You might find if you have two people / things in one image you can prompt them both into the other. Some people are pasting/appending/concatonating two images side by side and also having luck with that.
MULTIMODAL AI
-
Omni-Reference: AI Image Generation with Custom References
By
–
**What is Omni-Reference?**
– Omni-reference can be best thought of as a system of saying “put THIS in my image”. – It can work for characters, objects, vehicles, or non-human creatures
– Omni-reference works with personalization, stylization, style references, and moodboards -
Omni-Reference launches AI image generation with custom reference control
By
–
Omni-Reference is now live! It's a new way to say "put THIS in my image" for characters, objects, vehicles, and more. Check out the examples or see the full info dump below
-
Google Unveils Multimodal AMIE Diagnostic AI Agent
By
–
Building on Articulate Medical Intelligence Explorer — AMIE, our research diagnostic conversational AI agent — today on the blog we share a first of its kind demonstration of a multimodal conversational diagnostic AI agent, multimodal AMIE. Learn more →
https://
goo.gle/42D0QcB -
Meta SAM 2.1 Powers Cutouts Feature in New Edits App
By
–
Curious about the tech behind Edits? Our latest blog post explores how Meta Segment Anything Model (SAM) 2.1 is enabling the Cutouts feature in the new Edits app. Learn more:
-
Real-time img2img diffusion and AR image models development
By
–
Anyone working on real-time img2img diffusion/AR img models? Have an idea…
-
Full-Body Character Generation in Novel Locations from Reference
By
–
Example: Generating full-body character images in novel locations from a single, limited character reference.
— Runway (@runwayml) 1 mai 2025
(4/5) pic.twitter.com/N85jndRAJIExample: Generating full-body character images in novel locations from a single, limited character reference. (4/5)
-
Gen-4 References: Consistent Character and World Generation Tool
By
–
Gen-4 References is a powerful tool for exploring consistent characters, worlds and ideas. With as little as one image, you can generate novel content of just about anything. Below are a few examples of how to do so by combining images with conversational prompting.
— Runway (@runwayml) 1 mai 2025
Example: A… pic.twitter.com/FgxqlrzpESGen-4 References is a powerful tool for exploring consistent characters, worlds and ideas. With as little as one image, you can generate novel content of just about anything. Below are a few examples of how to do so by combining images with conversational prompting. Example: A
-
AI References Transform Old Photos Into New Locations
By
–
Example: Using References with an old photograph to transport its subjects into new locations.
— Runway (@runwayml) 1 mai 2025
(2/5) pic.twitter.com/MqReHMwTs2Example: Using References with an old photograph to transport its subjects into new locations. (2/5)
-
Google Launches Gemini 2.5 Flash with Hybrid Reasoning
By
–
New: Gemini 2.5 Flash! Google DeepMind's latest model has hybrid reasoning capabilities, along with a 1m token context window, multimodal input support, and native search, all while prioritizing speed and cost. (1/2)