Remove Background: RMBG 3.0
Download Workflow
Download JSON or search “Remove Background: RMBG 3.0” in Template Library
Diffusion Model
rmbg3_int8_convrot.safetensors → ComfyUI/models/diffusion_models/
Text Encoder
qwen3vl_4b_int8_convrot.safetensors → ComfyUI/models/text_encoders/
VAE
flux2-vae.safetensors → ComfyUI/models/vae/
withered_hydrangeas_still_life_vintage_lit.png
Load into the
LoadImage node- Drop your photo into the
LoadImagenode. - Turn on
auto_prompt, which is off in the shipped template. With it off, the node sends the fixed instruction andsubject_noteis unused. - Optional: write one short sentence about the material in
subject_note, for exampleClear glass bottle, paper label, metal cap. - Run the workflow.
SaveImagewrites both results underComfyUI/output/rmbg3/.
Workflow controls
auto_prompt: when on, a vision model writes the matting instruction from the image and yoursubject_note. When off, the fixed instruction the model was trained on is sent as is andsubject_noteis ignored.cfg: keep it at 1.0. The model is distilled without guidance, so a higher value trades fidelity to the source for transparency.alpha_brightness,alpha_contrast,mask_threshold,hard_mask: matte post-processing. Leavehard_maskoff to keep soft edges.mask_expand,mask_tapered_corners: grow and round the matte before it is applied.
When the cutout is wrong
Two limits come from the model itself: very busy or low-contrast scenes can pull in grass, props, or a watermark next to the subject, and fine structures such as insect wings can lose pixels.