Hy Image3.5 preview is on OnSolo, free for Members for two weeks

TTencent Hy9/23/2026, 00:07:07

OnSoloAI says its exclusive Hy Image3.5 preview is on OnSolo, supports 5 refs and 2K, and is free for Members for two weeks.

Tencent Hy says the preview is live on OnSolo for short-drama character sheets, full-motion video game assets, and keyframes. Tencent Hy also says characters hold across every episode and that edits refine instead of restarting.

#hy-image3.5 #onsolo #tencent-hy #image-generation

View original post ↗

Previous articleOpenClaw’s next version uses a decision model to choose steer or queue Next articleShanghai AI Lab and SJTU's LUMIA Lab release 8.9B open-weight model NCP-ArchPreview

Related AI news

Hy Image 3.5 preview is live on GMI Cloud at $0.024 per image

GMI Cloud is offering the Hy Image 3.5 preview at $0.024 per image, a rate it says is 8.8x cheaper than GPT Image 2 and 5.6x cheaper than Nano Banana Pro.

TTencent Hy•9/24/2026, 02:05:29•

#hy-image #gmi-cloud #image-generation #pricing

Tencent Hy Translation launches with offline on-device Hy-MT2

Tencent Hy Translation, powered by Hy-MT2, covers 33 languages, including five Chinese minority languages and dialects, and supports voice and photo translation fully offline on device. Tencent Hy says it is already live in 12 countries and regions.

TTencent Hy•9/24/2026, 00:16:25•

#tencent-hy #hy-mt2 #machine-translation #on-device

Tencent Hy extends critical-batch-size theory to online LLM RL

Tencent Hy says learning-rate retuning can preserve learning per response across GRPO and PPO over a bounded range of batch sizes. On fixed hardware, larger batches improve PPO generation-stage throughput by up to 2.29×, and its best measured GRPO configuration reaches the same validation target in 29% less time.

TTencent Hy•9/23/2026, 19:33:18•

#tencent-hy #llm-reinforcement-learning #critical-batch-size #grpo #ppo

Hy Image3.5 preview is available in ComfyUI

ComfyUI has made the Hy Image3.5 preview available for text-to-image and image-to-image generation at up to 2K. ComfyUI says it has a +30% win rate against Hy Image3.0 in human evaluation.

TTencent Hy•9/22/2026, 19:34:59•

#hy-image3.5 #comfyui #image-generation #text-to-image

Tencent Hunyuan says Hy Image3.5 preview is live at $0.024 per image

Tencent Hunyuan said Hy Image3.5 preview is live, with text-to-image and image-to-image generation up to 2K. Tencent Cloud API pricing is $0.024 per generated image, and it offered two weeks free only on OnSolo and Miora.

TTencent Hy•9/21/2026, 19:58:05•

#hunyuan #image-generation #tencent-cloud #api-pricing

Reset history AI News FAQ Usage limits RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.

Data & original project: Did Codex Reset · Licoy