Black Forest Labs released FLUX 3 Image Klein, a 5.6B-parameter open-weights model supporting text-to-image, image editing, up to ten reference images, native 4K output and pixel-level editing.
Black Forest Labs has released FLUX.3 Image Klein, an image model whose open-source distilled and base checkpoints are now on Hugging Face and available in Diffusers on day one.
Why it matters: The release notes are documentation-style, with usage code, measured VRAM and speed, and an architecture breakdown, letting readers assess deployment cost and workflow migration.
Security research firm White Circle has proposed an attack method called RISE in a preprint paper, using an off-the-shelf downloadable Qwen model as attacker and Gemini 3.8 Flash as judge, bypassing the safety filters of DALL·E 3, Google Nano Banana 2 and GPT-Image-2 via API calls, with about 13% of requests successfully generating explicit content.
Simon Willison added support for the Gemini 4 Argon model to his llm-gemini plugin, available today via the Gemini API and a $100/month subscription plan, and generated low, medium and high-tier pelican SVG examples, with the high tier costing 17.166 cents.
Mia Goth's representatives told The Verge that the verified fan account miagoth_ spread AI-generated fake images of her wearing a printed T-shirt, which were widely reported as real. The account has over a million followers and removal requests went unheeded. Meta's rules do not require static AI images to be labeled, and by Tuesday morning the account appeared to have been emptied.
According to Bloomberg, Epic Games plans to use AI to generate code and art for an unannounced Disney shooter, which has been delayed from its original March release window. Development teams are being asked to use tools like Anthropic's Claude more; one director said code is no longer hand-written, and all art will be produced with full AI workflows.
According to Bloomberg, Epic Games is moving to AI-first development in its partnership with Walt Disney, with models such as Anthropic's Claude writing all code and generating all art assets, while human developers manage and steer the work.
Nikon disqualified the original first-place video in its Small World in Motion competition for not complying with the contest rules on generative AI. The video, by Dr. Ning Xu, claimed to show cilia moving in the airway of a child with PCD; after questions were raised online about its authenticity, Dr. Xu acknowledged on LinkedIn using AI-assisted post-processing to distinguish and visualize reconstructed features in grayscale images.
Because the Hub only had a compressed version of the official 9B prompt rewriter for Qwen-Image 2.1, the author used HuggingChat's ML-intern mode to build a 0.8B student version that runs on CPU.
Why it matters: The author shares seven complete projects offering a reusable workflow covering prompt structure, budget control, baselines and smoke tests, with all prompts and itemized compute costs included.
Pollo AI uses GPT-5.6, GPT-6 Astra and GPT-Image-2.5 to help creators turn bold ideas into polished images and cinematic video ads.
Developer Thomas, with about a decade of Rust project experience, has launched open source clones of Adobe Premiere and Photoshop (Filmcraft and more), offered free under MIT/Apache licenses.
Google has released Nano Banana 2.1, an image generation and editing model that succeeds Nano Banana 2 (released in February 2026), at roughly half the price: 1K images drop from 6.70 cents to 3.36 cents, and 4K from 15.10 to 7.56 cents.
Simon Willison tested Mistral Large 4 with an SVG generation prompt about an armadillo in fishnet stockings jaywalking on Mars, comparing its output with claude-opus-5.5, gpt-6.1-sol, and gemini-3.8-flash, with each model using its default reasoning level.
AI ad creative platform Melius announced on Tuesday a total of $25 million in funding, including a $20 million Series A led by CRV and a $5 million seed round led by General Catalyst. Founded by three former Ramp engineers, the company pivoted to a "creative work agent lab" that generates ad assets and campaigns after abandoning its original AI marketing tool and rewriting its entire codebase, and says it topped $1 million in annualized revenue within two months of stealth exit in July.
Black Forest Labs has released Flux 3 Image, the image-side model of the Flux 3 family, claiming support for multi-step editing that leaves the rest of a picture untouched, covering text-to-image, image-to-image, text rendering, and photorealistic output.
Ideogram released its new model Ideogram 4.5, claiming it modifies only the image regions a user specifies while leaving the rest unchanged, addressing the artifact problem after repeated edits. The model offers four quality tiers costing 0.8 to 22 cents per image, with native 2K resolution, and is live on the Ideogram platform and API. Partners include Picsart, Runway, Pika and Leonardo AI, and the company says an open-weights version is coming soon.
Google Research introduced the Diffusion Controller framework, which reframes the denoising process as a continuous control problem, using a lightweight "steering damper" network to guide image generation without touching the main model's weights. In experiments based on Stable Diffusion v1.4, its fully unlocked version achieved a 90% win rate over the baseline on the Human Preference Score (HPS-v2) benchmark, and supports black-box/gray-box control of closed-source models.
An AWS machine learning blog tutorial shows how to deploy two endpoints on Amazon SageMaker AI using the same vLLM-Omni DLC: a real-time endpoint running FLUX.2-klein-4B for image generation and an asynchronous endpoint running Wan2.1-VACE-1.3B for image-conditioned video generation.
Hugging Face released Workflow1111, rebuilding AUTOMATIC1111's main features as a single Gradio Workflow canvas with 11 media pipelines and 73 nodes, covering text-to-image, hi-res fix, img2img, prompt matrix, VLM interrogation, detection-generated inpaint masks, ControlNet-style preprocessors, background removal, PNG Info, and image-to-video.
OpenAI released ChatGPT Images 2.5, which turns ideas, sketches, and reference photos into more personalized, more polished images that better fit the user’s creative intent.
Hugging Face announced that Diffusers now natively supports Nunchaku's SVDQuant 4-bit diffusion model inference, and via the new Nunchaku Lite integration path pre-quantized checkpoints can be loaded with from_pretrained() without local CUDA compilation.
Why it matters: The article shares measured latency and memory figures for W4A4 quantization with native loading in Diffusers, helping readers assess a viable path to running large models on consumer GPUs.
A Google Research paper published at ICLR 2026, "On the Interpolation Effect of Score Smoothing in Diffusion Models," explains that score smoothing makes generation interpolate between training data, shedding light on where diffusion models' creativity comes from.
Hugging Face details the data pipeline for its PRX image generation model: mixing public and internal datasets for pretraining, using a VLM to regenerate long captions, then converting them into streamable training data. The text encoder has been switched to Qwen3-VL, with text latents computed online during training at a throughput cost of only about 3–4%. Images are uniformly encoded as JPEG quality 92, and the data is built with Lance and streamed for training via MDS (Mosaic Streaming).
Google DeepMind released Nano Banana 2 Lite (gemini-3.1-flash-lite-image), the fastest and most cost-efficient image model in the family.
Why it matters: The article gives the speed, pricing, and access points for both models, and explains their positioning and API limits, helping developers assess whether to replace existing workflows.
Google announced that a 3D scene understanding-based photo recomposition method is now rolling out to the Auto frame feature in Google Photos.