A new paper demonstrates how to adapt image diffusion models for text generation using 10 times less data. Researchers have introduced a novel approach to generate text with diffusion models. While diffusion models excel in image and video generation, current state-of-the-art text generation systems still depend on discrete tokens.
GENERATIVE AI
-
Comparative Cost Analysis of Generative AI Video Tools
By
–
Parlons chiffres. Coût par vidéo avec Seedance 2.0 : ↳ Higgsfield → 1,29$ ↳ Freepik → 1,31$ ↳ Topview → 1,20$ ↳ OpenArt → 0,96$ ↳ Seedance → 0,76$ ↳ Pollo AI → 0,11$ 100$ = ~1 000 vidéos sur Pollo AI. Les mêmes 100$ = ~77 vidéos sur Higgsfield. Le calcul est
-
Practical Workflow for Low-Cost AI Video Generation
By
–
Je viens de générer cette vidéo à partir d'une seule photo et pour moins de 0,11$.
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 15 mai 2026
Non, c'est pas une faute de frappe.
Voilà comment j'ai fait :
Gardez-la précieusement en Signet 🔖 pic.twitter.com/5Njqc8BYZpJe viens de générer cette vidéo à partir d'une seule photo et pour moins de 0,11$. Non, c'est pas une faute de frappe. Voilà comment j'ai fait : Gardez-la précieusement en Signet
-
Codex critiques developer-focused interface and bias against non-coders.
By
–
Codex is very good, but it is still a very "developer coded" interface for an everything app. And it continues the somewhat annoying AI perspective that non-coders are just not as competent and need stuff hidden from them, as opposed to requiring a different form of complexity.
-
AI Creates Episodic Short Dramas from Prompts
By
–
🚨 Mobile-first storytelling just got a cool upgrade.
— Charly Wargnier (@DataChaz) 15 mai 2026
Drama Studio is now live on @TopviewAIhq, the world's very first AI-native episodic short drama creator.
→ You bring the story prompt
→ Topview handles casting, dialogue, voice, and editing 👀 https://t.co/nDSgtSkufHMobile-first storytelling just got a cool upgrade. Drama Studio is now live on @TopviewAIhq
, the world's very first AI-native episodic short drama creator. → You bring the story prompt
→ Topview handles casting, dialogue, voice, and editing -
Supertonic: High-Speed Open-Source On-Device TTS Engine
By
–
this TTS model generates speech 167x faster than you can hear it. Supertonic is an on-device TTS engine that runs via ONNX for cross-platform inference. – no GPU
– 31 languages
– captures every emotion
– beats ElevenLabs on speed
– runs even on a Raspberry Pi 100% open-source. -
OpenAI working on ‘Locked use’ feature for Codex on Mac
By
–
OpenAI is working on a dedicated setting for Codex to allow users to enable "Locked use." > Let Codex use your Mac while it's locked No more need to carry a half-open laptop around?
-
MiniMax Hub AI Video Generation Tool and Workflow
By
–
MiniMax Hub is free to try. Seedance 2.0 models are 65% off until June. Fast + Standard.
480p / 720p / 1080p. If your AI video workflow is still 37 Chrome tabs and pain… Download it here: https://
hub.minimax.io Follow @GodofPrompt for more AI tools + workflows. -
Optimizing Creative Workflows with AI Skills and Prompt Structures
By
–
The sleeper feature is Skills. Build a workflow once. Reuse it forever. Prompt structures.
MV creation steps.
Character consistency rules.
First/last frame formats.
QA checks. Stop doing the same creative admin work like a human API call. -
AI Agents for Autonomous Video Production Workflows
By
–
For video, this gets nasty.
— God of Prompt (@godofprompt) 15 mai 2026
Give it reference images, music, and a rough idea.
The Agent can plan scenes, generate assets, keep references organized, and use models like Seedance 2.0 for video output.
You stop babysitting every step.
You direct. It executes. pic.twitter.com/qiHeP2Z4T5For video, this gets nasty. Give it reference images, music, and a rough idea. The Agent can plan scenes, generate assets, keep references organized, and use models like Seedance 2.0 for video output. You stop babysitting every step. You direct. It executes.