#Image generation

AIKrea Agent is now available inside After Effects, where it can create motion graphics, resize videos, and handle sound and images. The post says it can be tried for free.

AIHiggsfield AI promotes Genjutsu, a tool for creating AI influencer videos from your own face or from scratch and joining viral trends. Users can try up to 5 generations free, and the tool is available in Higgsfield and through a ChatGPT Extension.

AIHiggsfield AI promotes its AI Influencer Studio, inviting users to create a viral AI influencer for free. The post links to the studio at but gives no details on features, models, or limits.

AIVibe coding, paw edition. 🐶 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗲𝘀𝗶𝗴𝗻, 𝗽𝗼𝘄𝗲𝗿𝗲𝗱 𝗯𝘆 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝟲.𝟴 𝗙𝗹𝗮𝘀𝗵 𝗣𝗿𝗲𝘃𝗶𝗲𝘄, 𝗯𝗿𝗶𝗻𝗴𝘀 𝘀𝘁𝗮𝘁𝗶𝗰 𝗶𝗺𝗮𝗴𝗲𝘀 𝘁𝗼 𝗹𝗶𝗳𝗲.

AIAI image models default to attractive women because training data, averaged-face aesthetics, and user preference feedback reinforce one another. A 1973 test image from Playboy, later widely used in image processing, shows how such defaults form early. Reward models trained on user choices can increase NSFW output even when prompts are unrelated.

AINVIDIA's Bryan Catanzaro says players testing DLSS 5 show that neural rendering has redefined real-time graphics, calling it the payoff of ten years of dedicated research and development. He frames the change as "5 years of graphics progress in one toggle," linking to a video demonstration.

AIPixVerse says users can describe a character to their AI agent and use the PixVerse plugin to generate a full design sheet. The post provides no further details on features, pricing, or availability.

AIKling AI announced Kling 4 with a short social media post titled "Thoughts in motion" and hashtags #Kling4 and #KlingAI. The post contains no specifications, benchmarks, pricing, or release details.

AIfal brought the generative media community together at its GenMedia Conference 2026 in San Francisco last week. Sessions revisited Pixar's early days and discussed how AI could lower filmmaking costs while keeping people in creative control.

AIPika announced its new platform on X, directing users to a dev.pika.art page to start creating. The post gives no specific features, models, pricing, or release details beyond this invitation.

AIPika has redesigned its video creation experience, offering Video Studio for creators who want to focus on craft and direct generation through specific models for those with model preferences. A creator notes that Seedance on the platform costs about half of what they pay elsewhere, with no locked top-tier model behind a higher plan.

AIMiniMax Design now offers Opus 5.5, which its account presents as a new way to create from code to motion. The post provides no further details on features, pricing, or availability.

AIHiggsfield AI is promoting its AI Influencer Studio, letting users try the tool with up to five free generations. The post links to the studio page but provides no details on features, models, or pricing.

AIHiggsfield AI has introduced AI Influencer, a tool for creating your own AI influencer and inserting them into any trend. Users can try it with up to 5 free generations on Higgsfield and in the ChatGPT extension, and the post says it is powered by Genjutsu.

AIxAI has released an experimental TypeScript SDK, installable via npm install @xai-official/sdk, that covers text, voice, image, and video in one package. It provides access to the latest Grok models along with server-side tools including real-time X search, web search, code execution, and remote MCP.

AISuno's account posted a link to a song on suno.com, writing "ngl we nailed it too." A replying user praised the track's dramatic pauses, though the post gives no model version, benchmark, or other concrete figures.

AIExplore viral presets

AIPixVerse is promoting unlimited use of GPT-Image 2.5 for turning cities into museum gift shop-style products, with the post describing this as the last day of the offer. The post provides no further details on pricing, duration, or terms.

AIThe team at @thesystms built a creative agent in 48 hours, and @ingi_erlingsson documented how he reads a moodboard, starting with feeling, then color, tone, and camera. @armandgw turned that process into a Krea Agent skill.

AIA quiet landscape, gently in motion. 🌿💧❄️ With Dynamic Design powered by SenseNova 6.8 Flash Preview, Xiaohongshu creator @Muzlz8888 (Mr.木子李子) sets the sand swirling, the stream flowing, the ducks moving and the snow drifting — while keeping the buildings still. From a static image to a scene with rhythm. ✨

AIKling 4.0 is in closed beta, with an official launch planned for October, and supports video up to 30 seconds long with up to 4K resolution and 10-bit HDR output. Creator Johnson Sheng reports stable dynamic motion, consistent characters and props across shots, and an unedited 30-second fight sequence, while noting that Kling 4.0 is aimed at commercial production.

AIIdeogram praised photographers for their craft and said it hopes to help them save hours of work. The post contains no concrete product features, model names, or figures, and it does not specify what kind of editing help is offered.

AIMidjourney's alpha site now shows style previews in the sidebar before generation, enlarges images in Create, and lets users save default parameters per folder. This week's update focuses on bug fixes and cleanup, with new collaborative tools planned for next week.

AINVIDIA has released PixelUMM, an encoder-free unified multimodal model with 15,199,672,064 parameters that handles text, image, and video understanding and generation directly in pixel space. It represents images as 16-by-16 RGB pixel patches on a Qwen3-8B language backbone, with iterative denoising for generation. The checkpoint is licensed for non-commercial research or evaluation only, while the source code is under Apache License 2.0.

AIKrea (@krea_ai) shared a link to a page for an image model it refers to as "bfl-3-image." The post gives no further details on capabilities, pricing, or release terms.

AIKrea has made FLUX 3 Image available on its platform. The model supports multi-turn edits that leave all other pixels unchanged, layout via bounding boxes, generation up to 4K, and composition with up to 10 references.

AIHiggsfield AI has made FLUX 3 Image available to try on its platform, linking directly to its image generation page with the flux-3-image model selected. The post provides no details on capabilities, pricing, or benchmarks.

AIHiggsfield has launched FLUX 3 Image, a new Black Forest Labs image model, now available on its platform. The model lets users edit a single detail without altering the rest of the image, place objects using bounding boxes, combine up to 10 reference images, and generate output at up to 4K resolution.

AIBlack Forest Labs has released FLUX 3 Image, which generates native 4K images and supports hyper-specific layouts using bounding boxes. It can make multiple targeted edits at once while staying consistent across them, and up to 10 references can be used to compose an image. The first week is 50% off, and an open-weights version is coming in the coming weeks.

AIReplicate has made Black Forest Labs' flux-3-image model available to try through a link to its platform. The post provides no further details on capabilities, pricing, or performance.

AIPika's app can convert any product image, including one taken on a phone, into a ready-made ad spot. A quoted post from @Gemalpha_88 shows a single product shot turned into a full cinematic ad using New Pika.

AIPika has released a set of new creation apps on its updated platform at pika.art. The post itself gives no further details about the apps' features or capabilities.

AIPika has launched Color Grade, a creative editing feature that applies a chosen tonality to any image or clip. It is normally used to adjust color footage but can also colorize black-and-white content.

AIPika has launched a new AI creative platform offering more than 40 apps covering needs from finishing edits to full video ads. The company describes the product as built for creatives and designed to meet exacting output standards.

AIEmber-1, built on the Kimi K3 base model, is reported by @kickingkeys to cost about 20% less and use about 36% fewer reasoning tokens across 124 test prompts. The same tester says it runs about 2x faster, while the source's painting examples show its own expressive style.

AIRunway says its system can expand any media into an interactive, real-time world simulation. The post presents this as turning fixed experiences into immersive multimodal simulations for both people and agents.

AIRunway describes Portals as visual elements with soft, dream-like edges that mark where generated content begins. Users can drag a Portal onto the page, where it sits alongside their content.

AICute in any time zone. 🐼 🎬 Dynamic Design, powered by SenseNova 6.8 Flash Preview, brings static images to life.