Creative Agents

Agentic image/video/design generation

10 articles

All Agent Harnesses Tools & MCP Multi-Agent Systems Creative Agents Memory & Planning Safety & Evals RL for Agents AI & ML

Viewgrid list compact

Creative Agents

Identity preservation remains a distinct challenge for generative image models

The authors systematically benchmark three approaches to identity preservation in generative image models: encoding identity in the input context, using trainable subject-specific parameters (like LoRA), or maintaining a persistent identity layer. Their results show that persistent identity layers consistently reduce identity degradation across iterative edits, small subject scales, and multi-subject compositions, while preserving image quality and instruction adherence.

7 Sept·2 min

Creative Agents

Image-only pretraining helps build a strong open image generator

The authors trained a 6B diffusion transformer from scratch, first using image-only pretraining and mid-training to establish a visual generative prior before relying more heavily on image-text supervision. They report leading Qwen-Image-Bench scores among open-source models in both English and Chinese, and release the model weights, code, and training recipes.

6 Sept·2 min

Creative Agents

Coding agents combine generated imagery with editable web-based visual layouts

Ye and colleagues present Editable Visual Design, a system for producing visual designs that remain structurally editable rather than being flattened into a single image. The agent generates isolated visual assets, assembles them with native HTML/CSS, and revises the result using feedback from rendered previews; the authors report successful applications to posters, infographics, and related formats.

5 Sept·2 min

Creative Agents

Language enables precise character and camera control in video worlds

Chen et al. turn MiniMax-H3 into an interactive world model by expressing actions as paired character and camera instructions aligned with video time steps. Their lightweight adaptation uses 8,000 gameplay samples and updates 0.199% of the model’s parameters while retaining generation quality and extending control to unseen scenarios.

3 Sept·2 min

Creative Agents

Temperature-controlled preference updates reduce manifold drift in flow models

Han et al. analyze preference optimization for flow-matching generative models, showing that reward-driven updates can push outputs away from the pretrained data manifold when the induced displacement has a component normal to that manifold. Their proposed ThermoDPO-weighted objective improves both a toy benchmark and text-rendering metrics for Stable Diffusion 3.5 Medium.

23 Aug·2 min

Creative Agents

Explicit identity-layout planning improves group images with specified people

Xu et al. developed a group-image generation framework that represents each requested person with an addressed identity token, predicts an identity–layout plan, and uses that plan to guide synthesis. On an identity-disjoint benchmark, the method improved face similarity over GPT-Image-2 while covering 97.3% of requested identities with a 2.8% duplicate rate.

23 Aug·2 min

Creative Agents

Hybrid attention enables high-quality video generation on a single GPU

The authors introduce SANA-Video 2.0, a video diffusion transformer that uses a hybrid of linear and softmax attention to achieve efficient long-sequence processing. The model, scaled to 5B and 14B parameters, generates 720p video on a single H100 GPU and achieves a VBench score of 84.30 at 480p in 13.2 seconds, matching the quality of larger softmax-based models while being significantly faster.

24 July·2 min

Creative Agents

An agentic framework that fills in missing context for real-world image generation

The authors propose Qwen-Image-Agent to address the context gap where user requests for image generation are often underspecified, implicit, or depend on up-to-date knowledge. The framework uses Context-Aware Planning to identify missing details and Context Grounding to acquire them from reasoning, search, memory, and feedback. On the newly introduced IA-Bench benchmark and two other datasets, it achieves state-of-the-art performance against strong baselines.

25 June·2 min

Creative Agents

Code-driven agents generate images via sketching and texturing stages

The authors propose GenClaw, an agentic image generation framework that breaks generation into three stages: conceptualization, code-based sketching (e.g., SVG, HTML, Three.js), and final texturing via an image model. This replaces black-box prompt rewriting with explicit, editable code intermediates, enabling precise control and interpretability.

29 May·2 min

Creative Agents

Unified visual-generation agentic model outperforms larger closed-source models

The authors propose VisionCreator, a native visual-generation agentic model that unifies Understanding, Thinking, Planning, and Creation (UTPC) capabilities. End-to-end trained on a new dataset and optimized via Progressive Specialization Training and Virtual Reinforcement Learning, VisionCreator-8B/32B models outperform larger closed-source models on the new VisGenBench benchmark across multiple dimensions.

3 Mar·2 min