Download
1 variant available
509
2.4K
Move, rotate, or reframe objects in a photo with a text instruction
Open this ready-to-run workflow on Floyo. No install needed.
HOW IT WORKS
Step 1. Upload your picture. The image you want edited. Works great with: product shots · characters · interiors · concept art
Step 2. Describe the change. Write the edit in plain language. Spatial instructions land the best, like "rotate the chair to show the front view," "move the cup to the left edge of the table," or "add wings to the man."
Step 3. Hit run and download. The model reads the scene and applies the edit. Preview it in the workflow, then download. Ready for: Photoshop · Figma · Canva · any editor
First time? Leave every setting as-is. The defaults (1920 x 1280 · 40 steps · CFG 4 · fixed seed) are the right starting point for almost everyone.
Overview
This workflow edits an image from a spatial text instruction using JoyAI Image Edit, an open-weight model from JD Open Source, the open-source arm of JD.com. Spatial understanding is what sets it apart. The model parses the scene first, works out where each object sits and how they relate, then applies your instruction to the right region. That makes it strong at edits most models fumble: rotating a product, sliding an object across the frame, changing the camera angle, and generating a new viewpoint from a single still, all while the rest of the scene holds. It pairs an 8B Qwen 3 VL encoder with a 16B diffusion transformer, 24B total. You upload a picture, describe the change, and get the edit back in about 2 minutes. No setup, no nodes to wire.
Who it's for: product teams, designers, and VFX artists who want spatial, instruction-based editing in ComfyUI without wiring the nodes from scratch. Not for: face and identity work or close-up skin detail. Use a Qwen Image Edit workflow for those, and reach for JoyAI when the edit is about position, angle, or viewpoint.
Why Floyo
Floyo is the only ComfyUI platform built for teams in the browser.
Made for teams. Share run history, files, and models across your whole team. A teammate opens your exact run and picks up where you left off. No file handoffs, no version confusion.
No install, no setup. Every workflow and model is preloaded. Open it in your browser and run. Nothing to download, nothing to configure.
No local hardware. Workflows run on H100 NVL GPUs, so heavy models run fast without a card of your own. Your VRAM stops being the limit.
Open and closed models in one place. Floyo runs open-source workflows and API models side by side.
How to use (in your browser on Floyo)
Upload the picture you want to edit.
Describe the change, naming the object, the direction, and the angle or distance, then run.
Download the edited image, ready for any editor.
Expectations The models are preloaded, so there is nothing to download. Running it needs a free Floyo account. This is a 24B model running 40 undistilled steps, so each edit takes about 2 minutes. A few things decide the result. Be literal with spatial edits: "move the cup 3 centimetres to the left" beats "adjust the cup," so name the object, the direction, and the distance or angle. Say what stays fixed alongside what changes. Keep steps at 25 or higher, since below 20 the picture softens. If the edit drifts from your instruction, raise CFG one point at a time. JoyAI Image Edit is Apache 2.0 licensed, so your edits are yours to use commercially, with no revenue threshold and no territory limits.
Use Cases
Spatial Repositioning. Move, rotate, or resize an object in a shot without redoing the render or the photo.
Product Multi-View. Generate alternate angles of a product from a single reference image for listings and catalogs.
Scene Composition. Add or remove elements from a frame, like placing wings on a character or clearing clutter from a set.
Camera Angle Changes. Shift the perspective on a scene from a single still, producing a new viewpoint without reshooting.
What can JoyAI Image Edit reposition?
