汇集视觉、图像生成、视频生成、语音与多模态模型新消息。
## Highlights - `Client` accepts `StdioServerParameters` directly: `Client(StdioServerParameters(command="uv", args=["run", "server.py"]))` (#3321). - Prompt messages accept `Image` and `Audio`, prompt functions may return bare content blocks, and `Message` /
## What's Changed * fix(gemini): remove unsupported $schema from tool parameters by @qbc2016 in https://github.com/agentscope-ai/agentscope/pull/2277 * feat(workspace): share workspace across different agents by @iluv7 in https://github.com/agentscope-ai/agent
来源标注日期：2026-08-21（未提供具体时刻）。 Today, the new multimodal vision understanding model DeepSeek-V4-Flash-Vision-Exp is now available on the DeepSeek API platform. This is an experimental model that can be accessed by setting model='deepseek-v4-flash-vision-exp'. Ter
NVIDIA Ising Calibration is an open source vision language model (VLM) designed to interpret diagnostic outputs from quantum processors and determine how they...
The demand for high-quality video continues to accelerate across industries, powering everything from immersive streaming experiences to remote collaboration,...
Video is a core data path across NVIDIA Jetson applications, from robotics and intelligent video analytics to industrial automation, healthcare, media...
Modern vision-language models (VLMs) can support tasks such as visual question answering, captioning, and image-text reasoning. In practice, however, the data...
Status: Resolved All impacted services have now fully recovered. Affected components Conversations (Operational) Image Generation (Operational) ChatGPT Work (Operational)
模型仓库动态。仓库创建：2026-08-19T16:40:35.000Z。最后修改：2026-08-19T23:46:54.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：zero-shot-image-classification。
模型仓库动态。仓库创建：2026-08-19T16:41:21.000Z。最后修改：2026-08-19T23:46:54.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：zero-shot-image-classification。
模型仓库动态。仓库创建：2026-08-19T14:56:11.000Z。最后修改：2026-08-19T23:46:53.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：zero-shot-image-classification。
模型仓库动态。仓库创建：2026-08-19T15:02:28.000Z。最后修改：2026-08-19T23:46:53.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：zero-shot-image-classification。
模型仓库动态。仓库创建：2026-08-19T14:43:49.000Z。最后修改：2026-08-19T23:46:52.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：zero-shot-image-classification。
模型仓库动态。仓库创建：2026-08-19T14:48:47.000Z。最后修改：2026-08-19T23:46:52.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：zero-shot-image-classification。
an illustrated image with icons and phrasing like "Add Notebook" and "Ask Google" Here’s how you can use Google Search tools to study for classes and standardized tests.
# Patch release v5.15.1 This patch most notably solves a few issues with DFlash and MTP candidate generators, as well as an issue where images could sometimes not be processed on accelerator if using Lanczos filter. It contains the following commits: - Fix DFl
模型仓库动态。仓库创建：2026-04-09T06:29:07.000Z。最后修改：2026-08-17T16:43:16.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：zero-shot-image-classification。
模型仓库动态。仓库创建：2026-04-09T05:55:21.000Z。最后修改：2026-08-17T16:43:12.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：zero-shot-image-classification。
模型仓库动态。仓库创建：2026-04-09T06:29:08.000Z。最后修改：2026-08-17T16:43:08.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：zero-shot-image-classification。
模型仓库动态。仓库创建：2026-08-05T08:22:59.000Z。最后修改：2026-08-14T15:00:01.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
模型仓库动态。仓库创建：2026-08-13T08:01:58.000Z。最后修改：2026-08-14T14:44:41.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
模型仓库动态。仓库创建：2026-08-04T09:24:18.000Z。最后修改：2026-08-14T13:03:03.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
模型仓库动态。仓库创建：2026-07-29T13:07:51.000Z。最后修改：2026-08-14T13:02:45.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-text。
模型仓库动态。仓库创建：2026-08-07T12:23:29.000Z。最后修改：2026-08-14T10:51:40.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：text-to-audio。
## What's Changed * Fix KSamplerAdvanced with add_noise disabled on nested latents by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15447 * Update workflow templates to v0.11.40 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15522 * chore:
The video shows Sheets canvas in action. Sheets canvas turns data into interactive dashboards, custom study trackers, seating charts, and more, all with a simple prompt.
模型仓库动态。仓库创建：2026-07-28T10:45:18.000Z。最后修改：2026-08-13T01:46:29.000Z。仓库修改不等同于模型正式发布。 数据经第三方 Hugging Face 镜像采集，需以原始模型页面复核。 任务：image-text-to-video。
## What's Changed * Make it easier to debug nested tensors. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15383 * Update workflow templates to v0.11.37 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15415 * Minimum officially s
### Summary of major features and improvements * #### More GenAI coverage and framework integrations to minimize code changes * New models supported: * On CPU, GPU, and NPU: SmolLM3-3B, LFM2-1.2B, LFM2.5-1.2B * On CPU and GPU: Harrier OSS-v1-0.6B, Qwen3-8B wit
# Highlights *582 PRs from 194 contributors.* **Kimi K3 day-0 support**: A 2.8T-parameter multimodal LatentMoE (896 experts, top-16, routed in a 3584-dim latent space) with a 1M-token context, 69 KDA linear-attention layers interleaved with 24 MLA layers, and
