PocketPal
PocketPal (https://github.com/a-ghorbani/pocketpal-ai) allows you to install a lightweight LLM directly in your iOS or Android phone and use it in...
Lucie
Lucie (https://huggingface.co/OpenLLM-France/Lucie-7B): language model 🇫🇷, fully open-source, suitable for uses such as education. Developed by the consortium @openllm_france and @linagora....
SPAR 3D
SPAR 3D (https://huggingface.co/spaces/stabilityai/stable-point-aware-3d…) transforms a 2D image into a 3D image. After removing the background and isolating the object, transforms...
Phi 4
Phi 4 (https://huggingface.co/microsoft/phi-4) latest version of Microsoft’s LLM / SLM (Small Model) is available in open-source (MIT license). Fairly short...
Omnicontrol
Omnicontrol (https://huggingface.co/spaces/Yuanshi/OminiControl…) generates images from a source image and an instruction. Model-based generation of image analysis and Flux 1. Free,...
3D Trellis
Trellis (https://huggingface.co/spaces/JeffreyXiang/TRELLIS…) generates a #3D model from one or more images. Background automatically erased and fine adjustments available. Export GLB...
Shou Xin
Shou Xin (https://huggingface.co/Datou1111/shou_xin…) generates images as pencil drawings in b&w or color – based on Flux. Add “shou_xin” + “pencil...
DeepSeek
DeepSeek (https://chat.deepseek.com): language model reasoning. Edit on 22/01/2025 DeepSeek now offers DeepSeek R1, a direct competitor to the latest major...
Nemotron 70B
Nemotron 70B from @nvidia (https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct…) is a language model based on Llama 70B, with better results than GPT4o or Claude...
Magic Quill
Magic Quill (https://huggingface.co/spaces/AI4Editing/MagicQuill…) allows you to generate new parts of an image in selected parts. Multiple selection sizes and fine...
Stable Diffusion 3.5
Stable Diffusion 3.5 (https://stability.ai/news/introducing-stable-diffusion-3-5…) is the latest image generation model from @StabilityAI. Available in two versions: wide and wide turbo...
Hermes 3
Hermes 3 (https://lambda.chat/chatui/) is a language model based on Llama 3.1 announced with greater reasoning skills and more creative. Description...
SVG Studio
SVG Studio (https://svgstud.io) offers two tools centered around the SVG format: a generator with advanced functions based on Stable Diffusion...
ToonCrafter
ToonCrafter (https://huggingface.co/spaces/Doubiiu/tooncrafter…) generates a very short video from two images, one at the beginning and one at the end. Fine...
Molmo
Molmo (chatbot: https://molmo.allenai.org): a multimodal language model open-source for image analysis/conversations.Description: https://molmo.allenai.org/blog. Unlimited. Images for testing: https://commons.wikimedia.org/wiki/File:Alps-glaciers.png?uselang=fr… / https://upload.wikimedia.org/wikipedia/commons/thumb/e/ea/Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg/520px-Van_Gogh_-_Starry_Night_-_Google_Art_Project.jpg… .
Pro Feed
Flux pro (https://replicate.com/black-forest-labs/flux-pro) is a new image generation template with powerful text-in-image generation management. Demo with fine adjustments to test...
Qwen 2
Qwen 2 (project: https://huggingface.co/Qwen and demo on Hugging Face: https://huggingface.co/spaces/Qwen/Qwen2-57b-a14b-instruct-demo…) is a language model open-source developed by @AlibabaGroup. 5 sizes...
Auraflow
Auraflow (https://huggingface.co/spaces/multimodalart/AuraFlow…) is a new opensource image generation model with 6.8 billion parameters (documentation: https://huggingface.co/fal/AuraFlow). Advanced features available. Beta version,...
Swift
Swift (https://swift-ai.vercel.app): a voice assistant based on LLama developed by Groq, Cartesia and Vercel. Quick reaction allows conversations (FR if...
Pdf to chat
Pdf to chat (http://pdftochat.com) offers the analysis of pdf documents via a chatbot with pdf reader tools. Iteration and internal...
Morphic
Morphic (http://morphic.sh): open-source search engine coupled with a text generative AI. Response with request for precision, sources, images, generation and...
Notes GPT
Notes GPT (http://usenotesgpt.com) transcribes audio notes into items in a checklist and offers a summary. Generation via Mistral ai. Specify...
Image to music
Image to music (https://imagetomusic.top) generates music with an image. Without account and open-sourceTests (img wikimedia): – Gull: https://cdn-uploads.huggingface.co/production/uploads/noauth/5Ie6bRDNcgJUbZ1lghfHc.wav… – Starry...
SDXL Lightning
SDXL Lightning (https://fastsdxl.ai), based on Stable Diffusion XL, generates images in real time. “Seed” available. Free, no account, unlimited and...
Stable Cascade
Stable Cascade (https://stability.ai/news/introducing-stable-cascade…) is the new @StabilityAI image generation model, faster and less resource-intensive. In demo on HugginFace: https://huggingface.co/spaces/multimodalart/stable-cascade…. Quite...
OpenGPTs
OpenGPTs (https://opengpts-example-vz4y4ooboq-uc.a.run.app Documentation on Github:https://github.com/langchain-ai/opengpts…): customizable chatbots in the manner of OpenAI GPTs. 6 LLMs available, 3 possibilities: simple chatbot,...
Image Mixer
Image Mixer (https://cloud.lambdalabs.com/demos/lambda/image-mixer-demo…) generates an image from a series of URLs, texts or images (5 maximum), each source can be...
Paint AI
Paint AI (https://paintai.groupmind.co.uk): a simple drawing tool… without tools! Tools generated on demand from a prompt and then editable if...
AI Comic Factory
AI Comic Factory (https://huggingface.co/spaces/jbilcke-hf/ai-comic-factory) created 2 comic strips from a prompt, a style and a choice of template. French if...
Turbo Art
Turbo Art (https://turbo.art) generates #images from a prompt and allows you to interact in real time via simple drawing tools...
Fast SDXL
Fast SDXL (https://huggingface.co/spaces/openskyml/fast-sdxl-stable-diffusion-xl…): image generation tool based on Stable Diffusion XL. Generate an image in about 20s with fine parameterization...
SDXL turbo
SDXL turbo (beta version: https://clipdrop.co/stable-diffusion-turbo…) is the latest image generation model from Stable Diffusion @StabilityAI (description:https://stability.ai/news/stability-ai-sdxl-turbo). Split-second generated images and...
Stable Video Streaming
Stable Video Diffusion (https://stability.ai/news/stable-video-diffusion-open-ai-video-model…) generates short videos from an image. On the waiting list but 2 possible test locations: https://huggingface.co/spaces/multimodalart/stable-video-diffusion…...
Illusion Diffusion HQ
Illusion Diffusion HQ (https://huggingface.co/spaces/AP123/IllusionDiffusion) allows you to create optical illusions from a proposed or imported illusion and a prompt. Many...
Idefics
Idefics (https://huggingface.co/spaces/HuggingFaceM4/idefics_playground…), a visual language model, answers questions asked on images. Accepts FR, answer in EN. Free, open-source. Test sources:...
Waveformer
Waveformer (https://waveformer.replicate.dev) generates a piece of music for up to 30 sec from a prompt, based on MusicGen. Export audio...
FlashcardX
FlashcardX (https://ai.flashcardx.com) creates flash cards from copied and pasted text. Free, open-source and account not mandatory. Source for the test:...
Ask2end
Ask2end (ask2end.com): a question asked on a given topic, Ask2End answers it and then produces a new question/answer until the...
Transvibe
Transvibe (https://transvribe.com) allows the querying of a YouTube video via a chatbot. Transcript export possible. Free and without account.
Semantic Scholar
Semantic Scholar (http://semanticscholar.org) uses AI in its search engine for scientific articles (200M database) and makes links between articles. Accepts...
AiPage
AiPage (http://AiPage.dev): a prompt and a home page in HTML is generated. Direct modifications possible, export HTML. Opensource and without...
LLAMA
Want to test Llama2, @MetaAI’s open-source model? 3 tools discovered:– @a16z demo: https://llama2.ai (with account)– demo of Huggingface https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI… (without...
Pollination
Pollinations (https://pollinations.ai -> https://replicate.com/pollinations): generative AI of images free and without account. An image gallery, a location for a prompt...
MusicGen
MusicGen from Facebook is in demo on Huggingface (https://huggingface.co/spaces/facebook/MusicGen): a prompt with a piece of music as possible inspiration and...
The infinite drum machine
The infinite drum machine (https://experiments.withgoogle.com/ai/drum-machine/…): when AI classifies and maps everyday sounds autonomously to generate configurable beats. Open source. Video...
Zoo
Zoo (https://zoo.replicate.dev): 7 generative AI models of images (3 stable diffusion, dall-e, kandisky, deepfloyd and material-diffusion) in the same free,...
Teach anything
Teach anything (https://teach-anything.com): A question asked with a chosen language and answer level and an explanation is generated.
MiniGPT4
When a visual model meets a language model… MiniGPT4 illustrates the image dialogue features of GPT4: a starting image becomes...
Open Assistant
Open-assistant, a new text-generating AI model, in development and open-source, that can be helped to develop in French via tasks...
AutoGPT
Would you like to discover AutoGPT (https://github.com/Significant-Gravitas/Auto-GPT…) which makes ChatGPT more autonomous without having the skills for its long installation?...
StableLM
After ChatGpt, Claude or Dragonfly (available in@poe_platform), want to test a new language model? @StabilityAI (= Stable diffusion) provides StableLM...
BingGPT
Bing’s chatbot – only it – and therefore GPT4 directly in your computer without going through Edge or the Bing...
WebChatGPT
An access to the web for Chat GPT so that it can draw on recent sources and cite them? The...
Paint by Text
Paint by text, the editing of images from a text query. https://paintbytext.chat
Scribble Diffusion
A freehand drawing specified by a prompt and Scribble Diffusion offers us an image. Open source. https://scribblediffusion.com/ Try it here:...