AIAIAny
  • Search
  • Collection
  • Category
  • Tag
  • Daily AI
AIAIAny

Category

Explore by categories

AIAIAny

Curated AI Resources for Everyone

[email protected]

Powered by airss.app

Product
  • Search
  • Collection
  • Category
  • Tag
Resources
  • Blog
Company
  • Privacy Policy
  • Terms of Service
  • Sitemap
Copyright © 2026 All Rights Reserved.
  • All Categories

  • AI Leaderboard

  • AI Agent Tutorials

  • AI Coding Tutorials

  • AI Model

  • AI Agent Papers

  • Chatbot

  • AI Dataset

  • Machine Learning Foundation Books

  • AI Train

  • AI Deploy

  • AI Client

  • Machine Learning Foundation Papers

  • Machine Learning Foundation Tutorials

  • AI Image Demos

  • AI Agent

  • Large Language Model Tutorials

  • Large Language Model Papers

  • Machine Learning Engineering Papers

  • Computer Vision Tutorials

  • Computer Vision Papers

  • Natural Language Processing Papers

  • Reinforcement Learning Papers

  • Speech Technology Papers

  • AI API

  • AI Coding

  • AI Image

  • AI Video

  • MLOps

  • MCP Client

  • MCP Server

  • AI Video Papers

  • AI Audio

  • AI Others

  • AI Infra

  • Embodied AI

GitHub
AI Image·2026
Icon for item

Modly

Lightning Pixel

Turns photos into exportable 3D meshes using open-source AI models that run entirely on your GPU. Desktop app for Windows and Linux with an extension system to install local model generators and export common 3D formats.

#ai-image#image#nodejs#python#github+2
GitHub
Computer Vision Papers·2026
Icon for item

See-through: Single-image Layer Decomposition for Anime Characters

Jian Lin, Chengze Li +6·Saint Francis University, University of Pennsylvania +2

Turns a single anime illustration into up to 23 semantically organized, inpainted layers with inferred drawing order, exported as a layered PSD. It provides a 2.5D animation starting point, but does not handle Live2D rigging or motion.

#github#paper#research#segmentation#depth+2
GitHub
AI Agent·2026
Icon for item

Higgsfield AI Skills

Higgsfield AI

Turns image, video, and visual-brand work into workflows callable by AI coding agents, spanning character identity, product photography, brand systems, website building, and video analysis.

#agent-skills#ai-agent#coding-agents#claude-code#ai-image+2
GitHub
AI Image·2026
Icon for item

HeliosGen

SegFault42, poms32 +4

Build and run node-based AI image and video generation pipelines locally — chain prompts, models, reference images and automations on an infinite canvas. Key differentiators: multi-model pipelines and local-first operation (bring your own kie.ai key), so you keep media and credits under your control.

#desktop#ai-workflow#ai-image#ai-video#react+6
GitHub
AI Agent·2026
Icon for item

0x0funky/agent-sprite-forge

Turns one approved character still into game-ready 2D animations. It combines image-to-video generation with frame-level quality checks, keying, registration, timing, and engine exports.

#agent-skills#ai-agent#ai-image#ai-video#coding-agents+2
GitHub
AI Image·2026
Icon for item

Prompt as Code | GPT-Image2 (awesome-gpt-image-2)

freestylefly, ImgBotApp +2

Turns 530+ GPT-Image2 examples into a structured 'Prompt-as-Code' library and style skill for reproducible image-generation workflows; includes a browsable gallery, 20+ industrial templates, and an agent-ready style skill for automation.

#prompt-engineering#ai-image#ai-image-demos#agent-skills#gitHub+1
Hugging Face
AI Model·2026
Icon for item

HiDream-O1-Image-Dev

HiDream-ai

Distilled dev checkpoint of an image foundation model that natively unifies raw pixels and text tokens for text-to-image, image editing, long-text rendering, and subject-driven personalization at up to 2048×2048. The Dev variant targets faster (28-step) inference for iterative use and research.

#foundation-model#multimodal#transformers#ai-image#ai-demos+2
Hugging Face
AI Image·2026
Icon for item

HiDream-O1-Image

HiDream-ai

Generates and edits high-resolution images (up to 2048×2048) from text and reference images, plus subject-driven personalization. Implements a pixel-level unified transformer that encodes raw pixels and text in one token space and includes a reasoning-driven prompt agent for layout and text rendering.

#transformers#multimodal#ai-image#huggingface#gemma+4
Hugging Face
AI Model·2026
Icon for item

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

Microsoft

Research-focused text-to-image foundation model that prioritizes training efficiency: a 3.8B-parameter architecture trained on an 800M image-text corpus with mixed-resolution learning, FLUX.2 VAE, RL tuning, and a distilled 4-step Lens-Turbo for fast high-resolution generation.

#microsoft#huggingface#ai-image#image#transformers+3
GitHub
AI Image·2026
Icon for item

无限画布 (infinite-canvas)

Node-based infinite-canvas web workstation for iterative visual creation — integrates image/video generation, reference editing, prompt library, multi-agent assistants, and asset management. Runs in-browser with configurable OpenAI-compatible endpoints; suited for local/personal deployment (AGPL-3.0).

#ai-image#image#ai-agent#mcp-client#typescript+6
Hugging Face
AI Model·2026
Icon for item

Bonsai Image · Ternary 4B (gemlite 2-bit)

Prism ML (prism-ml)

A ternary-weight (~1.58-bit) 4B text-to-image diffusion transformer optimized for NVIDIA GPUs using Gemlite INT2 and HQQ; it reduces the transformer to ~1.21 GB (4.55 GB CUDA payload) and targets 1024×1024 generation with a 4-step FlowMatch-Euler sampler.

#huggingface#ai-image#image#nvidia#ai-inference+3
Hugging Face
AI Image·2026
Icon for item

Krea 2 (Comfy-Org/Krea-2)

Comfy-Org, Krea

Provides ComfyUI-ready repackaged checkpoints of the Krea 2 image model family for local text-to-image workflows. Includes RAW (undistilled base for fine-tuning and LoRA training) and Turbo (8-step distilled checkpoint for fast inference), using a Qwen Image VAE and Qwen3‑VL encoder.

#qwen#diffusers#huggingface#ai-image#image+2
  • Previous
  • 1
  • 2
  • More pages
  • 6
  • 7
  • 8
  • Next