The rapid progress in generative models has resulted in impressive leaps in generation quality, blurring the lines between synthetic and real data. Web-scale datasets are now prone to the inevitable contamination by synthetic data, directly impacting the training of future generated models. Already, some theoretical results on self-consuming generative models (a.k.a., iterative retraining) have emerged in the literature, showcasing that either model collapse or stability could be possible depending on the fraction of generated data used at each retraining step. However, in practice, synthetic data is often subject to human feedback and curated by users before being used and uploaded online. For instance, many interfaces of popular text-to-image generative models, such as Stable Diffusion or Midjourney, produce several variations of an image for a given query which can eventually be curated by the users. In this paper, we theoretically study the impact of data curation on iterated retraining of generative models and show that it can be seen as an implicit preference optimization mechanism.

Disney and OpenAI have made a surprise deal - what happens next? Disney's famous Mickey Mouse character will soon be available for use in AI-generated videos The world's best-known AI company and the world's best-known entertainment firm have come to a surprise agreement to allow AI versions of some of the most iconic characters in film, TV and cartoons to be used in generative AI videos and images. Social media is dead - here's what comes next The Walt Disney Company has signed a deal with OpenAI that will allow the AI firm's Sora video generation tool and ChatGPT image creator to use more than 200 of Disney's most iconic characters. Meanwhile, Disney remains in dispute with another AI firm, Midjourney, over alleged infringement of their intellectual property (IP), claiming Midjourney aims to "blatantly incorporate and copy Disney's and Universal's famous characters" into their image generating tool. The characters now deemed fair game for OpenAI users include the likes of Mickey and Minnie Mouse, Simba and Mufasa from and Moana, as well as Marvel and Lucasfilm characters, including some of's most well-known names.

The three years since the release of ChatGPT, OpenAI's generative AI chatbot, have seen huge changes in every part of our lives. Social media is dead - here's what comes next The most high-profile case was filed by Disney and Universal in June, both of whom alleged in a lawsuit that AI image generator Midjourney had been trained on their intellectual property, allowing users to create images that "blatantly incorporate and copy Disney's and Universal's famous characters". The latest on what's new in science and why it matters each day. In October, the Japanese government formally asked OpenAI, the company behind the Sora 2 AI video generator, to respect the intellectual property rights of its culture, including manga and popular video games such as those published by Nintendo. Sora 2 has faced further controversy due to its ability to create lifelike footage of real people.

Text-to-image (T2I) models have been widely applied in generating high-fidelity images across various domains. However, these models may also be abused to produce Not-Safe-for-Work (NSFW) content via jailbreak attacks. Existing jailbreak methods primarily manipulate the textual prompt, leaving potential vulnerabilities in image-based inputs largely unexplored. Moreover, text-based methods face challenges in bypassing the model's safety filters. In response to these limitations, we propose the Multimodal Prompt Decoupling Attack (MPDA), which utilizes image modality to separate the harmful semantic components of the original unsafe prompt. MPDA follows three core steps: firstly, a large language model (LLM) decouples unsafe prompts into pseudo-safe prompts and harmful prompts. The former are seemingly harmless sub-prompts that can bypass filters, while the latter are sub-prompts with unsafe semantics that trigger filters. Subsequently, the LLM rewrites the harmful prompts into natural adversarial prompts to bypass safety filters, which guide the T2I model to modify the base image into an NSFW output. Finally, to ensure semantic consistency between the generated NSFW images and the original unsafe prompts, the visual language model generates image captions, providing a new pathway to guide the LLM in iterative rewriting and refining the generated content.

While recent advancements in deep neural networks (DNNs) have substantially enhanced visual AI's capabilities, the challenge of inadequate data diversity and volume remains, particularly in construction domain. This study presents a novel image synthesis methodology tailored for construction worker detection, leveraging the generative-AI platform Midjourney. The approach entails generating a collection of 12,000 synthetic images by formulating 3000 different prompts, with an emphasis on image realism and diversity. These images, after manual labeling, serve as a dataset for DNN training. Evaluation on a real construction image dataset yielded promising results, with the model attaining average precisions (APs) of 0.937 and 0.642 at intersection-over-union (IoU) thresholds of 0.5 and 0.5 to 0.95, respectively. Notably, the model demonstrated near-perfect performance on the synthetic dataset, achieving APs of 0.994 and 0.919 at the two mentioned thresholds. These findings reveal both the potential and weakness of generative AI in addressing DNN training data scarcity.

It's been a busy month for Midjourney. This week, the generative AI startup released its sophisticated new video tool, V1, which lets users make short animated clips from images they generate or upload. The current version of Midjourney's AI video tool requires an image as a starting point; generating videos using text-only prompts is not supported. Midjourney did not immediately respond to requests for comment. Disney and Universal reiterated statements made by its executives about the lawsuit, including Disney's legal head Horacio Gutierrez alleging that Midjourney's output amounts to "piracy."

Yangliuqing woodblock prints, a cornerstone of China's intangible cultural heritage, are celebrated for their intricate designs and vibrant colors. However, preserving these traditional art forms while fostering innovation presents significant challenges. This study explores the DeepSeek + MidJourney approach to generating creative, themed Yangliuqing woodblock prints focused on the fight against COVID-19 and depicting joyous winners. Using Fréchet Inception Distance (FID) scores for evaluation, the method that combined DeepSeek-generated thematic prompts, MidJourney-generated thematic images, original Yangliuqing prints, and DeepSeek-generated key prompts in MidJourney-generated outputs achieved the lowest mean FID score (150.2) with minimal variability (σ = 4.9). Additionally, feedback from 62 participants, collected via questionnaires, confirmed that this hybrid approach produced the most representative results. Moreover, the questionnaire data revealed that participants demonstrated the highest willingness to promote traditional culture and the strongest interest in consuming the AI-generated images produced through this method. These findings underscore the effectiveness of an innovative approach that seamlessly blends traditional artistic elements with modern AI-driven creativity, ensuring both cultural preservation and contemporary relevance.

The Minions pose during the world premiere of the film "Despicable Me 4" in New York City, June 9, 2024. The website of Midjourney, an artificial intelligence (AI) capable of creating AI art, is seen on a smartphone on April 3, 2023, in Berlin, Germany. 'PIRACY IS PIRACY': Two major Hollywood studios are suing Midjourney, a popular AI image generator, over its use and distribution of intellectual property. AI RACE: Meta CEO Mark Zuckerberg is reportedly building a team of experts to develop artificial general intelligence (AGI) that can meet or exceed human capabilities. TECH HUB: New York is poised to play a central role in the development of artificial intelligence (AI), OpenAI executives told key business and civic leaders on Tuesday.

Midjourney's tool, which creates images from text prompts, has 20 million users on its Discord server, where users type their inputs. In the lawsuit, the two movie-making giants share examples in which Midjourney is able to create images that uncannily resemble characters each company owns the rights to, such as the Minions, controlled by Universal, or the Lion King, owned by Disney. They also say Midjourney "ignored" their attempts to remediate the issue prior to taking legal action. Midjourney did not immediately respond to New Scientist's request for comment. The lawsuit has been welcomed by Ed Newton-Rex at Fairly Trained, a non-profit organisation that promotes fairer training practices for AI companies.

Disney and Universal have filed a lawsuit against Midjourney, alleging that the San Francisco–based AI image generation startup is a "bottomless pit of plagiarism" that generates "endless unauthorized copies" of the studios' work. The complaint includes dozens of images that purportedly demonstrate how Midjourney can conjure images featuring the studios' intellectual property. One image depicts Yoda from Star Wars holding a light saber, which it says was made by inputting the prompt "Yoda with lightsaber, IMAX." Another shows that typing "The Boss Baby" as a prompt allegedly resulted in an image of an animated child in a tuxedo closely resembling the protagonist of Universal's The Boss Baby franchise. "This is an extremely significant development," says IP lawyer Chad Hummel, who sees the compilation of images in the complaint as compelling evidence that "the output is not sufficiently transformative."