soCzech/ShowHowTo
Code for the paper "ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions" published at CVPR 2025
This project helps generate clear, visual, step-by-step instructions for a task, based on an existing image or scene. You provide an initial image and a text prompt describing the desired steps, and it creates a sequence of images that visually show how to achieve each step. This is useful for anyone who needs to create dynamic visual guides, such as educators demonstrating practical skills or marketers showcasing product assembly.
No commits in the last 6 months.
Use this if you need to transform a single image or scene and a set of instructions into an animated sequence that visually walks someone through each step.
Not ideal if you're looking to generate video from scratch without a specific starting image, or if your instructions are purely conceptual without a visual outcome.
Stars
21
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/soCzech/ShowHowTo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...