentagon over AI blacklist; Google releases Gemini Embedding 2
ByteDance released DeerFlow 2.0, an open-source agent harness built on LangGraph/LangChain that orchestrates parallel sub-agents with sandboxed Docker environments, progressive skill-loading, and persistent memory for complex workflows. Anthropic filed two lawsuits against the U.S. Pentagon contesting a supply-chain risk blacklist tied to its refusal to remove guardrails preventing Claude's use in autonomous weapons and domestic surveillance, with potential multi-billion dollar revenue impact. Google released Gemini Embedding 2, a multimodal embedding model unifying text, images, video, audio, and PDFs in a single vector space, succeeding the text-only predecessor. Meta acquired Moltbook, an agent-to-agent social platform built around the OpenClaw framework, while OpenAI hired OpenClaw's creator and acquired AI security testing platform Promptfoo.