You're using ChatGPT 4.5, which doesn't have native image output at all Also my screenshots are two separate chats; initial refusals make it more likely to refuse in the future so you want to start a new one
MULTIMODAL AI
-
MatchAnything: Universal Cross-Modality Image Matching Framework
By
–
📢 MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training
— Satya Mallick (@LearnOpenCV) 31 mars 2025
MatchAnything presents a powerful large-scale pretraining framework for universal image matching across modalities, enabling detector-free matchers (ROMA, ELoFTR) to handle unseen cross-modal… pic.twitter.com/1a6zbeRzWTMatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training MatchAnything presents a powerful large-scale pretraining framework for universal image matching across modalities, enabling detector-free matchers (ROMA, ELoFTR) to handle unseen cross-modal
-
Runway Gen-4: SOTA Image-to-Video Model
By
–
Runway released Gen-4, a new SOTA image-to-video model that excels at fidelity, dynamic motion and controllability. Available to paid users starting today. https://t.co/3dZtt8BcLa pic.twitter.com/rkqIaTBAUD
— 🚨 AI News | TestingCatalog (@testingcatalog) 31 mars 2025Runway released Gen-4, a new SOTA image-to-video model that excels at fidelity, dynamic motion and controllability. Available to paid users starting today.
-
Runway Gen-4: AI Video Generation for Real Production Workflows
By
–
Learn more at the link below about how our research, product and creative teams worked in close collaboration to build Gen-4 for real-world productions and pipelines. http://
runwayml.com/research/intro
ducing-runway-gen-4
… 8/8 -
Gen-4 Image-to-Video Rolling Out to All Paid Plans
By
–
Gen-4 Image-to-Video is now rolling out to all paid plans and Enterprise customers. References will be available soon. 7/8
-
Gen-4 Enables Consistent Visual Storytelling Through AI
By
–
Using visual references, combined with instructions, Gen-4 allows you to create new images and videos with consistent styles, subjects, locations and more. Allowing for continuity and control within your stories. To test the model’s narrative capabilities, we have put together
-
Gen-4 Creates Hyper-Real Animals in New York Cinematic Scenes
By
–
New York is a Zoo is a showcase of Gen-4’s impressive visual effects capabilities that brings hyper-real animals into cinematic scenes of New York. Each scene in the film was created by first combining real reference images of animals with real photographs of New York using Gen-4
-
Gen-4 AI Models Launch for Advanced Media Generation
By
–
Today we're introducing Gen-4, our new series of state-of-the-art AI models for media generation and world consistency. Gen-4 is a significant step forward for fidelity, dynamic motion and controllability in generative media. Gen-4 Image-to-Video is rolling out today to all paid
-
Gen-4 Sets New Standard for AI Video Generation
By
–
Gen-4 sets a new standard for video generation and is a marked improvement over Gen-3 Alpha. It excels in its ability to generate highly dynamic videos with realistic motion as well as subject, object and style consistency with superior prompt adherence and best-in-class world
-
LLM Text Interfaces Need to Evolve Beyond Command Terminals
By
–
Writing text back and forth with an LLM is like we're all the way back to the era of command terminals. The "correct" output is a lot closer to custom web apps written just for your query, information laid out spatially, multimodal, interactive, etc. Will take some time. https://t.co/dMAQEjE8GF pic.twitter.com/N849kmMTZQ
— Andrej Karpathy (@karpathy) 31 mars 2025Writing text back and forth with an LLM is like we're all the way back to the era of command terminals. The "correct" output is a lot closer to custom web apps written just for your query, information laid out spatially, multimodal, interactive, etc. Will take some time.