A LoRA for Qwen-Image-2.1 called "Doodle In", allowing doodling in anything while maintaining the art style.
This gives you flexibility and image editing controls that were difficult with prompts alone. Edit in 6-steps using Viggle
URL in reply below猬囷笍
5 years ago, we released @Gradio to make it easier to build frontends for AI apps. At that time, that was the main blocker for making AI more accessible to the community. But this is no longer a challenge. So we asked ourselves and other developers: "what are the main challenges
Give Qwen-Image 2.1 one transparent cutout and say "rotate the camera 90 degrees to the right".
It hands back the same object from the new angle, still transparent. No background removal, no 3D model.
A LoRA, trained by ML-Intern for under $20. 馃У
Qwen-Image 2.1 draws its best pictures when a 9B "prompt rewriter" expands your request first. That is 20 GB in bf16 and uses 1700 words as system prompt, and thinks for ~1,600 tokens before answering.
We shrank it to 0.8B. It fits on a laptop now. 馃У
