Available now on local and 1-2 hours on cloud 🫡
ComfyUI announced the availability of a feature or service that can be accessed locally immediately and on cloud infrastructure with a 1-2 hour latency or deployment time. This post likely refers to a
Knowledge catalogue
ComfyUI announced the availability of a feature or service that can be accessed locally immediately and on cloud infrastructure with a 1-2 hour latency or deployment time. This post likely refers to a
B9050 is a release build of llama.cpp, an open-source C/C++ project that enables LLM inference with minimal setup and high performance on diverse hardware platforms. The project provides LLM inference
B9055 is the latest version of llama.cpp, released on May 7, 2026. Llama.cpp is an LLM inference framework implemented in C/C++ that enables efficient large language model execution with broad hardwar
b9056 is a release of llama.cpp, a C/C++ implementation for LLM inference . The project enables users to run LLaMA models on consumer hardware without expensive GPUs or cloud infrastructure . This rel
I was unable to find specific details about the b9058 release. Based on the context, b9058 is a build version from the llama.cpp project, which is an open source software library that performs inferen
b9060 is a release build identifier for llama.cpp, an open-source LLM inference framework implemented in C/C++. This build represents a snapshot in the project's ongoing development, containing bug fi
Release b9061 is a build version of llama.cpp, a C/C++ implementation designed to enable LLM inference with minimal setup and state-of-the-art performance across various hardware platforms . As a spec
Release b9063 is a build of llama.cpp, a project for LLM inference in C/C++. llama.cpp enables efficient large language model execution on consumer hardware through optimized implementations and quant
llama.cpp b9066 is a release of a C/C++ implementation for large language model (LLM) inference . Based on the release repository structure, b9066 represents a specific build or commit version of the
CleanFreak is a ComfyUI organization tool that automatically arranges nodes into categorized columns by function (loaders, encoders, samplers, decoders) with a single click, supporting over 1200 pre-c
ComfyUI-Lora-FindingLora is a specialized loader extension for the ComfyUI image generation framework that streamlines LoRA (Low-Rank Adaptation) model management through fuzzy search functionality, e
arXiv:2605.04830v1 Announce Type: new Abstract: Diffusion models undergo a phase transition in a critical time window during generation dynamics, with two complementary diagnoses of criticality. The s
arXiv:2605.03900v1 Announce Type: new Abstract: Frontier AI systems perform best in settings with clear, stable, and verifiable objectives, such as code generation, mathematical reasoning, games, and
arXiv:2605.04413v1 Announce Type: new Abstract: Structural causal models provide a unified semantics for interventions and counterfactuals, but most identifiability results rely on restrictive assumpt
arXiv:2605.04346v1 Announce Type: cross Abstract: The Forward-Forward algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-fr
arXiv:2605.04593v1 Announce Type: new Abstract: Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictio
arXiv:2605.04722v1 Announce Type: new Abstract: Input Convex Neural Networks (ICNNs) are commonly used in a two-stage manner: one first trains a convex network and then minimizes it over its input in
arXiv:2506.20911v2 Announce Type: replace Abstract: We develop a cost-efficient neurosymbolic agent to address challenging multi-turn image editing tasks such as ``Detect the bench in the image while
A ComfyUI workflow that uses Flux 2 Klein for the first upscale pass where detail is introduced carefully, then uses SeedVR2 to push the final resolution higher via tiling. The workflow maintains the
arXiv:2605.03986v1 Announce Type: new Abstract: Multi-Agent Systems (MAS) built using AI agents fulfill a variety of user intents that may be used to design and build a family of related applications.
Generate 10 images in under 10 seconds. Introducing Grok @imagine Image Quality. A new image model in the Grok Imagine family that generates impressive realism, text rendering and prompt adherence at
arXiv:2605.05164v1 Announce Type: new Abstract: Accurate analysis of histopathological images is critical for disease diagnosis and treatment planning. Whole-slide images (WSIs), which digitize tissue
arXiv:2605.04282v1 Announce Type: new Abstract: Visual SLAM is a core component of spatial computing systems, yet deploying learned local feature extractors on microcontroller-class hardware remains c
arXiv:2605.04103v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and effi
arXiv:2605.04682v1 Announce Type: cross Abstract: Spatial transcriptomics offers spatially resolved gene expression profiling within tissue sections, but its cost and limited throughput hinder large-s
arXiv:2605.02928v1 Announce Type: cross Abstract: In this study, we investigate the application of keyword spotting (KWS) in the domain of Hindi speech recognition, utilizing a dataset comprising 40,0
arXiv:2605.05009v1 Announce Type: new Abstract: Many decentralized distillation methods are designed around training-time coordination, yet deploy each node in isolation even when more capable neighbo
arXiv:2512.23864v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown remarkable generalization by mapping web-scale knowledge to robotic control, yet they remain bl
'Lighthouse' mode is a ComfyUI feature that visualizes workflow dependencies through color-coded highlighting based on graph distance from a selected node. When a user clicks on any node, direct depen
LTX-2.3 is an open-source video generation model capable of producing slow-motion effects and hyper-detailed visuals , with 4K output up to 20 seconds and native audio . The model addresses creator pa
arXiv:2605.04744v1 Announce Type: new Abstract: Plant breeding underpins global food security through incremental, accumulating improvements in crop yield, quality and sustainability, achieved via rep
Post-training quantization is a technique that reduces model size and improves inference performance by converting weights and activations to lower precision formats after training is complete. NVIDIA
Popular NoSQL-based database company MongoDB Inc. today announced a new set of capabilities during the company’s .Local conference in London, bringing together everything software and artificial intel
Grok Imagine is an image quality model that has been discussed on the ComfyUI blog, likely covering its capabilities for evaluating or enhancing image generation quality within the ComfyUI framework.
A LoRA adapter for FLUX.2 Klein that enables camera angle control across 72 unique positions using 8 azimuths, 9 elevations, and 3 distances . The model rotates objects through 360° azimuth and 60° el
arXiv:2511.01553v2 Announce Type: replace Abstract: AI systems on edge devices require online continual learning -- adapting to non-stationary streams and unfamiliar classes without catastrophic forge
Open source isn't just good for developers, it's one of America's strongest tools for AI security. More models means more defenders and more front doors protected. Earlier this week at the @MilkenInst
arXiv:2601.00020v3 Announce Type: replace-cross Abstract: Electroencephalography (EEG)-based brain-computer interfaces (BCIs) are strongly affected by non-stationary neural signals that vary across se
arXiv:2605.05017v1 Announce Type: cross Abstract: Embodied AI (EAI) systems are rapidly transitioning from simulations into real-world domestic and other sensitive environments. However, recent EAI so
arXiv:2605.04542v1 Announce Type: new Abstract: Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, dist
arXiv:2605.04647v1 Announce Type: new Abstract: We introduce ReflectDrive-2, a masked discrete diffusion planner with separate action expert for autonomous driving that represents plans as discrete tr
arXiv:2605.04913v1 Announce Type: new Abstract: LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it
arXiv:2605.03804v1 Announce Type: new Abstract: Long-term personalized memory for LLM agents is challenging on resource-limited edge devices due to high storage costs and multimodal complexity. To add
arXiv:2605.04468v1 Announce Type: cross Abstract: Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acq
arXiv:2605.04057v1 Announce Type: new Abstract: This paper focuses on a key challenge in Neural Architecture Search (NAS): integrating established architectural knowledge while exploring new designs u
arXiv:2605.05103v1 Announce Type: new Abstract: We introduce the **Concept Field** of a text corpus: a local drift field with pointwise uncertainty, estimated in sentence-embedding space from the delt
arXiv:2410.17517v5 Announce Type: replace-cross Abstract: Decision-making is an essential attribute of any intelligent agent or group. Natural systems are known to converge to effective strategies thr
Thoth v3.21.0 is a local-first AI assistant with integrated tools including a personal knowledge graph, voice, vision, shell, and browser automation capabilities. This release introduces Buddy Compani
arXiv:2512.20056v2 Announce Type: replace-cross Abstract: As Earth's climate changes, it is impacting disasters and extreme weather events across the planet. Record-breaking heat waves, drenching rain
arXiv:2602.06869v2 Announce Type: replace Abstract: We study a persistent failure mode in multi-objective alignment for large language models (LLMs): training improves performance on only a subset of
arXiv:2605.04543v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Models via draft-then-verify, where verification can be framed as an Optimal Transport (OT) problem. Exi
v0.30.0-rc3 is a release candidate version of Ollama published on May 7, 2026. As a release candidate, this version represents a pre-release milestone for the Ollama open-source project, which enables
Based on the release notes available, v0.30.0-rc4 appears to be a release candidate focused on continuous integration and platform-specific optimizations. The title suggests this build targeted Window
arXiv:2605.04078v1 Announce Type: new Abstract: Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent metho
We started running monthly research sessions at the @agi_inc office. First one was last Friday on PNM compilation. If you do on-device research and want to come present, apply here: https://form.typef
arXiv:2605.05148v1 Announce Type: new Abstract: One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized direc
arXiv:2605.01376v1 Announce Type: new Abstract: Current AI systems, grounded in oversimplified neuroscience, risk eroding the distinction between truth and falsehood. They maximize reward by amplifyin
arXiv:2605.03623v1 Announce Type: new Abstract: We propose a unified, few-step generative modeling framework based on cumulative flow maps for long-range transport in probability space, inspired by fl
arXiv:2605.03317v1 Announce Type: new Abstract: Representation alignment has recently emerged as an effective paradigm for accelerating Diffusion Transformer training. Despite their success, existing
arXiv:2605.02709v1 Announce Type: new Abstract: Healthcare automation is shaped by local procedures and organizational constraints, so agent capabilities rarely transfer unchanged across settings. Age