#Image generation

AIAlibaba's Wan 3.0 ranks #1 overall on the new Artificial Analysis AA-Video-T2V v2.0 text-to-video leaderboard, priced at $12 per minute of video. The benchmark judges models at 1080p using over 68,000 human preference votes across 1,000 prompts, and the author states Wan 3.0 leads 10 of 20 category boards.

AIManus 2.0 introduces Video Editor, which lets users refine videos Manus generates, including changes to music, captions, and cut timing, without regenerating the entire video. The article describes Manus creating explainers, launch films, and animations from a single prompt, drawing on web search, video models such as Seedance 2.5, and code for motion graphics.

AILuma has launched Variants, which builds placement-ready versions of one approved static ad across five formats (Story 9:16, Portrait 4:5, Square 1:1, Medium Rectangle 6:5, Widescreen 16:9) and selected languages. Logos, headlines, and CTAs stay intact while layout and copy adapt to each placement and market. The first release covers static ads, resizing, and translation, and is available now from the Discover tab in Luma.

AILuma now offers Ideogram 4.5, an image edit model that gives creative teams more control over what changes and what stays. The post presents this as preserving the original work while opening new editing possibilities. Ideogram describes 4.5 as reducing artifacts, pixel shifts, and color changes across repeated edits.

AIReplicate has launched Ideogram 4.5 and Ideogram 4.5 Precise Edit, each with a dedicated model page for trying them. The post provides only the two links, so no further features, pricing, or benchmarks are stated.

AIReplicate now hosts Ideogram 4.5, an image model built for hyper-precise, multi-turn editing. It is aimed at editorial mockups, brand assets, and imagery without artifacts.

AIPika invites users to build with its models through a Pika API club, with a link to the developer portal. The post provides no model names, pricing, or feature details.

AIHiggsfield's full interface is now available inside Codex, powered by GPT-6.1 Sol, with access to local files and automation skills. The integration lets users automate creative workflows end-to-end within ChatGPT.

AIComfy API is now available to all users on a paid Comfy plan, letting them package a ComfyUI workflow with its custom nodes, LoRAs, models, and Python dependencies and deploy it as an autoscaling API endpoint. Builds capture the ComfyUI version and dependencies, and each immutable release gets its own URL, so the tested environment is the deployed one. Usage is billed separately, with GPU time charged by the second and storage prorated hourly.

Why it matters: The post explains how a ComfyUI workflow is packaged into immutable releases and deployed as an autoscaling endpoint, showing a path from local graph to production service.

AIIdeogram 4.5 was built for precise, targeted editing but also performs very well across general editing tasks. Design Arena ranks it 15th in Image Editing with an Elo of 1250, placing it in the same performance band as MAI-Image-2.6 and Gemini 3 Pro Image Preview. It is especially strong at typography edits, such as modifying text in infographics.

AIIdeogram has launched Ideogram 4.5, an image editing model that is now live in Ideogram, the API, and launch partners. Open weights are coming soon. The launch post says the model avoids artifact buildup and pixel shifts across repeated edits, making multi-turn editing possible.

AIKrea (@krea_ai) links to a page for Ideogram 4.5, an image model now accessible through its platform. The post provides no further details on capabilities, pricing, or availability.

AIIdeogram 4.5 is now available on Krea, and the post says it is built to handle repeated edits. The post states that repeated editing usually causes artifacts, pixel shifts, and color drift, which this model aims to solve.

AIIdeogram 4.5 changes only the parts of an image a user asks to edit, so repeated edits keep output quality intact. It is available now in Ideogram and through the API, which offers two endpoints: precise edit, where output matches the input size, and generate + edit.

AIIdeogram 4.5 comes in four quality modes, ranging from 0.8¢ to 22¢ per image, all at native 2K resolution. Available now on our launch partners: @superscale_ai @Picsart @cfabricacom @luminal_ai @arena @runware @florafaunaai @krea_ai @trymoda @LeonardoAi @runwayml @pika_labs @fal @ComfyUI @magnific @GammaApp @LumaLabsAI @DesignArena

AIIdeogram 4.5 turns a single room photo into a design canvas where furnishings, finishes, and palettes can be swapped one edit at a time. The room's architecture stays unchanged throughout the edits.

AIIdeogram 4.5 can edit stylized, complex text in place and translate it into other languages while keeping the original design intact. The company says it has long led in typography and text rendering, and 4.5 extends that strength to editing and translation.

AIIdeogram 4.5 lets users change one element at a time in AI-generated images while the product stays accurate. The post says this makes building a full campaign much easier.

AIIdeogram recommends restoring an old photo in stages: first remove scratches and damage, then add color, then enhance. The post says trying to fix everything in a single prompt rarely works, so multi-turn editing lets each edit be refined separately.

AIIdeogram can recolor a product or relight the whole scene, with shadows, reflections, and highlights updating to match. The composition stays identical after the edit.

AIIdeogram posted a side-by-side test of identical edits on Ideogram 4.5, GPT Image 2.5 Sunburst, Nano Banana Pro, and Nano Banana 2. The post claims GPT Image and Nano Banana outputs become unusable within a few edits, while Ideogram 4.5 remains clean across repeated edits.

AIIdeogram released Ideogram 4.5, which it calls the most precise edit model, claiming it avoids the artifacts, pixel shifts, and color changes that leading models add with each edit. The company says this eliminates artifact buildup and makes multi-turn editing possible. It is live in Ideogram, via the API, and with launch partners, with open weights promised soon.

AILuma introduces Ad Variants, a feature in Luma that produces multiple versions of a finished ad for different sizes and markets while keeping the same campaign. The post frames it as a way to extend an existing ad into localized formats without rebuilding each version.

AISenseTime previewed Dynamic Design, powered by SenseNova 6.8 Flash, which turns static images into animated visuals. The system decides which elements stay static and which to animate, chooses HTML/CSS, SVG, transparent images, or video for each element, and choreographs text reveals and subject motion. SenseNova 6.8 Flash is coming soon, and SenseTime is offering a limited beta.

AITencent Hunyuan announced a three-track creative challenge with three winners sharing prizes. Background from GMI Cloud says the Hy Image 3.5 preview is free there for seven days, supporting image generation and editing up to 2K with up to five reference images. The post also points to $1,800 in cash and credits for winners.

AIKling 4.0 is entering early access, with a wider rollout planned for October, and Kling 4.0 Flash opens to Ultra Yearly subscribers on September 28. The update generates videos up to 30 seconds in a single pass, accepts up to 15 reference assets, and supports up to 10 keyframe images. Upcoming features include 10-bit HDR output at 4K and 1080p and video extension up to 2 minutes.

Why it matters: The post specifies concrete capability limits such as 30-second native generation, up to 15 references, and 10 keyframes, which help users judge fit for production workflows.

AIGoogle Research has introduced Diffusion Controller, a lightweight steering damper that precisely guides image generation to improve prompt alignment. The post says it improves image quality while preserving baseline stability, with details available in the linked blog.

AIGoogle Research introduced Diffusion Controller, a framework that treats image generation as a continuous control problem rather than separate inference-time guidance and fine-tuning fixes. Its lightweight add-on "steering damper" network keeps the base model frozen and works on black-box or gray-box models, and it outperformed the industry standard on human preference matching. In a Stable Diffusion v1.4 test, the fully unlocked version achieved a 90% win rate over the baseline.

AIModelScope invites users experiencing problems with Qwen-Image-2.1 to submit feedback through an official form that connects them directly to the Qwen Image research team. Users are asked to share prompts, images, or workflows to help the team investigate and improve the model. Submissions in English or Chinese are welcome.

AIThe article presents a four-part prompt structure (action verb, target element, desired result, protection instructions) for AI photo editing, saying it preserves approved work across platforms. It identifies three common failure causes: unmatched light direction, stacked edits in one prompt, and vague visual language. It states that simple skin retouching takes 2-3 minutes versus 15-30 minutes manually.

AIKrea, an AI creative platform, has published a dedicated video page at The post provides only this link, so no features, models, pricing, or capabilities are confirmed.

AIKling AI released THE BEAT, a short film created with Kling 4.0 that follows a drummer's journey back to the stage. The post promotes the piece with the tagline "WATCH ME PLAY" and provides no further technical details.

AIModelScope released two Qwen-Image-2.1 LoRAs, LayerExtract and LayerRemove, for layer-based image editing. LayerExtract isolates a prompt-specified subject onto a transparent background, while LayerRemove deletes the matching object from the source image and reconstructs the scene behind it. Both can be hot-swapped within the same DiffSynth-Studio pipeline, and the LoRA weights are licensed under Apache 2.0, with Qwen-Image-2.1 base-model terms also applying.

AIKling AI's blog outlines a structured prompt method for basketball league logos, covering league identity, basketball symbol, style, colours, and composition. It provides six example prompts for professional, modern, youth, retro, minimal, and street styles, and shows how to generate concepts with Kling IMAGE 3.0 from text or reference images.

AIHailuo AI promoted a weekend cartoon post, and a quoted clip by @awesome_visuals, titled "the chef's revenge," was made with MiniMax H3 Max. The post offers no further details on the model's features or performance.

AIKrea published a post linking to presenting an agent-focused product page. The post itself provides no further details on features, models, pricing, or availability.

AIHiggsfield AI published an open-source breakdown of its "Passport Rush" project, including every prompt and asset used. The post links to the project page on higgsfield.ai for readers to explore the materials.

AIHiggsfield AI released "Passport Rush," described as the first hybrid AI-animated short made with a Blender and Higgsfield pipeline. The film combines handcrafted 2D storyboards and 3D Blender previs with AI animation. The project is now open source, with every prompt and asset publicly available.

AIAmazon Neuron Science and Reactor collaborated to optimize Rolling Forcing, an autoregressive diffusion video model, for real-time generation on AWS Trainium. The model generates 16 frames per second, the standard video playback rate, meeting latency requirements for streaming video generation.

AILuma Labs has launched a virtual model try-on app that users can access directly through its web platform. The post only links to the app and does not describe its features, models, or pricing.