Model reference · open weights
FireRed-Image-Edit-1.1 is an open-weight image model from FireRedTeam. FireRed-Image-Edit-1.1 (BF16) weighs 57.7 GB; the smallest configuration that runs it is H100 80 GB.
FireRed-Image-Edit-1.1 is a 20.4B parameter image-to-image model developed by FireRedTeam for general-purpose image editing. It supports English and Chinese and is released under the apache-2.0 license. The model features enhanced identity consistency, multi-image conditioning, and domain-specialized editing capabilities.
Summary of the FireRedTeam/FireRed-Image-Edit-1.1 model card, 2026-10-01
What it is
| Released by | FireRedTeam |
|---|---|
| Type | Image models |
| Task | Image edit |
| Parameters (lead) | 20.4B |
| Runs with | diffusers |
| Released | 2026-03-02 |
| Popularity | 12k downloads / month |
| Weights | 57.7 GB (FireRed-Image-Edit-1.1 (BF16), file size) |
| Licence | Open weights |
What it runs on
Weights 57.7 GB (file size) · its biggest part 40.9 GB · working memory for one 1024×1024 image about 5.0 GB · overhead about 537 MB.
| Card | One 1024×1024 image | Counted memory |
|---|---|---|
| RTX 3060 12 GB … L40S 48 GB | does not fit | |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
Estimates, not measurements: the weights are the build's file size; one 1024×1024 image needs about 5 GB of working memory (larger images more); "encoders offloaded" means only the biggest part is on the card at once — diffusers' model offload, or ComfyUI unloading the text encoder. diffusers can also place a pipeline's parts on separate cards (device_map) — not estimated here. Counted memory is 92 % of what CUDA reports for the card.
From the model card
🤗 HuggingFace | 🤖 ModelScope | 🖥️ Demo | 📄 Technical Report
We introduce FireRed-Image-Edit-1.1, an upgrade to our general-purpose image editing foundation model. Building upon the capabilities presented in the FireRed-Image-Edit-1.0 Technical Report, version 1.1 significantly enhances identity consistency, multi-image conditioning, and domain-specialized editing performance, bringing the model closer to real-world creative production needs.
Some real outputs produced by FireRed-Image-Edit across general editing.
FireRed-Image-Edit establishes a new state-of-the-art among open-source models on Imgedit, Gedit, and RedEdit, while surpassing our closed-source competitors in specific dimensions—a distinction further corroborated by human evaluations highlighting its superior prompt following and visual consistency.
Quoted from the model card on Hugging Face — the full card is behind the Hugging Face link above.
Running it yourself
Rent a machine by the hour. Runs as it is with diffusers — on the machine, in Python.
# on your rented machine: pip install diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
pipe = DiffusionPipeline.from_pretrained("FireRedTeam/FireRed-Image-Edit-1.1", torch_dtype=torch.bfloat16).to("cuda")
start = load_image("/workspace/in.png")
image = pipe(prompt="the same scene at golden hour", image=start).images[0]
image.save("/workspace/out.png")