invoke-ai/InvokeAI · error · ValueError

Control weights must be within -1 to 2 range

Error message

Control weights must be within -1 to 2 range

What it means

InvokeAI validates control (ControlNet) and IP-Adapter weights via validate_weights, requiring each weight to lie within [-1, 2]. Values outside that range would produce degenerate conditioning or are simply unsupported, so a ValueError is raised.

Source

Thrown at invokeai/app/invocations/util.py:8

from typing import Union


def validate_weights(weights: Union[float, list[float]]) -> None:
    """Validate that all control weights in the valid range"""
    to_validate = weights if isinstance(weights, list) else [weights]
    if any(i < -1 or i > 2 for i in to_validate):
        raise ValueError("Control weights must be within -1 to 2 range")


def validate_begin_end_step(begin_step_percent: float, end_step_percent: float) -> None:
    """Validate that begin_step_percent is less than or equal to end_step_percent"""
    if begin_step_percent > end_step_percent:
        raise ValueError("Begin step percent must be less than or equal to end step percent")

View on GitHub (pinned to 0b6a024f2f)

Solutions

1. Clamp each weight into the [-1, 2] range (e.g. 2.0 instead of 3)
2. For lists, ensure every element is within range
3. If stronger effect is needed, stack multiple control adapters rather than exceeding the weight cap

Example fix

// before
validate_ip_adapter_weight(2.5)
// after
validate_ip_adapter_weight(min(max(w, -1.0), 2.0) for each w)  # e.g. 2.0

def validate_weights_client(weights):
    vals = weights if isinstance(weights, list) else [weights]
    if any(w < -1 or w > 2 for w in vals):
        raise ValueError("Control weights must be within -1 to 2 range")
    return weights

def weights_in_range(weights) -> bool:
    vals = weights if isinstance(weights, list) else [weights]
    return all(isinstance(w, (int, float)) and -1 <= w <= 2 for w in vals)

try:
    invocation.invoke(context)
except ValueError as e:
    if "Control weights must be within -1 to 2 range" in str(e):
        invocation.control_weight = [min(max(w, -1.0), 2.0) for w in weights]
        invocation.invoke(context)
    else:
        raise

When it happens

Trigger: Calling validate_control_weight or validate_ip_adapter_weight with weight=-1.5, 2.5, or a list containing any element outside [-1, 2]; e.g. controlnet weight field set to 3 in a workflow.

Common situations: Trying aggressive negative conditioning (< -1) to suppress a concept; typing 20 instead of 2.0; copying weights from other tools that allow a wider range.

Related errors

• The Anima ControlNet-LLLite model '{lllite_field.control_mod
• This Anima ControlNet-LLLite adapter is an inpainting adapte
• Unsupported Anima ControlNet-LLLite adapter: expected 3 or 4
• denoising_start ({self.denoising_start}) must be less than d
• LoRA "{lora_key}" already applied to transformer.

AI-assisted analysis of invoke-ai/InvokeAI@0b6a024f2f (2026-08-29). Data as JSON: /api/errors/df866e056af893df. Report an issue: GitHub.