Alpie
Alpie (https://alpie.ai/ and documentation: https://github.com/169Pi/Alpie-Core) is a chatbot that offers in-depth research, generation of presentations, spreadsheets and websites. After choosing...
Aipoker.bot
Aipoker.bot (https://aipoker.bot/ and documentation: https://github.com/aipoker-bot) allows you to play poker against artificial intelligence against 49 opponents. 24 LLMs available with...
StepAudio 3 Music
StepAudio 3 Music (https://huggingface.co/spaces/stepfun-ai/StepAudio-3-Music and documentation: https://platform.stepfun.ai/docs/en/guides/models/stepaudio-3-music) generates songs or instrumental pieces from a description, with or without lyrics. Three...
ChessLM
ChessLM (sekor.eu.org/chesslm and documentation: github.com/skorotkiewicz/chesslm) plays chess against a lightweight, open-source AI model, chessLM, directly in the browser. A classic...
MultiMatte
MultiMatte (https://usefeyn.com/multimatte/ and documentation: https://github.com/feyninc/nobg) clips an image from a text statement, keeping what has been named and removing the...
North Small Translate
North Small Translate (https://huggingface.co/spaces/CohereLabs/North-Small-Translate-1.0 and documentation: https://huggingface.co/CohereLabs/North-Small-Translate-1.0) translates pasted text into up to eight languages simultaneously, with automatic source language...
StoryDiffusion
StoryDiffusion (https://huggingface.co/spaces/YupengZhou/StoryDiffusion and documentation: https://github.com/HVision-NKU/StoryDiffusion) generates comic book or photo novel-style boxes from a list of instructions. Generated from a...
Scira
Scira (formerly MiniPerplx: https://scira.ai/ and documentation: https://github.com/zaidmukaddam/scira) is a chatbot open-source specialized search engine that responds based on external sources...
LongCat-Video
LongCat-Video (demo: https://huggingface.co/spaces/multimodalart/LongCat-Video and documentation: https://github.com/meituan-longcat/LongCat-Video) generates a 6-second video from a text instruction, or an image with an instruction....
MiroThinker
MiroThinker (https://dr.miromind.ai/ — documentation: https://github.com/MiroMindAI/MiroThinker) answers a complex question by conducting a multi-step web search and producing a report with...
Boogu Image
Boogu Image (http://demo-base.boogu.org and documentation: https://github.com/boogu-project/Boogu-Image) generates and edits images from a text instruction, with embedded text rendering in French-English...
Lolaby
Lolaby (https://huggingface.co/spaces/build-small-hackathon/lolaby and documentation: https://huggingface.co/build-small-hackathon/lolaby-llama-3b) generates personalised lullabies based on an image (drawing or photo), a child’s first name, age...
Open Paper
Open Paper (application: https://openpaper.ai/ and documentation: https://github.com/khoj-ai/openpaper) allows you to read, annotate and query academic research articles. The imported pdf...
Stable Audio 3
Stable Audio 3 (https://huggingface.co/collections/stabilityai/stable-audio-3) is the new version of the music generation model of the Stable Audio family already seen...
Dim0
Dim0 (https://app.dim0.net and documentation: https://github.com/vcmf/dim0) is an infinite table, organized as a mind map, that can be filled with documents,...
Pixal3D
Pixal3D (four servers available: https://huggingface.co/spaces/TencentARC/Pixal3D-Server and documentation: https://github.com/TencentARC/Pixal3D) generates a high-quality 3D model from an imported image. Several renderings and...
Hum2song
Hum2Song (https://www.carlostoxtli.com/hum2song/, documentation: https://github.com/toxtli/hum2song) generates a musical accompaniment from a hummed or sung melody. Works locally and does not transmit...
CompaRAG
CompaRAG (https://comparag.vercel.app/, description: https://www.linkedin.com/pulse/au-coeur-du-premier-comparateur-doutils-rag-fran%C3%A7ais-la-sarazin-phd-rhdje/ and documentation: https://github.com/ArthurSrz/CompaRAG/) compares RAG tools blindly from instructions and documents submitted by the user.RAG, for...
Tokemon
Tokemon (https://tokemonlabs.com/ and documentation: https://github.com/leejustin/tokemon) presents 30 AI language models in the form of a Pokédex (see on Wikipedia) with...
Linto Studio
LinTO Studio (https://studio.linto.ai/ and documentation: https://github.com/linto-ai) transcribes and generates subtitles from audio or video files. Developed by Linagora 🇫🇷 and...
Open Maic
Open Maic (https://openmaic.io/, documentation: https://github.com/THU-MAIC/OpenMAIC, online demo https://open.maic.chat/) generates interactive courses from an imported topic description or PDF, orchestrating multiple...
Presenton
Presenton (https://presenton.ai/ — documentation: https://github.com/presenton/presenton) generates presentations from an imported statement or document. Open source, it can be installed and...
FireRed Image-Edit
FireRed Image-Edit (Documentation: https://github.com/FireRedTeam/FireRed-Image-Edit and Demo: https://huggingface.co/spaces/prithivMLmods/FireRed-Image-Edit-1.0-Fast) transforms an image from an instruction. Multiple images can be combined, elements can...
Reka
Reka (https://reka.ai/ and models: https://huggingface.co/RekaAI) offers several multimodal models for image and video analysis, text and voice.Two first versions were...
Smol LM 3
Smol LM 3 (documentation: https://huggingface.co/HuggingFaceTB/SmolLM3-3B and demonstration: https://huggingface.co/spaces/HuggingFaceTB/SmolLM3-3B-WebGPU) is a very lightweight language model (3 B parameters), produced by Huggingface....
Pascal Editor
Pascal Editor (application: https://editor.pascal.app/ and documentation: https://github.com/pascalorg/editor) generates, from instructions in a chatbot, 2D and 3D architectural plans with realistic...
World Monitor
World Monitor (https://www.worldmonitor.app/ and documentation: https://www.worldmonitor.app/docs/documentation, github: https://github.com/koala73/worldmonitor) is a real-time dashboard that brings together global geopolitical and economic information...
Adam
Adam (https://adam.new/ and documentation: https://github.com/Adam-CAD/CADAM) is a model that, coupled with a language model, transforms a natural language query into...
Gemma 4
Gemma 4 (description: https://huggingface.co/blog/gemma4) is the latest open-source model from Google.It is available on Hugging Face, in the Google AI...
Molmo web
Molmo Web (Documentation: https://allenai.org/blog/molmoweb and demonstration: https://molmoweb.allen.ai/) is a web agent that automates an internet search ordered by an instruction...
Coherent transcribed
Cohere Transcribe (documentation: https://huggingface.co/CohereLabs/cohere-transcribe-03-2026 and demonstration: https://huggingface.co/spaces/CohereLabs/cohere-transcribe-03-2026) transcribes recorded or imported audios. 12 languages available including French.Very faithful and fast...
Public ai
Public Ai (Chatbot: https://chat.publicai.co, project website: https://publicai.co/ and documentation: https://github.com/forpublicai) is an open-source chatbot based on the Apertus language model...
Deep Scholar
Deep scholar (https://deep-scholar.vercel.app, based on Lotus, open-source: https://github.com/lotus-data/lotus) is a semantic search engine coupled with a language model and focused...
Kugel Audio
Kugel Audio (documentation: https://github.com/Saganaki22/ComfyUI-KugelAudio and demonstration: https://huggingface.co/spaces/multimodalart/kugelaudio) is a text-to-speech (text-to-voice) model with 24 European voices. Two possibilities: generation from...
Sesame
Sesame (https://www.sesame.com/) is an oral conversation model currently in research version, based on the open-source csm model (https://github.com/SesameAILabs/csm).Current research is...
Voxtral
Voxtral (documentation: https://mistral.ai/fr/news/voxtral-transcribe-2 and demo: in Mistral AI studio or for direct transcription voxtral mini realtime – out of order...
Hugging Chat
Hugging Chat (https://huggingface.co/chat/) closed in 2025 (see the HuggingChat Assistants and HuggingChat Tools archives for the previous version) is accessible...
Chef by Convex
Chef by Convex (documentation: https://github.com/get-convex/chef and application: https://chef.convex.dev/) builds applications with databases from an instruction. Several language models are offered...
LLM Council
LLM Council (documentation: https://github.com/machine-theory/lm-council?tab=readme-ov-file, demonstration: https://huggingface.co/spaces/burtenshaw/karpathy-llm-council and video presentation of related research: <a href="https://www.youtube.com/watch?v=hI0XCE27QqE”>https://www.YouTube. com/watch?v=hI0XCE27QqE is a “democratic” space that...
Z-image
Z-image (documentation: https://github.com/Tongyi-MAI/Z-Image and Turbo version demonstration: https://huggingface.co/spaces/Tongyi-MAI/Z-Image-Turbo) is a lightweight (6 million parameters) and fast image generation model. Very...
Flux 2 Klein
Flux 2 Klein is an open-source lightweight model of Black forest LAbs from the same family as Flux 2 or...
TranslateGemma
TranslateGemma (documentation: https://blog.google/innovation-and-ai/technology/developers-tools/translategemma/ and 27B https://huggingface.co/spaces/hysts/translategemma-27b-it or 4B: https://huggingface.co/spaces/fantos/translate-gemma) is a translation template available in three sizes (4, 12, and...
GLM Image
GLM Image (documentation: <a href="https://huggingface.co/zai-org/GLM-Image”>https://huggingface.co/zai-org/GLM-Image and demonstration: <a href="https://huggingface.co/spaces/multimodalart/GLM-Image”>https://huggingface.co/spaces/multimodalart/GLM-Image) is a open-source image generation model produced by z.ai, publisher of...
Supertonic
Supertonic (documentation: https://huggingface.co/Supertone/supertonic-2 and demo: https://huggingface.co/spaces/Supertone/supertonic-2) is a “text-to-voice” model that can be installed and run locally on your computer...
Qwen Image Layered
Qwen Image Layered (documentation: <a href="https://github.com/QwenLM/Qwen-Image-Layered?spm=a2ty_o06.30285417.0.0.3ef2c921BiEZgfet”>https://github.com/QwenLM/Qwen-Image-Layered?spm=a2ty_o06.30285417.0.0.3ef2c921BiEZgfet demo: <a href="https://huggingface.co/spaces/Qwen/Qwen-Image-Layered”>https://huggingface.co/spaces/Qwen/Qwen-Image-Layered) generates the different “layers” or slaps of a supplied image by...
HY Motion 1.0
HY Motion 1.0 (documentation: HY Motion 1.0 is a model dedicated to the generation of 3D animations of characters –...
Google AI Edge Gallery
Google AI Edge Gallery (Github: https://github.com/google-ai-edge/gallery, direct IOS and Android Appstore links via the Play Store) is an experimental mobile...
Chatterbox
Chatterbox (documentation: https://github.com/resemble-ai/chatterbox and demonstration: https://huggingface.co/spaces/ResembleAI/Chatterbox-Multilingual-TTS) is a “text to speech” model open-source available in 23 languages for its Multilingual...
Mistral OCR 3
Mistral OCR 3 (documentation: https://mistral.ai/fr/news/mistral-ocr-3 and demonstration: https://console.mistral.ai/build/document-ai/ocr-playground) is the latest character recognition model in Mistral. Mistral OCR 3 accounts...
SAM Audio
Meta’s Sam Audio (description: https://ai.meta.com/samaudio/ and demo: https://aidemos.meta.com/segment-anything) searches for and isolates elements of a video or audio file from...
Molmo 2
Molmo 2 (documentation: https://allenai.org/blog/molmo2 / models: https://huggingface.co/collections/allenai/molmo2 / demonstration: https://playground.allenai.org/?model=molmo2-8b) is a series of lightweight and multimodal models specialized in...
Lucy
Lucy (https://platform.decart.ai/) is a set of image and video generation templates from Decart.ai: Mirage to change the style of a...
Stream 2
Flux 2 (https://playground.bfl.ai/) is a set of models from Black Forest labs: Flux flex, Flux Pro, and Flux dev. It...
Qwen Image Edit Camera Angle Control
Qwen Image Edit Camera Angle Control (demo: <a href="https://huggingface.co/spaces/linoyts/Qwen-Image-Edit-Angles”>https://huggingface.co/spaces/linoyts/Qwen-Image-Edit-Angles and documentation: <a href="https://huggingface.co/dx8152/Qwen-Edit-2509-Multiple-angles”>https://huggingface.co/dx8152/Qwen-Edit-2509-Multiple-angles) generates views from different angles of a...
Kutri
Kutri (documentation: https://huggingface.co/krutrim-ai-labs and chatbot: https://www.kruti.ai/) is the “India’s first AI assistant” chatbot produced by Krutrim AI Labs. Multilingual (including...
Oracles or novelists
Oracles or Novelists (app: https://oraclesouromanciers.streamlit.app/ and documentation: https://github.com/ArthurSrz/oracles_ou_romanciers) is an app that, according to its author Arthur Sarazin, “generates alternative...
Search for Jina.ai
Search by Jina.ai (demo: https://search.jina.ai/ and documentation: https://github.com/jina-ai) is a search engine with reasoning based on a series of dedicated...
TurboSeek
TurboSeek (https://www.turboseek.io/ and documentation: https://github.com/Nutlope/turboseek) is a search engine with generative AI, based on Gpt-oss for the answer and Llama...
Handy
Handy (https://handy.computer/ and documentation https://github.com/cjpais/Handy) is a speech to text tool, available on MacOS, Windows, and Linux and that works...
Minimax M2
Minimax M2 (https://agent.minimax.io/ and documentation: <a href="https://huggingface.co/MiniMaxAI/MiniMax-M2″>https://huggingface.co/MiniMaxAI/MiniMax-M2) is a language model specialized in agents with reflection and code or presentations....
Folo
Folo (documentation: https://github.com/RSSNext/Folo and application: folo.is) is a content aggregator (social networks, RSS feeds) augmented by generative AI-based functions: summary,...
Matrix Game
Matrix Game (documentation: https://matrix-game-v2.github.io/ and demo: https://huggingface.co/spaces/dn6/matrix-game-2) generates a motion video from a still image and an instruction. 8-second videos....
Umint
Umint (https://umint-openwebui.hf.space and documentation: https://huggingface.co/umint) for UltimaX Intelligence is a chatbot that brings together language and image models (GPT, Deepseek,...
Qwen 3 Omni
Qwen 3 Omni (documentation: https://github.com/QwenLM/Qwen3-Omni and use on hugging Face <a href="https://huggingface.co/collections/Qwen/qwen3-omni-68d100a86cd0906843ceccbe”>https://huggingface.co/collections/Qwen/qwen3-omni-68d100a86cd0906843ceccbe or Qwen Chat) is a language model “omnimodal”...
Qwen 3 next
With Qwen 3 next (documentation: http://huggingface.co/collections/Qwen/qwen3-next-68c25fd6838e585db8eeea9d and test on Qwen Chat) Alibaba offers a new language model open-source with long...
Hunyuan image
Hunyuan image (https://github.com/Tencent-Hunyuan/HunyuanImage-2.1 documentation and https://huggingface.co/spaces/tencent/HunyuanImage-2.1 demonstration) is a free open-source generation template from Tencent that generates high-resolution images. The...
Apertus
Apertus (download: https://huggingface.co/swiss-ai and free and unlimited test space on Public AI Inference Utility: https://chat.publicai.co/ ) is a fully open-source...
HunyuanVideo-Foley
HunyuanVideo-Foley (description: https://huggingface.co/tencent/HunyuanVideo-Foley and demonstration: https://huggingface.co/spaces/tencent/HunyuanVideo-Foley) sounds videos from the original and an instruction (optional). Up to 6 audios can...
Gpt-oss
Gpt-oss (demo: https://gpt-oss.com/ and documentation: https://huggingface.co/collections/openai/gpt-oss-68911959590a1634ba11c7a4): two language models open-source produced and made available by OpenAI, the first with 120...
TripoSG-Scribble
TripoSG-Scribble ( https://huggingface.co/spaces/VAST-AI/TripoSG-scribble Demonstration and Documentation: https://github.com/VAST-AI-Research/TripoSG) generates 3D images from a freehand drawing or photo and instruction. Optional instruction.Adjustment...
Qwen image edit
Qwen Image Edit (demo: <a href="https://huggingface.co/spaces/Qwen/Qwen-Image-Edit”>https://huggingface.co/spaces/Qwen/Qwen-Image-Edit and documentation: <a href="https://huggingface.co/Qwen/Qwen-Image-Edit”>https://huggingface.co/Qwen/Qwen-Image-Edit, also available on Qwen Chat) modifies a source image from...
Ernie 4.5
Ernie 4.5 (documentation: https://github.com/PaddlePaddle/ERNIE) is a language model developed by Baidu in several versions from 0.3 B to 424 B...
ThinkSound
ThinkSound (demo: https://huggingface.co/spaces/FunAudioLLM/ThinkSound and documentation: https://github.com/FunAudioLLM/ThinkSound) generates the soundtrack of videos by synchronizing and adding it directly to the original...
Gemma 3n
Gemma 3n (to be tested in Google ai studio or on Hugging Face spaces): two “lightweight” open-source language models designed...
Stepfun
Stepfun (https://stepfun.ai/) is a text and image generation chatbot that offers several templates and an agent: Step-R1-V-Mini specialized in reasoning...
Sparc3D
Sparc3D (available via https://hitem3d.ai/, documentation: https://lizhihao6.github.io/Sparc3D) is a model for generating 3D images from an image. Export GLB, OBJ &...
Kyutai STT
Kyutai STT (https://kyutai.org/next/stt) is Kyutai’s “speech to text” model, available in two versions open-source: STT-1B-en_fr (Documentation: https://huggingface.co/kyutai/stt-1b-en_fr): , which includes...
Ace-step
Ace-Step (https://huggingface.co/spaces/ACE-Step/ACE-Step) is a open-source music generation model (documentation: https://ace-step.github.io/).Generate from lyrics and one of the 10 preset musical styles...
AudioX
AudioX (https://huggingface.co/spaces/Zeyue7/AudioX) generates sounds and music from an instruction and can link them to a video.Sounds and 10-second video clip,...
Bagel
Bagel (demo: https://demo.bagel-ai.org/ and documentation: https://github.com/ByteDance-Seed/Bagel) is a multimodal model open-source ByteDance including text, image and reasoning. French is accepted...
Open Knowledge Maps
Open Knowledge Maps (https://openknowledgemaps.org/) generates a map of scientific knowledge based on the corresponding 100 scientific articles published in Open...
Llama Tutor
Llama Tutor (https://llamatutor.together.ai/ and documentation: https://github.com/Nutlope/llamatutor) is a chatbot based on Llama 3.1 configured to support learning according to a...
Superexpert
Superexpert (https://superexpert.ai, demo space: https://demo.superexpert.ai and download: https://github.com/Superexpert/superexpert-ai) allows the creation of custom chatbots. Open source, it can be deployed...
Hunyuan 3D
Hunyuan 3D (https://3d.hunyuan.tencent.com. Open source, documentation: https://huggingface.co/tencent/Hunyuan3D-2) generates textured 3D models from an instruction or image. Fine-tuning, URL sharing and...
Magi
Magi (https://sand.ai/magi) generates videos from an image.The extension of the generated videos is possible by keeping the elements present in...
Bitnet B 1.58
Bitnet B 1.58 (Documentation: https://huggingface.co/microsoft/bitnet-b1.58-2B-4T and chatbot on Huggingface: <a href="https://huggingface.co/spaces/suayptalha/Chat-with-Bitnet-b1.58-2B-4T”>https://huggingface.co/spaces/suayptalha/Chat-with-Bitnet-b1.58-2B-4T) is a Microsoft language model open-source that works with...
Hidream
Hidream (Templates & Documentation: https://huggingface.co/collections/HiDream-ai/hidream-i1-67f3e90dd509fed088a158b3) is a open-source image generation template available in three versions: dev, full, and fast. High...
Llama 4
Llama 4 (presentation on https://www.llama.com) is Meta’s new language model available in two versions, Scout (demo: <a href="https://huggingface.co/spaces/openfree/Llama-4-Scout-17B-Research”>https://huggingface.co/spaces/openfree/Llama-4-Scout-17B-Research) and Maverick...
Deepsite
Deepsite (https://huggingface.co/spaces/enzostvs/deepsite) generates a single page of code from an instruction to create applications or web pages. The code is...
Docs
Docs (https://docs.numerique.gouv.fr) is a collaborative word processor with generative AI features: generating text from a text that acts as an...
Wan 2.1
Wan 2.1 is a open-source video generation template from Alibaba (documentation: https://github.com/Wan-Video/Wan2.1, demo: https://huggingface.co/spaces/Wan-AI/Wan2.1, and dedicated website: https://wan.video/). On the...
DiffRhythm
DiffRhythm (description: https://aslp-lab.github.io/DiffRhythm.github.io/ and test: https://huggingface.co/spaces/ASLP-lab/DiffRhythm) generates music tracks with lyrics from the timed lyrics and a music snippet.Tool for...
Aya
Aya from “Cohere For AI” (https://cohere.com/research/aya): 3 language models and 2 image analysis models from a research project with the...
Open Deep Research
Open Deep Research (description: https://huggingface.co/blog/open-deep-research and demo space: https://huggingface.co/spaces/m-ric/open_Deep-Research ) is the ” reasoning ” research agent developed by Hugging Face… in...
Mind Map Wizard
Mind Map Wizard (https://mindmapwizard.com) generates mind maps from a statement (150 character limit).Editing in text format, url sharing and pdf,...
Zonos
Zonos (description: https://www.zyphra.com/post/beta-release-of-zonos-v0-1#zonos_2, test space: https://playground.zyphra.com/audio) voiced a pasted text. 4 expressive voices and 6 languages available. Cloning voices from...
Tulu 3
Tülu 3 405B (https://playground.allenai.org) is a language model of the American non-profit research institute AI2 (https://allenai.org). Fully open-source (data, code,...
Janus Pro
Janus Pro (description: https://huggingface.co/deepseek-ai/Janus-Pro-7B) is a DeepSeek image model. Multimodal. Efficient in image analysis, more random in generation (e.g. text...
Open Canvas
Open Canvas (https://opencanvas.langchain.com) adds interactive generation to a chatbot in the manner of ChatGPT canvases or Claude artifacts. With GPT...