Updated
Updated
Showing low-relevance items too. Hide low-relevance items
Nick Turley@nickaturleyAI score42AINick Turley of OpenAI reacted with a one-word "good!" to Arena's report that GPT-Image-2 ranked first across all Image Arena leaderboards. Arena cited a 1512 Text-to-Image score, a 242-point lead over the second-place Nano-banana-2 model.
Nick Turley@nickaturleyPickAI score67AINick Turley announced ChatGPT Images 2.0 as a major advance in image generation, citing better adherence to detailed instructions, rendering of dense text, and more accurate understanding of the world. He said the model can spend extra time planning and refining outputs for tasks needing more accuracy and clarity, and that users have generated over 1 billion images with ChatGPT.
Why it matters: The post names concrete gains in instruction following, dense text rendering, and optional extended thinking for image output, which helps readers gauge practical scope.
NVIDIA AI Developer@NVIDIAAIDevAI score39AIResearchers introduced a simple, sample-efficient online reinforcement learning technique for post-training image generation models. It is presented as a possible steerable alternative to classifier-free guidance (CFG) that can be driven by any scalar reward, including human preference.
AIStability AI has introduced Brand Studio, an end-to-end creative production platform for enterprise teams that builds around each brand's identity. Its Brand Central hub supports custom Brand ID models and Campaigns, while Producer Mode turns prompts into step-by-step production plans. Curated Model Routing selects models including Stable Diffusion, Nano Banana, and Seedream, and new Precision Inpainting and Product Insertion tools enable targeted edits.
AIBlack Forest Labs released FLUX.2 Small Decoder, a distilled VAE decoder that works as a drop-in replacement for the standard FLUX.2 decoder on Hugging Face. It decodes about 1.4x faster and uses about 1.4x less VRAM at decode time, with ~28M decoder parameters versus ~50M in the full decoder and minimal quality loss. It is available under the Apache 2.0 license and is compatible with FLUX.2-klein-4B, FLUX.2-klein-9B, FLUX.2-klein-9b-kv, and FLUX.2-dev.
Intern Large Models@intern_lmAI score47AIInternVL-U is a lightweight 4B unified multimodal model that combines reasoning, generation, and editing in one framework, according to Intern Large Models. The post says it uses unified contextual modeling, modality-specific modular design, and decoupled visual representations to balance performance and efficiency. It reportedly outperforms unified baselines more than 3× its size on text rendering, scientific reasoning, and spatially grounded generation and editing, and is open-source on GitHub and Hugging Face.
Nano Banana 2.1@NanoBananaAI score62AINano Banana 2, also called Gemini 3.1 Flash Image, adds visual grounding with Google Search, 512px resolutions, and extreme aspect ratios of 1:8 and 1:4. The guide advises using it as the default for new projects, with Nano Banana Pro reserved for complex prompts it fails, and keeping Thinking mode off by default.
AIBlack Forest Labs has released FLUX.2 [klein] 9B-KV, a variant of FLUX.2 [klein] 9B that caches reference-image key-value pairs to speed up multi-reference editing by up to 2.5 times. The 9B flow model, which uses an 8B Qwen3 text embedder and is step-distilled to 4 inference steps, is available for non-commercial use under the FLUX Non-Commercial License and fits in about 29GB VRAM.
Nano Banana 2.1@NanoBananaAI score18AIGoogle's Nano Banana account says users can turn anything into an enamel pin with Nano Banana 2, either by selecting the "Enamel pin" style in the Gemini app or by using a prompt. The example prompt asks for just the subject as a gold enamel pin shown as a minimal photo on a desk.
Nano Banana 2.1@NanoBananaAI score10AIGoogle's Nano Banana 2 is presented as the best model for a prompt that asks for a cute, nearly spherical animal with oversized eyes and no separate head, shown in its natural habitat. The example prompt specifies cartoonishly cute features with the eyes looking up cheekily.
Meta@MetaAI score27AIMeta is working with environmental survey teams to use its Segment Anything Model (SAM) to identify minute changes in water conditions in satellite images. The company hopes faster analysis will support rapid flood response and keep communities safer.
Oriol Vinyals@OriolVinyalsMLAI score60AINano Banana 2, officially released as Gemini 3.1 Flash Image Preview, ranks first in Image Arena text-to-image with a score of 1279. The quoted post says it also ties for first in single-image editing at 1407 and costs $0.067 per image, about half the price of Nano Banana Pro.
Nano Banana 2.1@NanoBananaPickAI score67AINano Banana announces Nano Banana 2, which it describes as its best image generation and editing model yet. The model can be tried in the Gemini app, Google AI Studio, and other places the post does not specify.
Why it matters: The post names the access points for Nano Banana 2, which helps readers see where the image generation and editing model can be tried.
Nano Banana 2.1@NanoBananaAI score10AINano Banana, the account linked to Google and Gemini, shares a prompt asking an image model to imagine the image as a simple cookie cutter and show the resulting unfrosted homemade cookies on a plate without showing the cutter. The post is a creative prompt example rather than an announcement of a new feature.
Nano Banana 2.1@NanoBananaAI score6AINano Banana, Google's Gemini image account, shares a prompt for a 9:16 wallpaper with negative space near the top and bottom, a subtle top-to-bottom gradient, no blur, and no cropping. The post advises keeping the scene simple and placing the subject and style at the end of the prompt, with example images attached.
Nano Banana 2.1@NanoBananaAI score14AINano Banana (@NanoBanana) posts a sample prompt showing how specific image-generation instructions can be, describing a San Francisco cafe scene with a couple by the window, a sleeping black-and-white French bulldog, and a mirrored "Nano's Cafe" gold lettering on the glass. The post offers the detailed prompt as an illustration of how far users can go with specificity, covering clothing, props, lighting, and poses.
Nano Banana 2.1@NanoBananaAI score18AINano Banana (@NanoBanana) suggests adding the word "risograph" to image prompts for a distinctive print effect. The example prompt asks for a 2x2 grid of icons on pure white with thick black outlines, stochastic stippling, and vibrant, unfaded color, here themed "cute but weird animals (that are real)."
AIBlack Forest Labs released FLUX.2 [klein] 4B, a 4 billion parameter model that unifies text-to-image generation and image editing with multi-reference support. The source says it runs on consumer GPUs such as the RTX 3090 or 4070 with about 13GB VRAM, and its open weights are available under the Apache 2.0 license.
Why it matters: The source specifies a 4 billion parameter model running on about 13GB VRAM under Apache 2.0, which helps readers judge whether local image generation fits their hardware.
AIBlack Forest Labs has published FLUX.2 [klein] 4B Base, a 4 billion parameter text-to-image model that also supports multi-reference editing. The model is undistilled, is released with open weights under Apache 2.0, and is described as fitting in about 13GB VRAM on cards such as the RTX 3090 or 4070, with reference code available in its GitHub repository and support in ComfyUI and Diffusers.
AIBlack Forest Labs has released FLUX.2 [klein] 9B Base, a 9 billion parameter undistilled rectified flow transformer with open weights for text-to-image generation and multi-reference editing. The model is intended for fine-tuning, LoRA training, and research, and fits in about 29GB VRAM on NVIDIA RTX 4090-class GPUs. A reference implementation is available on GitHub, and the model works with ComfyUI and Diffusers.
AIZ.ai has launched GLM-Image, an image generation model built on a multimodal architecture that combines autoregressive semantic understanding with diffusion-based decoding. The update improves knowledge-intensive generation and makes text rendering inside images more stable and accurate, suiting commercial design and educational illustrations.
Nano Banana 2.1@NanoBananaAI score12AINano Banana posts a prompt template for generating a 3x3 grid of colorful, tactile 3D icons on a white background with no text. The post lists example themes: dogs with different emotions, bananas, January, and the same cat in different emotions.
BAAI@BAAIBeijingAI score47AITsinghua AIR and BAAI's DrugCLIP screened 10,000 proteins against 500 million molecules, identifying over 2 million drug candidates. The post claims a 1-million-fold speedup, reaching 10 trillion protein-molecule pairs per day, and positions DrugCLIP as bridging AlphaFold structures to drug candidates. The work is published in Science, with a platform available at drugclip.com.
Nano Banana 2.1@NanoBananaAI score9AINano Banana, the official account for Google's image model, shows an example of converting a scene to nighttime from the prompt "Make it nighttime." The post provides only this prompt and no further details about the model version, output quality, or availability.
Nano Banana 2.1@NanoBananaAI score4AINano Banana, Google's Gemini image account, posts a sample prompt for a traditional Christmas card featuring a couple in Christmas hats. The prompt specifies the text "Happy Christmas 2025" and a classical, friendly design in a winter wonderland setting.
Nick Turley@nickaturleyAI score60AIOpenAI's new ChatGPT Images is rolling out in ChatGPT starting today. The update offers more precise edits, stronger instruction following, and up to 4x faster generation while preserving lighting, composition, and likeness across edits.
Nano Banana 2.1@NanoBananaAI score14AINano Banana, the account owned by Google and Gemini, thanks @Arminn_Ai for inspiring a post showing 3D miniature isometric room images made with Nano Banana Pro. The post says users can upload their own photo to generate a personalized chibi-style figure in a cube-shaped room and offers to share the full prompt on request.
Nano Banana 2.1@NanoBananaAI score24AINano Banana, the account of Google's Gemini team, shares a prompt template for generating cute isometric 3D cube diorama lamps. The prompt specifies internal lighting, chibi figurine styling, matte PVC material, a neutral background in a dark room, many small details, and subtle dust and scratch textures.
AIApple has released SHARP, a model that generates a 3D Gaussian representation of a scene from a single photograph in less than a second on a standard GPU. The output renders in real time as high-resolution photorealistic views of nearby camera positions, with metric absolute scale, and the paper reports reductions of 25–34% in LPIPS and 21–43% in DISTS versus the best prior model.
Nano Banana 2.1@NanoBananaAI score4AINano Banana, Google's image model account, shares a prompt for a photo of a miniature chocolate shaped like a cartoon image shown as an advent window backdrop. The chocolate is held after being taken from a chocolate advent calendar.
Quoc Le@quocleixAI score34AIQuoc Le says Nano Banana Pro's text understanding is impressive, showing an infographic it created for the sequence-to-sequence paper from a single request. The post includes the generated image as its main evidence, with no figures on speed, pricing, or benchmarks.
ByteDance@BytedanceTalkAI score26AIByteDance's R&D team created the technology behind TikTok's "Cartoonify" sticker in just 48 hours during its annual Hackathon. The augmented reality effect makes physical objects on screen dance, cry, sing, and perform other actions.
