Too lazy to write a prompt? Just use an image instead.The vision is powered by <a target="_blank" rel="ugc" href="https://comfy.org/workflows/llm_qwen3_5_text_gen-aeb71e383642/">Qwen 3.5</a> with the <a target="_blank" rel="ugc" href="https://civarchive.com/models/2998872/qwen-image-21-turbo-int8-workflow-text-to-image">int8 workflow </a>of Qwen image 2.1.Performance 1024x1024: About 9 seconds 5070ti, 18 seconds 5060ti 16g (2Nd gen/warm).<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e1f52898-5d8b-4382-84df-eaac10e0db64/original=true/e1f52898-5d8b-4382-84df-eaac10e0db64.jpeg" />

Files with SHA256: 8c3ac757c2356b92ff34b4afa74d43c748f7ebdc8b3d24957dc39de28f00d214