Skip to content
K = 0.731
2026.10.17 · Sat

#图像生成

#图像生成

Today10/17Sat
  1. vLLM · X77

    MOSS-Image goes open source with bilingual text rendering and experimental layout control

    MosiAI announced the open-source release of MOSS-Image, built on a 5B Diffusion Transformer (DiT), with Chinese and English text rendering, up to 4K-token prompts, and experimental JSON layout control using bounding boxes. Base and SFT checkpoints are available on Hugging Face, alongside open model weights and Apache-2.0 licensed inference code. vLLM congratulated the team and announced Day-0 support through vLLM-Omni.

    Why it matters: The release provides a concrete example of combining bilingual text rendering with experimental bounding box layout control, giving developers a reference for image generation workflows that require explicit text and object placement.

10/16Fri
  1. The Decoder78

    Black Forest Labs releases FLUX 3 Image Klein with 8 GB VRAM support

    Black Forest Labs has released FLUX 3 Image Klein, a 5.6-billion-parameter open-weights model for text-to-image generation, image editing, and generation with up to ten reference images. It supports native 4K output, and its INT8 build runs on NVIDIA GPUs with 8 GB of VRAM, generating an image in under 9 seconds on an RTX 4070. The FLUX Kommunity License allows free commercial use for companies making under $5 million annually.

    Why it matters: The hardware requirements and commercial license threshold provide concrete context for assessing whether local image generation fits a team's available GPUs and business size.

10/15Thu
  1. Hugging Face Blog79

    Welcome FLUX.3 Image Klein in Diffusers

    Black Forest Labs’ FLUX.3 Image Klein launches with day-one Diffusers support for text-to-image generation, multi-reference image-to-image generation, and bounding-box layout control. Open checkpoints include a distilled model using 16 steps without CFG and a base model using 50 steps with CFG; the distilled model generated a 1024 × 1024 image in 1.93 s on an H100 in the reported benchmark. Hugging Face provides quantized loading examples, LoRA training scripts, and workflows for customizing its Modular Diffusers pipeline.

    Why it matters: The runtime measurements and quantization guidance help developers assess hardware requirements, including how reference images increase generation time and when lower precision reduces memory without improving speed.

10/11Sun
  1. 量子位78

    Google releases Nano Banana 2.1 image model with 4K output

    Google released Nano Banana 2.1, an upgraded image generation model with 4K output, mask-based editing and improved subject consistency. According to Arena, it gained about 61.7 points on average across text-to-image, multi-image editing and single-image editing, and Google halved API prices for 1K and 2K images while cutting 4K by about 25%. It is available in the Gemini app and Google AI Studio, with 50 free credits daily.

    Why it matters: The piece rounds up Arena ranking gains, API price cuts and early user tests of Nano Banana 2.1, including reported watermark and repeated-edit issues.

10/9Fri
  1. Qwen · X65

    Qwen releases Qwen-Image-2.1-Turbo, generating and editing images with 8-step denoising and open weights

    Qwen has released Qwen-Image-2.1-Turbo, based on the same 7B visual generation architecture as Qwen-Image-2.1, requiring only 8 denoising steps to generate and edit images, with weights now open on ModelScope and Hugging Face.

    Why it matters: Qwen's image model gains a Turbo accelerated version, with 8-step sampling and open weights offering a generation and editing path that can be integrated directly.

10/2Fri
  1. The Decoder78

    Black Forest Labs releases Flux 3 Image with multi-step editing

    Black Forest Labs released Flux 3 Image, an image model in the Flux 3 family. The company says it supports multi-step editing without changing other parts of an image and covers text-to-image, image-to-image, text rendering, and photorealistic generation.

    Why it matters: Flux 3 Image combines multi-step editing with 4K output and a reference-image limit, allowing comparison with Ideogram 4.5 on the pace of competition in image-editing models.

9/10Thu
9/8Tue
  1. OpenAI News60

    OpenAI releases ChatGPT Images 2.5

    OpenAI has released ChatGPT Images 2.5, which turns ideas, sketches, and reference photos into more personalized, polished images that better match what users had in mind.

    Why it matters: OpenAI's official launch of ChatGPT Images 2.5 gives readers an update on its positioning and input options for personalized image generation.

7/23Thu
  1. Hugging Face Blog62

    Diffusers adds native support for Nunchaku 4-bit diffusion inference

    Hugging Face has added Nunchaku Lite to Diffusers, allowing users to load Nunchaku SVDQuant 4-bit checkpoints directly with `from_pretrained()` without a custom pipeline or local CUDA compilation.

    Why it matters: The article reports how to load Nunchaku Lite in Diffusers, along with VRAM and latency comparisons, helping readers assess the practical requirements for running diffusion models on consumer GPUs.

7/1Wed
  1. Google DeepMind78

    Google DeepMind releases Nano Banana 2 Lite and Gemini Omni Flash

    Google DeepMind has released Nano Banana 2 Lite and Gemini Omni Flash. The former is the fastest model in the Nano Banana family.

    Why it matters: Both models are available to developers, with details on latency, pricing, and capability limits to help assess the cost and usability of the image-to-video pipeline.

4/23Thu
  1. Google Research60

    Google Photos adds Auto frame, using generative AI to change the viewpoint within a photo

    Google Research has announced a way to adjust viewpoint after a photo is taken in Google Photos' Auto frame feature. It treats the photo as a 3D scene and automatically changes the virtual camera position and focal length. The two-step method first uses an internal 3D point-map estimation model to reconstruct people and faces and estimate the original camera focal length, then uses a generative latent-diffusion model to fill blank areas revealed by the new view. For photos with people, the feature now automatically offers a second, reconstructed version that can correct perspective distortion in wide-angle selfies.

    Why it matters: Google Photos combines 3D-scene estimation with generative inpainting, showing how a new post-capture viewpoint-editing workflow is implemented.

You've reached the end