Model reference · open weights
FireRed-Image-Ed-1.0 is an open-weight image model from FireRedTeam, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
🤗 <a href="https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.0"HuggingFace</a | 🖥️ <a href="https://huggingface.co/spaces/FireRedTeam/FireRed-Image-Edit-1.0" Demo</a | 📄 <a href="https://github.com/FireRedTeam/FireRed-Image-Edit/blob/main/assets/FireRedImageEdit10TechinicalReport.pdf"Technical Report</a 🔥 FireRed-Image-Edit FireRed-Image-Edit is a general-purpose image editing model that delivers high-fidelity and consistent editing across a wide range of scenarios. ✨ Key Features - Strong Editing Performance: FireRed-Image-Edit delivers leading open-source results with accurate instruction following, high image quality, and consistent visual coherence. - Native Editing Capability: Built directly from text-to-image foundation model and endowed with editing capabilities. - Text Style Preservation: Maintains text styles with high fidelity, achieving performance comparable to closed-source solutions. - Photo Restoration: High-quality old photo restoration and enhancement. - Multi-Image Editing: Flexible editing of multiple images such as virtual try-on. 📰 News - 2026.02.14: We released FireRed-Image-Edit-1.0 model weights. Check more details in the Model Zoo section. - 2026.02.10: We released the Technical Report of FireRed-Image-Edit-1.0. 🎨 Showcase Some real outputs produced by FireRed-Image-Edit across genearl editing. 🗂️ Model Zoo 🏗️ Model Architecture ⚡️ Quick Start 1. Install the latest version of diffusers 2. Use the following code snippets to generate or edit images. 📊 Benchmark To better validate the capabilities of our model, we propose a benchmark called REDEdit-Bench. Our main goal is to build more diverse scenarios and editing instructions that better align with human language, enabling a more comprehensive evaluation of current editing models. We collected over 3,000 images from the internet, and after careful expert-designed selection, we constructed 1,673 bilingual (Chinese–English) editing pairs across 15 categories. Inference and Evaluation Code We provide the inference and evaluation code for REDEdit-Bench. Please refer to the redbenchinfer.py and redbencheval.py scripts in the src/tools directory for more details. Benchmark Distribution Th
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | FireRedTeam |
|---|---|
| Type | Image models |
| Parameters (lead) | 20.4B |
| Variants | 1 |
| Runs with | diffusers |
| Released | 2026-02-12 |
| Popularity | 28k downloads / month |
| Likes | 348 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| FireRed-Image-Edit-1.0 | 20.4B | BF16 | ~47 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys firered-image-ed-1-0 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (firered-image-ed-1-0 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"firered-image-ed-1-0","prompt":"a red bicycle","size":"1024x1024"}'
Details
Languages
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗