unslothai/unsloth · error · ValueError

{state.family.name} is an image-editing model and does not s

Error message

{state.family.name} is an image-editing model and does not support masks (mask_image).

What it means

Edit-capable families have no inpaint pipeline, so a mask_image would be silently dropped if accepted. This ValueError rejects a request that supplies mask_image to an editing family before any work starts, telling the caller to use the instruction prompt instead of a mask.

Source

Thrown at studio/backend/core/inference/diffusion.py:5362

                        raise ValueError("mask_image requires an input image (init_image).")
                    if upscale is not None and upscale > 1.0:
                        raise ValueError("upscale requires an input image (init_image).")
                    if reference_images:
                        raise ValueError("reference_images require an input image (init_image).")
                if reference_images and not getattr(state.family, "reference", False):
                    raise ValueError(
                        f"Reference images are not supported for the '{state.family.name}' "
                        "model family."
                    )
                if getattr(state.family, "edit", False):
                    # Instruction editing: the loaded pipe IS the edit pipeline and always needs an input image; the prompt is the instruction.
                    if init_image is None:
                        raise ValueError(
                            f"{state.family.name} is an image-editing model: provide an input image."
                        )
                    if mask_image is not None:
                        # The edit family has no inpaint pipeline; a mask would be silently dropped.
                        raise ValueError(
                            f"{state.family.name} is an image-editing model and does not "
                            "support masks (mask_image)."
                        )
                    workflow = "edit"
                    init_pil = decode_b64_image(init_image, mode = "RGB")
                elif mask_image is not None and init_image is not None:
                    workflow = "inpaint"
                    pipe = self._workflow_pipe(state, state.family.inpaint_pipeline_class, workflow)
                    init_pil = decode_b64_image(init_image, mode = "RGB")
                    mask_pil = decode_b64_image(mask_image, mode = "L")
                elif init_image is not None and upscale is not None and upscale > 1.0:
                    # Upscale (hires fix): enlarge with Lanczos, then re-run img2img at low strength to add detail.
                    workflow = "upscale"
                    pipe = self._workflow_pipe(state, state.family.img2img_pipeline_class, workflow)
                    init_pil = decode_b64_image(init_image, mode = "RGB")
                    iw, ih = init_pil.size
                    # Cap the factor, then the absolute output (longest side 2048); round to a multiple of 16 (VAE downsample + patch).
                    factor = max(1.0, min(float(upscale), 4.0))

View on GitHub (pinned to 203007d190)

Solutions

1. Remove mask_image and express the edit through the prompt instruction (e.g. 'replace the masked region concept' via natural language).
2. Load an inpaint-capable family if mask-based editing is required.

Example fix

# before
engine.generate(prompt="repaint", init_image=img, mask_image=mask)
# after (edit family)
engine.generate(prompt="change the hair color to red", init_image=img)

if getattr(loaded_family, "edit", False) and mask_image is not None:
    raise UserError("Edit models take instructions, not masks: remove mask_image.")

def family_accepts_mask(family) -> bool:
    return not bool(getattr(family, "edit", False))

try:
    out = engine.generate(prompt=p, init_image=img, mask_image=mask)
except ValueError as e:
    if "does not support masks" in str(e):
        out = engine.generate(prompt=mask_intent_as_instruction, init_image=img)
    else:
        raise

When it happens

Trigger: A request with mask_image set while the loaded family has edit=True (the mask+init_image combination would normally select the inpaint workflow, which does not exist for edit families).

Common situations: Porting an inpainting workflow (mask + init image) to a newer instruction-editing model and assuming mask semantics carry over; UI state where an old painted mask is still attached after loading an edit model.

Related errors

• mask_image requires an input image (init_image).
• {state.family.name} is an image-editing model: provide an in
• Unknown model_kind '{model_kind}'. Expected one of {sorted(_
• Invalid base64 image data: {exc}
• Image is too large ({w}x{h}); maximum is {max_side}px per si

AI-assisted analysis of unslothai/unsloth@203007d190 (2026-08-15). Data as JSON: /api/errors/6389a573a3e5cc14. Report an issue: GitHub.