Model reference · open weights

RORem-mixed

RORem-mixed is an open-weight image model from mayocream, 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.

Image mayocream 1 variants 36k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What RORem-mixed is

RORem-mixed GGUF (Q4K) This repository contains a Q4K GGUF conversion of the RORem-mixed SDXL inpainting UNet for stable-diffusion.cpp. RORem is an object-removal/inpainting model from RORem: Training a Robust Object Remover with Human-in-the-Loop. The mixed-resolution checkpoint was trained for both 512x512 and 1024x1024 inputs. Files This is not a complete SDXL pipeline. It does not include the VAE, CLIP-L, or CLIP-G weights. Use those components from diffusers/stable-diffusion-xl-1.0-inpainting-0.1. stable-diffusion.cpp usage The model was converted and tested with the official CUDA prebuilt from stable-diffusion.cpp release master-782-b290693. The white portion of the mask is regenerated. For manga translation, dilating the text or SFX mask before inference helps remove outlines and antialiasing remnants. Local benchmark Single 512x512 manga inpainting crop, 30 Euler steps, fixed seed, RTX 5090, stable-diffusion.cpp CUDA build b290693: This is one local sample, not a comprehensive quality benchmark. Q4K was effectively tied with Q40 in speed while producing an output closer to the FP16 reference. Limitations - RORem can hallucinate texture, line art, or objects inside large masks. - Output quality depends strongly on mask dilation, crop context, resolution, prompt, and seed. - This checkpoint is intended for inpainting/object removal, not general text-to-image generation. - The quantized model may differ from FP16 output. Attribution and licenses - RORem project and original checkpoint: leeruibin/RORem, published by its authors under Apache 2.0. - SDXL inpainting base: diffusers/stable-diffusion-xl-1.0-inpainting-0.1, licensed under CreativeML Open RAIL++-M. - Inference runtime: stable-diffusion.cpp. Users are responsible for complying with all applicable upstream licenses and usage restrictions. Citation

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makermayocream
TypeImage models
Variants1
Runs withstable-diffusion.cpp
Based onLetsThink/RORem, diffusers/stable-diffusion-xl-1.0-inpainting-0.1
Released2026-07-19
Popularity36k downloads / month
Likes5
LicenceOpen weights

How it works

How image models work

Text promptwhat to makeText encoderunderstands itDiffusion stepsdenoise to pixelsImagePNG / JPEGA diffusion model starts from noise and denoises it, guided by your prompt, into a finished image.

Variants

Sizes & precisions

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.

VariantParamsPrecisionVRAMFits 16 GBWeights
RORem-mixed-GGUFGGUFWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys rorem-mixed for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (rorem-mixed 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":"rorem-mixed","prompt":"a red bicycle","size":"1024x1024"}'

Details

Languages, data & research

Tags

stable-diffusion.cpp gguf stable-diffusion-xl sdxl inpainting object-removal manga image-to-image

Licence

Open weights

Open weights under openrail++ — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want RORem-mixed on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More image models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms