# johannakarras/DreamPose

Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"

Repository: https://github.com/johannakarras/DreamPose
Canonical: https://ross.abutalabs.com/products/dreampose
Language: Python
License: MIT
License Family: permissive
Last push: 2023-11-02T00:46:11+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 90
- inputs: {"age_days": 1261, "days_push": 1036, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1004, forks 79 (observed 2026-09-03T02:15:13.176556+00:00)

## What it is
Official PyTorch implementation of DreamPose, a Stable Diffusion-based model that synthesizes animated fashion videos from a single image and a pose sequence. It includes pretrained models, demo scripts, and finetuning pipelines for subject-specific video generation.

## Use cases
- animate a fashion photo into a video
- image-to-video synthesis with stable diffusion
- generate fashion model motion from pose sequences
- finetune stable diffusion for video generation
- research code for DreamPose paper

## When to choose
- you want to animate a single fashion image into a video using pose sequences
- you need the official DreamPose research implementation with pretrained checkpoints
- you want to finetune Stable Diffusion for subject-specific video synthesis

## When to avoid
- you need general-purpose text-to-video generation
- you lack GPU resources, as training requires multiple A100 GPUs
- you want a production-ready application rather than research code

## Facets
- artifact type: library
- maturity: maintenance
- function: video-processing, image-processing, machine-learning, deep-learning, llm-inference
- domain: deep-learning, computer-vision, image-processing, artificial-intelligence
- platform: python
- tags: stable-diffusion, image-to-video, fashion-synthesis, diffusion-models, research-code, pose-driven-animation, video, linux, gpu

## Member repositories
- johannakarras/DreamPose (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:13.176556+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:13:45.255817+00:00, confidence not recorded.
  - readme: https://github.com/johannakarras/DreamPose (fetched 2026-09-03T02:15:13.176556+00:00, sha a743f63b4b63)
- Data as of 2026-08-30T08:39:29.467469+00:00.