👨🏻‍🔧 Anyone who’s used Flux Kontext knows that these kinds of tasks usually require a specific “relighting LoRA” or “Put it here” to work reliably. 🫵 But with Qwen-Image-Edit, you don’t need that. Since it’s a Powerful prompt-based Edit Model, the prompt itself is the key. Try

🧑‍💻 The images you input into the Draw Things Canvas need to be prepared in advance with an image editing tool. You can keep the white edges, or remove them—it’s optional. 💡 Here are the Prompts for these four sample images, which might give you some inspiration: —————— 🔷

@drawthingsapp You rock!

@drawthingsapp Not all of them work perfectly, especially on high-noise, low-light photos. Qwen actually produces strange, plastic-like renderings. Nano Banana handles that quite well

@drawthingsapp Have you a ComfyUI wf?

@drawthingsapp great. 👍

🚨China just put out an incredible new image editing model beats Google’s Nanobanana to be #1 in image editing! Bytedance Seedream 4 is better at: —2K resolution < 2s. 4K support. 🍌 is low res —Much more lax policy on generations —Generate multiple images at once in a set! —Far

Seedream 4.0 is #1 in the Artificial Analysis Image Editing Leaderboard, and has pushed forward the state of the art along with the recent Gemini 2.5 Flash Image (Nano-Banana) release! We've compiled some examples so you can see for yourself just how much they've improved over

Qwen-Image InstantX Inpainting ControlNet is natively supported in ComfyUI Professional inpainting & image editing capabilities now available! 🔹 Object replacement 🔹 Text modification 🔹 Background changes 🔹 Outpainting Perfect for precise image edits with Qwen-Image's

yet ANOTHER release from ByteDance just landed on the hub ✨HuMo✨ > video generation w/ multi-modal conditioning: audio, text & image > supports consistent subject preservation, synchronized audio-driven motion > based on Wan 2.1 & Whisper Large v3