# ali-vilab/In-Context-LoRA

Official repository of In-Context LoRA for Diffusion Transformers

Repository: https://github.com/ali-vilab/In-Context-LoRA
Canonical: https://ross.abutalabs.com/products/in-context-lora
License Family: other
Last push: 2024-12-20T03:17:01+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 47
- inputs: {"age_days": 670, "days_push": 621, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2083, forks 95 (observed 2026-08-28T04:06:11.772148+00:00)

## What it is
Official repository for In-Context LoRA (IC-LoRA), a framework for adapting Diffusion Transformers to diverse visual generation tasks via LoRA fine-tuning. It provides pretrained models, training configurations, and ComfyUI workflows for tasks like film storyboard generation and visual identity design.

## Use cases
- generate film storyboards with diffusion transformers
- fine-tune LoRA adapters for image generation tasks
- create visual identity designs with AI
- run IC-LoRA models in ComfyUI
- benchmark zero-shot task generalization of generative models
- train custom LoRA models on paired image data

## When to choose
- you want pretrained LoRA models for Diffusion Transformers covering tasks like storyboard generation or visual design
- you need training data and configs to fine-tune diffusion models for custom visual generation tasks
- you use ComfyUI and want workflows for in-context image generation

## When to avoid
- you need a production-ready image editing application with a polished UI
- you work with non-diffusion model architectures or non-visual tasks
- you require a commercially licensed, fully supported product - the repo has no explicit license

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, stable-diffusion, llm-training
- domain: artificial-intelligence, image-processing, deep-learning
- platform: python, cross-platform
- tags: diffusion-transformers, lora, text-to-image, image-generation, comfyui, model-zoo, research, gpu

## Member repositories
- ali-vilab/In-Context-LoRA (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:11.772148+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 2026-08-30T02:55:53.092484+00:00, confidence not recorded.
  - readme: https://github.com/ali-vilab/In-Context-LoRA (fetched 2026-08-28T04:06:11.772148+00:00, sha 282a2ccbe300)
- Data as of 2026-08-30T08:39:29.467469+00:00.