FireRedTeam/FireRed-Image-Edit

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1341 stars · 79 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

FireRed-Image-Edit is an open-source image editing foundation model built on diffusion models, released as PyTorch model weights with inference code and a LoRA fine-tuning zoo. It achieves state-of-the-art instruction-based image editing with precise instruction following, high-fidelity generation, identity consistency, and multi-element fusion.

Use cases

• edit photos with natural language instructions
• instruction-based image editing model
• change objects in an image while keeping identity consistent
• fuse multiple image elements into one picture
• fine-tune an image editing model with LoRA
• run a state-of-the-art open-source image2image diffusion model

When to choose

• you need an open-source, instruction-following image editing model with high fidelity and identity consistency
• you want to fine-tune or adapt an image editing model via LoRA on your own data
• you need reproducible benchmarks for instruction-based image editing (REDEdit-Bench)
• your stack is Python/PyTorch with GPU resources available

When to avoid

• you need a polished end-user photo editor GUI rather than a model and inference code
• you have no GPU or cannot run large diffusion models locally
• you need text-to-image generation from scratch rather than editing existing images
• you require a permissive setup without downloading large model weights from Hugging Face

Facets

library · maturity active

image-processing machine-learning deep-learning image-processing artificial-intelligence deep-learning python cross-platform diffusion-models image-editing image2image instruction-following aigc pytorch generative-ai lora model-weights huggingface gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="FireRedTeam/FireRed-Image-Edit")