Latest: Tencent Launches Hunyuan Image 3.5 for 2K Reference-Following Generation
The model's reference-following capability and 2K output quality are available at a low per-generation cost, which according to one account enables iterative prompting rather than careful one-shot prompting.
When stories like this move, I write about them in an email each morning.
One free email each morning, around 8 AM US Eastern.
I have sent you a confirmation link. One click and you are in.
Not in your inbox? Look in spam or promotions. If it's there, mark it "Not spam" so future editions land in your inbox.
Tencent released Hunyuan Image 3.5 (also referred to as Hy Image3.5 Preview), an image generation model that produces output up to 2K resolution and accepts both text prompts and reference images as input. The model supports up to 5 reference inputs per generation. OnSolo is offering the model at 1 credit per generation, with free access for members for 2 weeks.
Tencent released Hunyuan Image 3.5 on September 23, an image generation model producing output up to 2K resolution that accepts up to 5 reference images alongside text prompts.
Rohan Paul said the model is "genuinely pretty good at following references and keeping the image polished, especially at 2K". OnSolo is offering access at 1 credit per generation with a 2-week free period for members, which Paul noted "makes it cheap enough to iterate instead of overthinking every prompt".
BackgroundFrontier models, open models, and how they are compared
When stories like this move, I write about them in an email each morning.
One free email each morning, around 8 AM US Eastern.
I have sent you a confirmation link. One click and you are in.
Not in your inbox? Look in spam or promotions. If it's there, mark it "Not spam" so future editions land in your inbox.