AI Creators Tools Directory
Featured Tools
Dreamina AI
Dreamina AI drops OmniHuman-1 a new image-to-video model that lip-syncs your portraits with audio and real gestures. It's not perfect but it's a sharp new option in the AI video space.
Pollo AI
Pollo AI is primarily an all-in-one video generator, letting users access models from Kling, Veo, Runway, Luma and others. Its user-friendly interface supports text-to-video, image-to-video, and the recently introduced video-to-video transformations, offering various styles like anime and pixel art. The platform is designed for speed, making it ideal for projects with tight deadlines.
Building visuals, videos or audio projects? There’s something here for you. And since we update almost daily, you’ll always find new stuff to check out.
Need to narrow it down? Easy—filters and a favorites feature let you find what works for you. Ready to simplify or make your next big idea? Start exploring now and see how AI can fit into your workflow.
Latest Tools
Dia
Dia adds emotion sound quirks and real voices to your text. Free if you run it yourself or pay a few cents to use it online.
Kyutai TTS
Kyutai's TTS-1.6B is a blazing fast open-source text-to-speech model with live voice output in English and French. It speaks in 220 ms flat and handles long texts like a pro.
Poe
Poe brings top AI bots, image makers, audio and video generators into one spot, aside from other generative AI tools. If you like messing with AI without the mess Poe’s a pretty chill option.
Vivago.ai
Vivago.ai turns text prompts into videos images and even 3D models. No skills needed just type and create. Free plan included.
Veena TTS
India's first open-source TTS model Veena brings natural voices to Hindi, Hinglish and English with sub"‘80"¯ms latency and four distinct voices.
OmniGen2
OmniGen2 is free open-source AI that edits images writes prompts blends visuals and keeps improving itself thanks to a smart feedback loop
Latest News
July 10, 2025
Recraft: Recraft just joined the AI agent network. They rolled out a Model Context Protocol server so now you can make and edit raster and vector images right inside chatbots like Claude or Cursor. Handy for devs and users who like to mess with new stuff.
July 10, 2025
Higgsfield AI: Higgsfield dropped Soul ID for it's image generator. It gives you custom stable characters with a Soul-esque artsy lifelike look.
July 9, 2025
Vivago.ai: Multi-Element Reference Video Generation is here. You can keep the same look across characters props and scenes using your own images.
July 9, 2025
Vidu AI: Vidu AI added a new Reference-to-Video tool that lets you upload up to seven images like characters scenes or props to make videos. It puts these together based on what you type and keeps the look steady across scenes. Characters stay the same with all their details which makes it good for episodes. You can change one image without messing up the whole scene so updates are easy while you're working on a video.
July 8, 2025
Veo: A faster and cheaper "Veo 3 Fast" mode has been added to the Frames to Video tool in Flow.
Users can now add speech to images using Veo 3’s first-frame to video feature. This audio function is still in beta and may not always produce sound.
July 6, 2025
Hailuo AI x Minimax: Hailuo has introduced the Max Plan, which includes:
- 20,000 credits/month for Hailuo 01, 02 & Agent
- Unlimited slow mode after credits
- 1080p & 768p, 10s & 6s videos
July 4, 2025
Veo: Google's Veo 3 is now rolling out globally for Gemini Pro users. People in India Indonesia Europe and more can now make up to three videos a day and the count resets daily. Each video has sound and gets made in minutes. It’s said photo to video might be coming soon. The update also lowers some limits and opens access wider.
July 3, 2025
Wan (Open-source): WanGP v6.5 is here!
Built-in MMAudio (low VRAM)
Post-gen upsampling & audio options
MagCache, SageAttention2++
Video2Video via Text2Video
FusioniX upsampler/restorer
July 3, 2025
FLUX.1 Kontext: Black Forest Labs has upgraded FLUX.1 Kontext with NVIDIA TensorRT support, enabling twice the inference speed on RTX GPUs. Model quantization has reduced memory usage from 24GB to 7GB (FP4) without quality loss. Production-ready variants in BF16, FP8, and FP4 formats are now available on Hugging Face.
July 3, 2025
Freepik: Freepik now offers UNLIMITED image generation for Premium+ and Pro users—no caps, tokens, or waiting. Designed to remove creative limits and keep your flow going.
Tests Comparing Generative AI Outputs
Guy climbing into tv
Woman magically going younger
World domination ai
Grannie riding cats
Realistic woman in anime scene
Explore Quick AI Video Templates & Effects
Right now, logged-in users can save their favorite tools and even rate them. It’s perfect for keeping track of what works and sharing your top picks with others.