you can do a omni-reference to put yourself in an image then do image-to-video from there
MULTIMODAL AI
-
Image Generation Quality and Professional Upscaling Needs
By
–
Me gusta mucho que se conserve tan bien la estética de las imágenes. Estoy revisitando imágenes generadas hace meses y animándolas y es un pasada!
— Carlos Santana (@DotCSV) 18 juin 2025
Dicho lo cual, una resolución de 480p sin un upscaler como Topaz, no va a ningún lado profesionalmente.
Y ya si tuvieran una API… pic.twitter.com/xOsycEhglNMe gusta mucho que se conserve tan bien la estética de las imágenes. Estoy revisitando imágenes generadas hace meses y animándolas y es un pasada! Dicho lo cual, una resolución de 480p sin un upscaler como Topaz, no va a ningún lado profesionalmente. Y ya si tuvieran una API…
-
Relax Mode Pro Tier: Advanced Motion Prompt Engineering
By
–
we're testing relax mode on the pro tiers and higher right now. try auto prompting at first then just try exploring writing more detailed motion prompts
-
New Image Modes and Upscaler Coming With GPU Constraints
By
–
we'll be releasing more image modes next and a upscaler too, for now we wanted to 'start small' because we might run out of gpus no matter what we do
-
AI Generated Alien Drinking Beer at NBA Finals Game
By
–
¿Un alien bebiendo cerveza en medio de la final de la NBA? ¡Sí, esto pasó y fue hecho por IA! pic.twitter.com/ZeUAVFXoNK
— Juan Merodio (@juanmerodio) 18 juin 2025¿Un alien bebiendo cerveza en medio de la final de la NBA? ¡Sí, esto pasó y fue hecho por IA!
-
New V1 Video Model Launched at $10 Monthly for Everyone
By
–
Introducing our V1 Video Model. It's fun, easy, and beautiful. Available at 10$/month, it's the first video model for *everyone* and it's available now. pic.twitter.com/iBm0KAN8uy
— Midjourney (@midjourney) 18 juin 2025Introducing our V1 Model. It's fun, easy, and beautiful. Available at 10$/month, it's the first video model for *everyone* and it's available now.
-
AI Models Advancing Toward Real-Time Open-World Simulations
By
–
As you know, our focus for the past few years has been images. What you might not know, is that we believe the inevitable destination of this technology are models capable of real-time open-world simulations. What’s that? Basically; imagine an AI system that generates imagery in
-
Runway Chat Mode generates images and videos conversationally
By
–
Use Chat Mode to generate anything. From ideation to iteration, you can now generate both images and videos within a single conversational interface. Learn how in today's Runway Academy. pic.twitter.com/CxST9QwkVs
— Runway (@runwayml) 18 juin 2025Use Chat Mode to generate anything. From ideation to iteration, you can now generate both images and videos within a single conversational interface. Learn how in today's Runway Academy.
-
Magnific AI preserves structure; Kling animates speaking in 10 minutes
By
–
Of course you could generate a color version in ChatGPT, but Magnific AI does a great job at keeping the "structure" of an old image and overlaying a new style on top of it. Kling took 2-3 renditions before the speaking part made sense. But still this all took 10 minutes max.